Azure AI Foundry 中的 Azure OpenAI 模型 REST API 预览版参考

本文详细介绍了 Azure OpenAI 的推理 REST API 端点。

API 规范

管理 Azure OpenAI 模型和资源并与之交互分为三个主要 API 图面：

• 控制面板
• 数据平面 - 创作
• 数据平面 - 推理

每个 API 图面/规范封装了一组不同的 Azure OpenAI 功能。 每个 API 都有自己独特的预览版和稳定/正式发布 (GA) API 版本集。 预览版目前按月发布。

Authentication

Azure OpenAI 提供两种身份验证方法。 可以使用 API 密钥或 Microsoft Entra ID。

• API 密钥身份验证：对于这种类型的身份验证，所有 API 请求都必须在 api-key HTTP 标头中包含 API 密钥。 本快速入门提供有关如何通过此类身份验证进行调用的指南。

• Microsoft Entra ID 身份验证：可以使用 Microsoft Entra 令牌对 API 调用进行身份验证。 身份验证令牌作为 Authorization 标头包含在请求中。 提供的令牌必须以 Bearer 开头，例如 Bearer YOUR_AUTH_TOKEN。 可以阅读有关如何使用 Microsoft Entra ID 进行身份验证的操作指南。

REST API 版本控制

服务 API 使用 api-version 查询参数进行版本控制。 所有版本都遵循 YYYY-MM-DD 日期结构。 例如：

POST https://YOUR_RESOURCE_NAME.openai.azure.com/openai/deployments/YOUR_DEPLOYMENT_NAME/chat/completions?api-version=2024-06-01

数据平面推理

本文的其余部分介绍了 2025-04-01-preview Azure OpenAI 数据平面推理规范的预览版本。

若要查找有关最新 GA API 版本的文档，请参阅最新 GA 数据平面推理 API

补全 - 创建

POST https://{endpoint}/openai/deployments/{deployment-id}/completions?api-version=2025-04-01-preview

为提供的提示、参数和所选模型创建补全。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

请求主体

“内容类型”: application/json

Responses

状态代码：200

说明：确定

状态代码：默认值

说明：服务不可用

Examples

Example

为提供的提示、参数和所选模型创建补全。

POST https://{endpoint}/openai/deployments/{deployment-id}/completions?api-version=2025-04-01-preview

{
 "prompt": [
  "tell me a joke about mango"
 ],
 "max_tokens": 32,
 "temperature": 1.0,
 "n": 1
}

响应：状态代码：200

{
  "body": {
    "id": "cmpl-7QmVI15qgYVllxK0FtxVGG6ywfzaq",
    "created": 1686617332,
    "choices": [
      {
        "text": "es\n\nWhat do you call a mango who's in charge?\n\nThe head mango.",
        "index": 0,
        "finish_reason": "stop",
        "logprobs": null
      }
    ],
    "usage": {
      "completion_tokens": 20,
      "prompt_tokens": 6,
      "total_tokens": 26
    }
  }
}

嵌入 - 创建

POST https://{endpoint}/openai/deployments/{deployment-id}/embeddings?api-version=2025-04-01-preview

获取给定输入的向量表示形式，该输入可由机器学习模型和算法轻松使用。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

请求主体

“内容类型”: application/json

Responses

状态代码：200

说明：确定

Examples

Example

返回给定提示的嵌入。

POST https://{endpoint}/openai/deployments/{deployment-id}/embeddings?api-version=2025-04-01-preview

{
 "input": [
  "this is a test"
 ]
}

响应：状态代码：200

{
  "body": {
    "data": [
      {
        "index": 0,
        "embedding": [
          -0.012838088,
          -0.007421397,
          -0.017617522,
          -0.028278312,
          -0.018666342,
          0.01737855,
          -0.01821495,
          -0.006950092,
          -0.009937238,
          -0.038580645,
          0.010674067,
          0.02412286,
          -0.013647936,
          0.013189907,
          0.0021125758,
          0.012406612,
          0.020790534,
          0.00074595667,
          0.008397198,
          -0.00535031,
          0.008968075,
          0.014351576,
          -0.014086051,
          0.015055214,
          -0.022211088,
          -0.025198232,
          0.0065186154,
          -0.036350243,
          0.009180495,
          -0.009698266,
          0.009446018,
          -0.008463579,
          -0.0020113448
        ]
      }
    ],
    "usage": {
      "prompt_tokens": 4,
      "total_tokens": 4
    }
  }
}

聊天补全 - 创建

POST https://{endpoint}/openai/deployments/{deployment-id}/chat/completions?api-version=2025-04-01-preview

为聊天消息创建完成操作

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

请求主体

“内容类型”: application/json

Responses

状态代码：200

说明：确定

状态代码：默认值

说明：服务不可用

Examples

Example

为提供的提示、参数和所选模型创建补全。

POST https://{endpoint}/openai/deployments/{deployment-id}/chat/completions?api-version=2025-04-01-preview

{
 "messages": [
  {
   "role": "system",
   "content": "you are a helpful assistant that talks like a pirate"
  },
  {
   "role": "user",
   "content": "can you tell me how to care for a parrot?"
  }
 ]
}

响应：状态代码：200

{
  "body": {
    "id": "chatcmpl-7R1nGnsXO8n4oi9UPz2f3UHdgAYMn",
    "created": 1686676106,
    "choices": [
      {
        "index": 0,
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": "Ahoy matey! So ye be wantin' to care for a fine squawkin' parrot, eh? Well, shiver me timbers, let ol' Cap'n Assistant share some wisdom with ye! Here be the steps to keepin' yer parrot happy 'n healthy:\n\n1. Secure a sturdy cage: Yer parrot be needin' a comfortable place to lay anchor! Be sure ye get a sturdy cage, at least double the size of the bird's wingspan, with enough space to spread their wings, yarrrr!\n\n2. Perches 'n toys: Aye, parrots need perches of different sizes, shapes, 'n textures to keep their feet healthy. Also, a few toys be helpin' to keep them entertained 'n their minds stimulated, arrrh!\n\n3. Proper grub: Feed yer feathered friend a balanced diet of high-quality pellets, fruits, 'n veggies to keep 'em strong 'n healthy. Give 'em fresh water every day, or ye\u00e2\u20ac\u2122ll have a scurvy bird on yer hands!\n\n4. Cleanliness: Swab their cage deck! Clean their cage on a regular basis: fresh water 'n food daily, the floor every couple of days, 'n a thorough scrubbing ev'ry few weeks, so the bird be livin' in a tidy haven, arrhh!\n\n5. Socialize 'n train: Parrots be a sociable lot, arrr! Exercise 'n interact with 'em daily to create a bond 'n maintain their mental 'n physical health. Train 'em with positive reinforcement, treat 'em kindly, yarrr!\n\n6. Proper rest: Yer parrot be needin' \u00e2\u20ac\u2122bout 10-12 hours o' sleep each night. Cover their cage 'n let them slumber in a dim, quiet quarter for a proper night's rest, ye scallywag!\n\n7. Keep a weather eye open for illness: Birds be hidin' their ailments, arrr! Be watchful for signs of sickness, such as lethargy, loss of appetite, puffin' up, or change in droppings, and make haste to a vet if need be.\n\n8. Provide fresh air 'n avoid toxins: Parrots be sensitive to draft and pollutants. Keep yer quarters well ventilated, but no drafts, arrr! Be mindful of toxins like Teflon fumes, candles, or air fresheners.\n\nSo there ye have it, me hearty! With proper care 'n commitment, yer parrot will be squawkin' \"Yo-ho-ho\" for many years to come! Good luck, sailor, and may the wind be at yer back!"
        }
      }
    ],
    "usage": {
      "completion_tokens": 557,
      "prompt_tokens": 33,
      "total_tokens": 590
    }
  }
}

Example

基于 Azure 认知搜索数据和系统分配的托管标识创建补全。

POST https://{endpoint}/openai/deployments/{deployment-id}/chat/completions?api-version=2025-04-01-preview

{
 "messages": [
  {
   "role": "user",
   "content": "can you tell me how to care for a dog?"
  }
 ],
 "data_sources": [
  {
   "type": "azure_search",
   "parameters": {
    "endpoint": "https://your-search-endpoint.search.windows.net/",
    "index_name": "{index name}",
    "authentication": {
     "type": "system_assigned_managed_identity"
    }
   }
  }
 ]
}

响应：状态代码：200

{
  "body": {
    "id": "chatcmpl-7R1nGnsXO8n4oi9UPz2f3UHdgAYMn",
    "created": 1686676106,
    "choices": [
      {
        "index": 0,
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": "Content of the completion [doc1].",
          "context": {
            "citations": [
              {
                "content": "Citation content.",
                "title": "Citation Title",
                "filepath": "contoso.txt",
                "url": "https://contoso.blob.windows.net/container/contoso.txt",
                "chunk_id": "0"
              }
            ],
            "intent": "dog care"
          }
        }
      }
    ],
    "usage": {
      "completion_tokens": 557,
      "prompt_tokens": 33,
      "total_tokens": 590
    }
  }
}

Example

基于 Azure 认知搜索图像矢量数据创建补全。

POST https://{endpoint}/openai/deployments/{deployment-id}/chat/completions?api-version=2025-04-01-preview

{
 "messages": [
  {
   "role": "user",
   "content": "can you tell me how to care for a dog?"
  }
 ],
 "data_sources": [
  {
   "type": "azure_search",
   "parameters": {
    "endpoint": "https://your-search-endpoint.search.windows.net/",
    "index_name": "{index name}",
    "query_type": "vector",
    "fields_mapping": {
     "image_vector_fields": [
      "image_vector"
     ]
    },
    "authentication": {
     "type": "api_key",
     "key": "{api key}"
    }
   }
  }
 ]
}

响应：状态代码：200

{
  "body": {
    "id": "chatcmpl-7R1nGnsXO8n4oi9UPz2f3UHdgAYMn",
    "created": 1686676106,
    "choices": [
      {
        "index": 0,
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": "Content of the completion."
        }
      }
    ],
    "usage": {
      "completion_tokens": 557,
      "prompt_tokens": 33,
      "total_tokens": 590
    }
  }
}

Example

基于 Azure 认知搜索矢量数据、以前的助手消息和用户分配的托管标识创建补全。

POST https://{endpoint}/openai/deployments/{deployment-id}/chat/completions?api-version=2025-04-01-preview

{
 "messages": [
  {
   "role": "user",
   "content": "can you tell me how to care for a cat?"
  },
  {
   "role": "assistant",
   "content": "Content of the completion [doc1].",
   "context": {
    "intent": "cat care"
   }
  },
  {
   "role": "user",
   "content": "how about dog?"
  }
 ],
 "data_sources": [
  {
   "type": "azure_search",
   "parameters": {
    "endpoint": "https://your-search-endpoint.search.windows.net/",
    "authentication": {
     "type": "user_assigned_managed_identity",
     "managed_identity_resource_id": "/subscriptions/{subscription-id}/resourceGroups/{resource-group}/providers/Microsoft.ManagedIdentity/userAssignedIdentities/{resource-name}"
    },
    "index_name": "{index name}",
    "query_type": "vector",
    "embedding_dependency": {
     "type": "deployment_name",
     "deployment_name": "{embedding deployment name}"
    },
    "in_scope": true,
    "top_n_documents": 5,
    "strictness": 3,
    "role_information": "You are an AI assistant that helps people find information.",
    "fields_mapping": {
     "content_fields_separator": "\\n",
     "content_fields": [
      "content"
     ],
     "filepath_field": "filepath",
     "title_field": "title",
     "url_field": "url",
     "vector_fields": [
      "contentvector"
     ]
    }
   }
  }
 ]
}

响应：状态代码：200

{
  "body": {
    "id": "chatcmpl-7R1nGnsXO8n4oi9UPz2f3UHdgAYMn",
    "created": 1686676106,
    "choices": [
      {
        "index": 0,
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": "Content of the completion [doc1].",
          "context": {
            "citations": [
              {
                "content": "Citation content 2.",
                "title": "Citation Title 2",
                "filepath": "contoso2.txt",
                "url": "https://contoso.blob.windows.net/container/contoso2.txt",
                "chunk_id": "0"
              }
            ],
            "intent": "dog care"
          }
        }
      }
    ],
    "usage": {
      "completion_tokens": 557,
      "prompt_tokens": 33,
      "total_tokens": 590
    }
  }
}

Example

为提供的 Azure Cosmos DB 创建补全。

POST https://{endpoint}/openai/deployments/{deployment-id}/chat/completions?api-version=2025-04-01-preview

{
 "messages": [
  {
   "role": "user",
   "content": "can you tell me how to care for a dog?"
  }
 ],
 "data_sources": [
  {
   "type": "azure_cosmos_db",
   "parameters": {
    "authentication": {
     "type": "connection_string",
     "connection_string": "mongodb+srv://rawantest:{password}$@{cluster-name}.mongocluster.cosmos.azure.com/?tls=true&authMechanism=SCRAM-SHA-256&retrywrites=false&maxIdleTimeMS=120000"
    },
    "database_name": "vectordb",
    "container_name": "azuredocs",
    "index_name": "azuredocindex",
    "embedding_dependency": {
     "type": "deployment_name",
     "deployment_name": "{embedding deployment name}"
    },
    "fields_mapping": {
     "content_fields": [
      "content"
     ],
     "vector_fields": [
      "contentvector"
     ]
    }
   }
  }
 ]
}

响应：状态代码：200

{
  "body": {
    "id": "chatcmpl-7R1nGnsXO8n4oi9UPz2f3UHdgAYMn",
    "created": 1686676106,
    "choices": [
      {
        "index": 0,
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": "Content of the completion [doc1].",
          "context": {
            "citations": [
              {
                "content": "Citation content.",
                "title": "Citation Title",
                "filepath": "contoso.txt",
                "url": "https://contoso.blob.windows.net/container/contoso.txt",
                "chunk_id": "0"
              }
            ],
            "intent": "dog care"
          }
        }
      }
    ],
    "usage": {
      "completion_tokens": 557,
      "prompt_tokens": 33,
      "total_tokens": 590
    }
  }
}

Example

为提供的 Mongo DB 创建补全。

POST https://{endpoint}/openai/deployments/{deployment-id}/chat/completions?api-version=2025-04-01-preview

{
 "messages": [
  {
   "role": "user",
   "content": "can you tell me how to care for a dog?"
  }
 ],
 "data_sources": [
  {
   "type": "mongo_db",
   "parameters": {
    "authentication": {
     "type": "username_and_password",
     "username": "<username>",
     "password": "<password>"
    },
    "endpoint": "<endpoint_name>",
    "app_name": "<application name>",
    "database_name": "sampledb",
    "collection_name": "samplecollection",
    "index_name": "sampleindex",
    "embedding_dependency": {
     "type": "deployment_name",
     "deployment_name": "{embedding deployment name}"
    },
    "fields_mapping": {
     "content_fields": [
      "content"
     ],
     "vector_fields": [
      "contentvector"
     ]
    }
   }
  }
 ]
}

响应：状态代码：200

{
  "body": {
    "id": "chatcmpl-7R1nGnsXO8n4oi9UPz2f3UHdgAYMn",
    "created": 1686676106,
    "choices": [
      {
        "index": 0,
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": "Content of the completion [doc1].",
          "context": {
            "citations": [
              {
                "content": "Citation content.",
                "title": "Citation Title",
                "filepath": "contoso.txt",
                "url": "https://contoso.blob.windows.net/container/contoso.txt",
                "chunk_id": "0"
              }
            ],
            "intent": "dog care"
          }
        }
      }
    ],
    "usage": {
      "completion_tokens": 557,
      "prompt_tokens": 33,
      "total_tokens": 590
    }
  }
}

Example

为提供的 Elasticsearch 创建补全。

POST https://{endpoint}/openai/deployments/{deployment-id}/chat/completions?api-version=2025-04-01-preview

{
 "messages": [
  {
   "role": "user",
   "content": "can you tell me how to care for a dog?"
  }
 ],
 "data_sources": [
  {
   "type": "elasticsearch",
   "parameters": {
    "endpoint": "https://your-elasticsearch-endpoint.eastus.azurecontainer.io",
    "index_name": "{index name}",
    "authentication": {
     "type": "key_and_key_id",
     "key": "{key}",
     "key_id": "{key id}"
    }
   }
  }
 ]
}

响应：状态代码：200

{
  "body": {
    "id": "chatcmpl-7R1nGnsXO8n4oi9UPz2f3UHdgAYMn",
    "created": 1686676106,
    "choices": [
      {
        "index": 0,
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": "Content of the completion [doc1].",
          "context": {
            "citations": [
              {
                "content": "Citation content.",
                "title": "Citation Title",
                "filepath": "contoso.txt",
                "url": "https://contoso.blob.windows.net/container/contoso.txt",
                "chunk_id": "0"
              }
            ],
            "intent": "dog care"
          }
        }
      }
    ],
    "usage": {
      "completion_tokens": 557,
      "prompt_tokens": 33,
      "total_tokens": 590
    }
  }
}

Example

为提供的 Pinecone 资源创建补全。

POST https://{endpoint}/openai/deployments/{deployment-id}/chat/completions?api-version=2025-04-01-preview

{
 "messages": [
  {
   "role": "user",
   "content": "can you tell me how to care for a dog?"
  }
 ],
 "data_sources": [
  {
   "type": "pinecone",
   "parameters": {
    "authentication": {
     "type": "api_key",
     "key": "{api key}"
    },
    "environment": "{environment name}",
    "index_name": "{index name}",
    "embedding_dependency": {
     "type": "deployment_name",
     "deployment_name": "{embedding deployment name}"
    },
    "fields_mapping": {
     "title_field": "title",
     "url_field": "url",
     "filepath_field": "filepath",
     "content_fields": [
      "content"
     ],
     "content_fields_separator": "\n"
    }
   }
  }
 ]
}

响应：状态代码：200

{
  "body": {
    "id": "chatcmpl-7R1nGnsXO8n4oi9UPz2f3UHdgAYMn",
    "created": 1686676106,
    "choices": [
      {
        "index": 0,
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": "Content of the completion [doc1].",
          "context": {
            "citations": [
              {
                "content": "Citation content.",
                "title": "Citation Title",
                "filepath": "contoso.txt",
                "url": "https://contoso.blob.windows.net/container/contoso.txt",
                "chunk_id": "0"
              }
            ],
            "intent": "dog care"
          }
        }
      }
    ],
    "usage": {
      "completion_tokens": 557,
      "prompt_tokens": 33,
      "total_tokens": 590
    }
  }
}

听录 - 创建

POST https://{endpoint}/openai/deployments/{deployment-id}/audio/transcriptions?api-version=2025-04-01-preview

将音频转录为输入语言。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

请求主体

Content-Type：multipart/form-data

Responses

状态代码：200

说明：确定

Examples

Example

从提供的语音音频数据中获取转录的文本和关联的元数据。

POST https://{endpoint}/openai/deployments/{deployment-id}/audio/transcriptions?api-version=2025-04-01-preview

响应：状态代码：200

{
  "body": {
    "text": "A structured object when requesting json or verbose_json"
  }
}

Example

从提供的语音音频数据中获取转录的文本和关联的元数据。

POST https://{endpoint}/openai/deployments/{deployment-id}/audio/transcriptions?api-version=2025-04-01-preview

"---multipart-boundary\nContent-Disposition: form-data; name=\"file\"; filename=\"file.wav\"\nContent-Type: application/octet-stream\n\nRIFF..audio.data.omitted\n---multipart-boundary--"

响应：状态代码：200

{
  "type": "string",
  "example": "plain text when requesting text, srt, or vtt"
}

翻译 - 创建

POST https://{endpoint}/openai/deployments/{deployment-id}/audio/translations?api-version=2025-04-01-preview

将输入音频转录并翻译为英语文本。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

请求主体

Content-Type：multipart/form-data

Responses

状态代码：200

说明：确定

Examples

Example

从提供的语音音频数据中获取转录的英语语言文本和关联的元数据。

POST https://{endpoint}/openai/deployments/{deployment-id}/audio/translations?api-version=2025-04-01-preview

"---multipart-boundary\nContent-Disposition: form-data; name=\"file\"; filename=\"file.wav\"\nContent-Type: application/octet-stream\n\nRIFF..audio.data.omitted\n---multipart-boundary--"

响应：状态代码：200

{
  "body": {
    "text": "A structured object when requesting json or verbose_json"
  }
}

Example

从提供的语音音频数据中获取转录的英语语言文本和关联的元数据。

POST https://{endpoint}/openai/deployments/{deployment-id}/audio/translations?api-version=2025-04-01-preview

"---multipart-boundary\nContent-Disposition: form-data; name=\"file\"; filename=\"file.wav\"\nContent-Type: application/octet-stream\n\nRIFF..audio.data.omitted\n---multipart-boundary--"

响应：状态代码：200

{
  "type": "string",
  "example": "plain text when requesting text, srt, or vtt"
}

语音 - 创建

POST https://{endpoint}/openai/deployments/{deployment-id}/audio/speech?api-version=2025-04-01-preview

从输入文本生成音频。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

请求主体

Content-Type：multipart/form-data

Responses

状态代码：200

说明：确定

Examples

Example

从提供的文本合成音频。

POST https://{endpoint}/openai/deployments/{deployment-id}/audio/speech?api-version=2025-04-01-preview

{
 "input": "Hi! What are you going to make?",
 "voice": "fable",
 "response_format": "mp3"
}

响应：状态代码：200

{
  "body": "101010101"
}

生成图像 - 创建

POST https://{endpoint}/openai/deployments/{deployment-id}/images/generations?api-version=2025-04-01-preview

根据给定的 DALLE 或 gpt-image-1 模型部署上的文本描述生成一批图像

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

请求主体

“内容类型”: application/json

Responses

状态代码：200

说明：好的

状态代码：默认值

说明：发生错误。

Examples

Example

根据提示创建图像。

POST https://{endpoint}/openai/deployments/{deployment-id}/images/generations?api-version=2025-04-01-preview

{
 "prompt": "In the style of WordArt, Microsoft Clippy wearing a cowboy hat.",
 "n": 1,
 "style": "natural",
 "quality": "standard"
}

响应：状态代码：200

{
  "body": {
    "created": 1698342300,
    "data": [
      {
        "revised_prompt": "A vivid, natural representation of Microsoft Clippy wearing a cowboy hat.",
        "prompt_filter_results": {
          "sexual": {
            "severity": "safe",
            "filtered": false
          },
          "violence": {
            "severity": "safe",
            "filtered": false
          },
          "hate": {
            "severity": "safe",
            "filtered": false
          },
          "self_harm": {
            "severity": "safe",
            "filtered": false
          },
          "profanity": {
            "detected": false,
            "filtered": false
          },
          "custom_blocklists": {
            "filtered": false,
            "details": []
          }
        },
        "url": "https://dalletipusw2.blob.core.windows.net/private/images/e5451cc6-b1ad-4747-bd46-b89a3a3b8bc3/generated_00.png?se=2023-10-27T17%3A45%3A09Z&...",
        "content_filter_results": {
          "sexual": {
            "severity": "safe",
            "filtered": false
          },
          "violence": {
            "severity": "safe",
            "filtered": false
          },
          "hate": {
            "severity": "safe",
            "filtered": false
          },
          "self_harm": {
            "severity": "safe",
            "filtered": false
          }
        }
      }
    ]
  }
}

图像代系 - 编辑

POST https://{endpoint}/openai/deployments/{deployment-id}/images/edits?api-version=2025-04-01-preview

根据给定 gpt-image-1 模型部署上的文本描述编辑图像

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

请求主体

Content-Type：multipart/form-data

Responses

状态代码：200

说明：好的

状态代码：默认值

说明：发生错误。

列表 - 助手

GET https://{endpoint}/openai/assistants?api-version=2025-04-01-preview

返回助手列表。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

Responses

状态代码：200

说明：确定

Examples

Example

返回助手列表。

GET https://{endpoint}/openai/assistants?api-version=2025-04-01-preview

响应：状态代码：200

{
  "body": {
    "object": "list",
    "data": [
      {
        "id": "asst_abc123",
        "object": "assistant",
        "created_at": 1707257477,
        "name": "Stock Analyst",
        "description": null,
        "model": "gpt-4-1106-preview",
        "instructions": "You are a financial analyst that analyzes stock market prices and other financial data present on user uploaded files or by calling external APIs.",
        "tools": [
          {
            "type": "code_interpreter"
          }
        ],
        "tool_resources": {},
        "metadata": {},
        "top_p": 1.0,
        "temperature": 1.0,
        "response_format": "auto"
      },
      {
        "id": "asst_abc456",
        "object": "assistant",
        "created_at": 1698982718,
        "name": "My Assistant",
        "description": null,
        "model": "gpt-4-turbo",
        "instructions": "You are a helpful assistant designed to make me better at coding!",
        "tools": [],
        "tool_resources": {},
        "metadata": {},
        "top_p": 1.0,
        "temperature": 1.0,
        "response_format": "auto"
      },
      {
        "id": "asst_abc789",
        "object": "assistant",
        "created_at": 1698982643,
        "name": null,
        "description": null,
        "model": "gpt-4-turbo",
        "instructions": null,
        "tools": [],
        "tool_resources": {},
        "metadata": {},
        "top_p": 1.0,
        "temperature": 1.0,
        "response_format": "auto"
      }
    ],
    "first_id": "asst_abc123",
    "last_id": "asst_abc789",
    "has_more": false
  }
}

创建 - 助手

POST https://{endpoint}/openai/assistants?api-version=2025-04-01-preview

使用模型和说明创建助手。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

请求主体

“内容类型”: application/json

Responses

状态代码：200

说明：确定

Examples

Example

使用模型和说明创建助手。

POST https://{endpoint}/openai/assistants?api-version=2025-04-01-preview

{
 "name": "Math Tutor",
 "instructions": "When a customer asks about a specific math problem, use Python to evaluate their query.",
 "tools": [
  {
   "type": "code_interpreter"
  }
 ],
 "model": "gpt-4-1106-preview"
}

响应：状态代码：200

{
  "body": {
    "id": "asst_4nsG2qgNzimRPE7MazXTXbU7",
    "object": "assistant",
    "created_at": 1707295707,
    "name": "Math Tutor",
    "description": null,
    "model": "gpt-4-1106-preview",
    "instructions": "When a customer asks about a specific math problem, use Python to evaluate their query.",
    "tools": [
      {
        "type": "code_interpreter"
      }
    ],
    "metadata": {},
    "top_p": 1.0,
    "temperature": 1.0,
    "response_format": "auto"
  }
}

获取 - 助手

GET https://{endpoint}/openai/assistants/{assistant_id}?api-version=2025-04-01-preview

检索助手。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

Responses

状态代码：200

说明：确定

Examples

Example

检索助手。

GET https://{endpoint}/openai/assistants/{assistant_id}?api-version=2025-04-01-preview

响应：状态代码：200

{
  "body": {
    "id": "asst_abc123",
    "object": "assistant",
    "created_at": 1699009709,
    "name": "HR Helper",
    "description": null,
    "model": "gpt-4-turbo",
    "instructions": "You are an HR bot, and you have access to files to answer employee questions about company policies.",
    "tools": [
      {
        "type": "file_search"
      }
    ],
    "metadata": {},
    "top_p": 1.0,
    "temperature": 1.0,
    "response_format": "auto"
  }
}

修改 - 助手

POST https://{endpoint}/openai/assistants/{assistant_id}?api-version=2025-04-01-preview

修改助手。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

请求主体

“内容类型”: application/json

Responses

状态代码：200

说明：确定

Examples

Example

修改助手。

POST https://{endpoint}/openai/assistants/{assistant_id}?api-version=2025-04-01-preview

{
 "instructions": "You are an HR bot, and you have access to files to answer employee questions about company policies. Always response with info from either of the files.",
 "tools": [
  {
   "type": "file_search"
  }
 ],
 "model": "gpt-4-turbo"
}

响应：状态代码：200

{
  "body": {
    "id": "asst_123",
    "object": "assistant",
    "created_at": 1699009709,
    "name": "HR Helper",
    "description": null,
    "model": "gpt-4-turbo",
    "instructions": "You are an HR bot, and you have access to files to answer employee questions about company policies. Always response with info from either of the files.",
    "tools": [
      {
        "type": "file_search"
      }
    ],
    "tool_resources": {
      "file_search": {
        "vector_store_ids": []
      }
    },
    "metadata": {},
    "top_p": 1.0,
    "temperature": 1.0,
    "response_format": "auto"
  }
}

删除 - 助手

DELETE https://{endpoint}/openai/assistants/{assistant_id}?api-version=2025-04-01-preview

删除助手。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

Responses

状态代码：200

说明：确定

Examples

Example

删除助手。

DELETE https://{endpoint}/openai/assistants/{assistant_id}?api-version=2025-04-01-preview

响应：状态代码：200

{
  "body": {
    "id": "asst_4nsG2qgNzimRPE7MazXTXbU7",
    "object": "assistant.deleted",
    "deleted": true
  }
}

创建 - 线程

POST https://{endpoint}/openai/threads?api-version=2025-04-01-preview

创建线程。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

请求主体

“内容类型”: application/json

Responses

状态代码：200

说明：确定

Examples

Example

创建线程。

POST https://{endpoint}/openai/threads?api-version=2025-04-01-preview

响应：状态代码：200

{
  "body": {
    "id": "thread_v7V4csrNOxtNmgcwGg496Smx",
    "object": "thread",
    "created_at": 1707297136,
    "metadata": {}
  }
}

获取 - 线程

GET https://{endpoint}/openai/threads/{thread_id}?api-version=2025-04-01-preview

检索线程。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

Responses

状态代码：200

说明：确定

Examples

Example

检索线程。

GET https://{endpoint}/openai/threads/{thread_id}?api-version=2025-04-01-preview

响应：状态代码：200

{
  "body": {
    "id": "thread_v7V4csrNOxtNmgcwGg496Smx",
    "object": "thread",
    "created_at": 1707297136,
    "metadata": {},
    "tool_resources": {
      "code_interpreter": {
        "file_ids": []
      }
    }
  }
}

修改 - 线程

POST https://{endpoint}/openai/threads/{thread_id}?api-version=2025-04-01-preview

修改线程。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

请求主体

“内容类型”: application/json

Responses

状态代码：200

说明：确定

Examples

Example

修改线程。

POST https://{endpoint}/openai/threads/{thread_id}?api-version=2025-04-01-preview

{
 "metadata": {
  "modified": "true",
  "user": "abc123"
 }
}

响应：状态代码：200

{
  "body": {
    "id": "thread_v7V4csrNOxtNmgcwGg496Smx",
    "object": "thread",
    "created_at": 1707297136,
    "metadata": {
      "modified": "true",
      "user": "abc123"
    },
    "tool_resources": {}
  }
}

删除 - 线程

DELETE https://{endpoint}/openai/threads/{thread_id}?api-version=2025-04-01-preview

删除线程。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

Responses

状态代码：200

说明：确定

Examples

Example

删除线程。

DELETE https://{endpoint}/openai/threads/{thread_id}?api-version=2025-04-01-preview

响应：状态代码：200

{
  "body": {
    "id": "thread_v7V4csrNOxtNmgcwGg496Smx",
    "object": "thread.deleted",
    "deleted": true
  }
}

列出 - 消息

GET https://{endpoint}/openai/threads/{thread_id}/messages?api-version=2025-04-01-preview

返回给定线程的消息列表。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

Responses

状态代码：200

说明：确定

Examples

Example

列出消息

GET https://{endpoint}/openai/threads/{thread_id}/messages?api-version=2025-04-01-preview

响应：状态代码：200

{
  "body": {
    "object": "list",
    "data": [
      {
        "id": "msg_abc123",
        "object": "thread.message",
        "created_at": 1699016383,
        "assistant_id": null,
        "thread_id": "thread_abc123",
        "run_id": null,
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": {
              "value": "How does AI work? Explain it in simple terms.",
              "annotations": []
            }
          }
        ],
        "attachments": [],
        "metadata": {}
      },
      {
        "id": "msg_abc456",
        "object": "thread.message",
        "created_at": 1699016383,
        "assistant_id": null,
        "thread_id": "thread_abc123",
        "run_id": null,
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": {
              "value": "Hello, what is AI?",
              "annotations": []
            }
          }
        ],
        "attachments": [],
        "metadata": {}
      }
    ],
    "first_id": "msg_abc123",
    "last_id": "msg_abc456",
    "has_more": false
  }
}

创建 - 消息

POST https://{endpoint}/openai/threads/{thread_id}/messages?api-version=2025-04-01-preview

创建消息。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

请求主体

“内容类型”: application/json

Responses

状态代码：200

说明：确定

Examples

Example

创建消息。

POST https://{endpoint}/openai/threads/{thread_id}/messages?api-version=2025-04-01-preview

{
 "role": "user",
 "content": "What is the cube root of the sum of 12, 14, 1234, 4321, 90000, 123213541223, 443123123124, 5423324234, 234324324234, 653434534545, 200000000, 98237432984, 99999999, 99999999999, 220000000000, 3309587702? Give me the answer rounded to the nearest integer without commas or spaces."
}

响应：状态代码：200

{
  "body": {
    "id": "msg_as3XIk1tpVP3hdHjWBGg3uG4",
    "object": "thread.message",
    "created_at": 1707298421,
    "assistant_id": null,
    "thread_id": "thread_v7V4csrNOxtNmgcwGg496Smx",
    "run_id": null,
    "role": "user",
    "content": [
      {
        "type": "text",
        "text": {
          "value": "What is the cube root of the sum of 12, 14, 1234, 4321, 90000, 123213541223, 443123123124, 5423324234, 234324324234, 653434534545, 200000000, 98237432984, 99999999, 99999999999, 220000000000, 3309587702? Give me the answer rounded to the nearest integer without commas or spaces.",
          "annotations": []
        }
      }
    ],
    "attachments": [],
    "metadata": {}
  }
}

获取 - 消息

GET https://{endpoint}/openai/threads/{thread_id}/messages/{message_id}?api-version=2025-04-01-preview

检索消息。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

Responses

状态代码：200

说明：确定

Examples

Example

检索消息。

GET https://{endpoint}/openai/threads/{thread_id}/messages/{message_id}?api-version=2025-04-01-preview

响应：状态代码：200

{
  "body": {
    "id": "msg_as3XIk1tpVP3hdHjWBGg3uG4",
    "object": "thread.message",
    "created_at": 1707298421,
    "thread_id": "thread_v7V4csrNOxtNmgcwGg496Smx",
    "role": "user",
    "content": [
      {
        "type": "text",
        "text": {
          "value": "What is the cube root of the sum of 12, 14, 1234, 4321, 90000, 123213541223, 443123123124, 5423324234, 234324324234, 653434534545, 200000000, 98237432984, 99999999, 99999999999, 220000000000, 3309587702? Give me the answer rounded to the nearest integer without commas or spaces.",
          "annotations": []
        }
      }
    ],
    "file_ids": [],
    "assistant_id": null,
    "run_id": null,
    "metadata": {}
  }
}

修改 - 消息

POST https://{endpoint}/openai/threads/{thread_id}/messages/{message_id}?api-version=2025-04-01-preview

修改消息。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

请求主体

“内容类型”: application/json

Responses

状态代码：200

说明：确定

Examples

Example

修改消息。

POST https://{endpoint}/openai/threads/{thread_id}/messages/{message_id}?api-version=2025-04-01-preview

{
 "metadata": {
  "modified": "true",
  "user": "abc123"
 }
}

响应：状态代码：200

{
  "body": {
    "id": "msg_abc123",
    "object": "thread.message",
    "created_at": 1699017614,
    "assistant_id": null,
    "thread_id": "thread_abc123",
    "run_id": null,
    "role": "user",
    "content": [
      {
        "type": "text",
        "text": {
          "value": "How does AI work? Explain it in simple terms.",
          "annotations": []
        }
      }
    ],
    "file_ids": [],
    "metadata": {
      "modified": "true",
      "user": "abc123"
    }
  }
}

创建 - 线程和运行

POST https://{endpoint}/openai/threads/runs?api-version=2025-04-01-preview

创建线程并在单个请求中运行它。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

请求主体

“内容类型”: application/json

Responses

状态代码：200

说明：确定

Examples

Example

创建线程并在单个请求中运行它。

POST https://{endpoint}/openai/threads/runs?api-version=2025-04-01-preview

{
 "assistant_id": "asst_abc123",
 "thread": {
  "messages": [
   {
    "role": "user",
    "content": "Explain deep learning to a 5 year old."
   }
  ]
 }
}

响应：状态代码：200

{
  "body": {
    "id": "run_abc123",
    "object": "thread.run",
    "created_at": 1699076792,
    "assistant_id": "asst_abc123",
    "thread_id": "thread_abc123",
    "status": "queued",
    "started_at": null,
    "expires_at": 1699077392,
    "cancelled_at": null,
    "failed_at": null,
    "completed_at": null,
    "required_action": null,
    "last_error": null,
    "model": "gpt-4-turbo",
    "instructions": "You are a helpful assistant.",
    "tools": [],
    "tool_resources": {},
    "metadata": {},
    "temperature": 1.0,
    "top_p": 1.0,
    "max_completion_tokens": null,
    "max_prompt_tokens": null,
    "truncation_strategy": {
      "type": "auto",
      "last_messages": null
    },
    "incomplete_details": null,
    "usage": null,
    "response_format": "auto",
    "tool_choice": "auto"
  }
}

列出 - 运行

GET https://{endpoint}/openai/threads/{thread_id}/runs?api-version=2025-04-01-preview

返回属于线程的运行列表。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

Responses

状态代码：200

说明：确定

Examples

Example

返回属于线程的运行列表。

GET https://{endpoint}/openai/threads/{thread_id}/runs?api-version=2025-04-01-preview

响应：状态代码：200

{
  "body": {
    "object": "list",
    "data": [
      {
        "id": "run_abc123",
        "object": "thread.run",
        "created_at": 1699075072,
        "assistant_id": "asst_abc123",
        "thread_id": "thread_abc123",
        "status": "completed",
        "started_at": 1699075072,
        "expires_at": null,
        "cancelled_at": null,
        "failed_at": null,
        "completed_at": 1699075073,
        "last_error": null,
        "model": "gpt-4-turbo",
        "instructions": null,
        "incomplete_details": null,
        "tools": [
          {
            "type": "code_interpreter"
          }
        ],
        "tool_resources": {
          "code_interpreter": {
            "file_ids": [
              "file-abc123",
              "file-abc456"
            ]
          }
        },
        "metadata": {},
        "usage": {
          "prompt_tokens": 123,
          "completion_tokens": 456,
          "total_tokens": 579
        },
        "temperature": 1.0,
        "top_p": 1.0,
        "max_prompt_tokens": 1000,
        "max_completion_tokens": 1000,
        "truncation_strategy": {
          "type": "auto",
          "last_messages": null
        },
        "response_format": "auto",
        "tool_choice": "auto"
      },
      {
        "id": "run_abc456",
        "object": "thread.run",
        "created_at": 1699063290,
        "assistant_id": "asst_abc123",
        "thread_id": "thread_abc123",
        "status": "completed",
        "started_at": 1699063290,
        "expires_at": null,
        "cancelled_at": null,
        "failed_at": null,
        "completed_at": 1699063291,
        "last_error": null,
        "model": "gpt-4-turbo",
        "instructions": null,
        "incomplete_details": null,
        "tools": [
          {
            "type": "code_interpreter"
          }
        ],
        "tool_resources": {
          "code_interpreter": {
            "file_ids": [
              "file-abc123",
              "file-abc456"
            ]
          }
        },
        "metadata": {},
        "usage": {
          "prompt_tokens": 123,
          "completion_tokens": 456,
          "total_tokens": 579
        },
        "temperature": 1.0,
        "top_p": 1.0,
        "max_prompt_tokens": 1000,
        "max_completion_tokens": 1000,
        "truncation_strategy": {
          "type": "auto",
          "last_messages": null
        },
        "response_format": "auto",
        "tool_choice": "auto"
      }
    ],
    "first_id": "run_abc123",
    "last_id": "run_abc456",
    "has_more": false
  }
}

创建 - 运行

POST https://{endpoint}/openai/threads/{thread_id}/runs?api-version=2025-04-01-preview

创建运行。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

请求主体

“内容类型”: application/json

Responses

状态代码：200

说明：确定

Examples

Example

创建运行。

POST https://{endpoint}/openai/threads/{thread_id}/runs?api-version=2025-04-01-preview

{
 "assistant_id": "asst_abc123"
}

响应：状态代码：200

{
  "body": {
    "id": "run_abc123",
    "object": "thread.run",
    "created_at": 1699063290,
    "assistant_id": "asst_abc123",
    "thread_id": "thread_abc123",
    "status": "queued",
    "started_at": 1699063290,
    "expires_at": null,
    "cancelled_at": null,
    "failed_at": null,
    "completed_at": 1699063291,
    "last_error": null,
    "model": "gpt-4-turbo",
    "instructions": null,
    "incomplete_details": null,
    "tools": [
      {
        "type": "code_interpreter"
      }
    ],
    "metadata": {},
    "usage": null,
    "temperature": 1.0,
    "top_p": 1.0,
    "max_prompt_tokens": 1000,
    "max_completion_tokens": 1000,
    "truncation_strategy": {
      "type": "auto",
      "last_messages": null
    },
    "response_format": "auto",
    "tool_choice": "auto"
  }
}

获取 - 运行

GET https://{endpoint}/openai/threads/{thread_id}/runs/{run_id}?api-version=2025-04-01-preview

检索运行。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

Responses

状态代码：200

说明：确定

Examples

Example

启动运行。

GET https://{endpoint}/openai/threads/{thread_id}/runs/{run_id}?api-version=2025-04-01-preview

响应：状态代码：200

{
  "body": {
    "id": "run_HsO8tYM4K5AAMAHgK0J3om8Q",
    "object": "thread.run",
    "created_at": 1707303196,
    "assistant_id": "asst_JtTwHk28cIocgFXZPCBxhOzl",
    "thread_id": "thread_eRNwflE3ncDYak1np6MdMHJh",
    "status": "completed",
    "started_at": 1707303197,
    "expires_at": null,
    "cancelled_at": null,
    "failed_at": null,
    "completed_at": 1707303201,
    "last_error": null,
    "model": "gpt-4-1106-preview",
    "instructions": "You are an AI model that empowers every person and every organization on the planet to achieve more.",
    "tools": [],
    "file_ids": [],
    "metadata": {}
  }
}

修改 - 运行

POST https://{endpoint}/openai/threads/{thread_id}/runs/{run_id}?api-version=2025-04-01-preview

修改运行。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

请求主体

“内容类型”: application/json

Responses

状态代码：200

说明：确定

Examples

Example

修改运行。

POST https://{endpoint}/openai/threads/{thread_id}/runs/{run_id}?api-version=2025-04-01-preview

{
 "metadata": {
  "user_id": "user_abc123"
 }
}

响应：状态代码：200

{
  "body": {
    "id": "run_abc123",
    "object": "thread.run",
    "created_at": 1699075072,
    "assistant_id": "asst_abc123",
    "thread_id": "thread_abc123",
    "status": "completed",
    "started_at": 1699075072,
    "expires_at": null,
    "cancelled_at": null,
    "failed_at": null,
    "completed_at": 1699075073,
    "last_error": null,
    "model": "gpt-4-turbo",
    "instructions": null,
    "incomplete_details": null,
    "tools": [
      {
        "type": "code_interpreter"
      }
    ],
    "tool_resources": {
      "code_interpreter": {
        "file_ids": [
          "file-abc123",
          "file-abc456"
        ]
      }
    },
    "metadata": {
      "user_id": "user_abc123"
    },
    "usage": {
      "prompt_tokens": 123,
      "completion_tokens": 456,
      "total_tokens": 579
    },
    "temperature": 1.0,
    "top_p": 1.0,
    "max_prompt_tokens": 1000,
    "max_completion_tokens": 1000,
    "truncation_strategy": {
      "type": "auto",
      "last_messages": null
    },
    "response_format": "auto",
    "tool_choice": "auto"
  }
}

提交 - 要运行的工具输出

POST https://{endpoint}/openai/threads/{thread_id}/runs/{run_id}/submit_tool_outputs?api-version=2025-04-01-preview

当运行具有 status: "requires_action" 且 required_action.type 为 submit_tool_outputs 时，此终结点可用于在工具调用完成后提交输出。 所有输出都必须在单个请求中提交。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

请求主体

“内容类型”: application/json

Responses

状态代码：200

说明：确定

Examples

Example

当运行具有 status: "requires_action" 且 required_action.type 为 submit_tool_outputs 时，此终结点可用于在工具调用完成后提交输出。 所有输出都必须在单个请求中提交。

POST https://{endpoint}/openai/threads/{thread_id}/runs/{run_id}/submit_tool_outputs?api-version=2025-04-01-preview

{
 "tool_outputs": [
  {
   "tool_call_id": "call_001",
   "output": "70 degrees and sunny."
  }
 ]
}

响应：状态代码：200

{
  "body": {
    "id": "run_123",
    "object": "thread.run",
    "created_at": 1699075592,
    "assistant_id": "asst_123",
    "thread_id": "thread_123",
    "status": "queued",
    "started_at": 1699075592,
    "expires_at": 1699076192,
    "cancelled_at": null,
    "failed_at": null,
    "completed_at": null,
    "last_error": null,
    "model": "gpt-4-turbo",
    "instructions": null,
    "tools": [
      {
        "type": "function",
        "function": {
          "name": "get_current_weather",
          "description": "Get the current weather in a given location",
          "parameters": {
            "type": "object",
            "properties": {
              "location": {
                "type": "string",
                "description": "The city and state, e.g. San Francisco, CA"
              },
              "unit": {
                "type": "string",
                "enum": [
                  "celsius",
                  "fahrenheit"
                ]
              }
            },
            "required": [
              "location"
            ]
          }
        }
      }
    ],
    "metadata": {},
    "usage": null,
    "temperature": 1.0,
    "top_p": 1.0,
    "max_prompt_tokens": 1000,
    "max_completion_tokens": 1000,
    "truncation_strategy": {
      "type": "auto",
      "last_messages": null
    },
    "response_format": "auto",
    "tool_choice": "auto"
  }
}

取消 - 运行

POST https://{endpoint}/openai/threads/{thread_id}/runs/{run_id}/cancel?api-version=2025-04-01-preview

取消 in_progress 的运行。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

Responses

状态代码：200

说明：确定

Examples

Example

取消 in_progress 的运行。

POST https://{endpoint}/openai/threads/{thread_id}/runs/{run_id}/cancel?api-version=2025-04-01-preview

响应：状态代码：200

{
  "body": {
    "id": "run_abc123",
    "object": "thread.run",
    "created_at": 1699076126,
    "assistant_id": "asst_abc123",
    "thread_id": "thread_abc123",
    "status": "cancelling",
    "started_at": 1699076126,
    "expires_at": 1699076726,
    "cancelled_at": null,
    "failed_at": null,
    "completed_at": null,
    "last_error": null,
    "model": "gpt-4-turbo",
    "instructions": "You summarize books.",
    "tools": [
      {
        "type": "file_search"
      }
    ],
    "tool_resources": {
      "file_search": {
        "vector_store_ids": [
          "vs_123"
        ]
      }
    },
    "metadata": {},
    "usage": null,
    "temperature": 1.0,
    "top_p": 1.0,
    "response_format": "auto"
  }
}

列出 - 运行步骤

GET https://{endpoint}/openai/threads/{thread_id}/runs/{run_id}/steps?api-version=2025-04-01-preview

返回属于运行的运行步骤列表。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

Responses

状态代码：200

说明：确定

Examples

Example

返回属于运行的运行步骤列表。

GET https://{endpoint}/openai/threads/{thread_id}/runs/{run_id}/steps?api-version=2025-04-01-preview

响应：状态代码：200

{
  "body": {
    "object": "list",
    "data": [
      {
        "id": "step_abc123",
        "object": "thread.run.step",
        "created_at": 1699063291,
        "run_id": "run_abc123",
        "assistant_id": "asst_abc123",
        "thread_id": "thread_abc123",
        "type": "message_creation",
        "status": "completed",
        "cancelled_at": null,
        "completed_at": 1699063291,
        "expired_at": null,
        "failed_at": null,
        "last_error": null,
        "step_details": {
          "type": "message_creation",
          "message_creation": {
            "message_id": "msg_abc123"
          }
        },
        "usage": {
          "prompt_tokens": 123,
          "completion_tokens": 456,
          "total_tokens": 579
        }
      }
    ],
    "first_id": "step_abc123",
    "last_id": "step_abc456",
    "has_more": false
  }
}

获取 - 运行步骤

GET https://{endpoint}/openai/threads/{thread_id}/runs/{run_id}/steps/{step_id}?api-version=2025-04-01-preview

检索运行步骤。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

Responses

状态代码：200

说明：确定

Examples

Example

检索运行步骤。

GET https://{endpoint}/openai/threads/{thread_id}/runs/{run_id}/steps/{step_id}?api-version=2025-04-01-preview

响应：状态代码：200

{
  "body": {
    "id": "step_abc123",
    "object": "thread.run.step",
    "created_at": 1699063291,
    "run_id": "run_abc123",
    "assistant_id": "asst_abc123",
    "thread_id": "thread_abc123",
    "type": "message_creation",
    "status": "completed",
    "cancelled_at": null,
    "completed_at": 1699063291,
    "expired_at": null,
    "failed_at": null,
    "last_error": null,
    "step_details": {
      "type": "message_creation",
      "message_creation": {
        "message_id": "msg_abc123"
      }
    },
    "usage": {
      "prompt_tokens": 123,
      "completion_tokens": 456,
      "total_tokens": 579
    }
  }
}

列出 - 矢量存储

GET https://{endpoint}/openai/vector_stores?api-version=2025-04-01-preview

返回矢量存储列表。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

Responses

状态代码：200

说明：确定

Examples

Example

返回矢量存储列表。

GET https://{endpoint}/openai/vector_stores?api-version=2025-04-01-preview

响应：状态代码：200

{
  "body": {
    "object": "list",
    "data": [
      {
        "id": "vs_abc123",
        "object": "vector_store",
        "created_at": 1699061776,
        "name": "Support FAQ",
        "bytes": 139920,
        "file_counts": {
          "in_progress": 0,
          "completed": 3,
          "failed": 0,
          "cancelled": 0,
          "total": 3
        }
      },
      {
        "id": "vs_abc456",
        "object": "vector_store",
        "created_at": 1699061776,
        "name": "Support FAQ v2",
        "bytes": 139920,
        "file_counts": {
          "in_progress": 0,
          "completed": 3,
          "failed": 0,
          "cancelled": 0,
          "total": 3
        }
      }
    ],
    "first_id": "vs_abc123",
    "last_id": "vs_abc456",
    "has_more": false
  }
}

创建 - 矢量存储

POST https://{endpoint}/openai/vector_stores?api-version=2025-04-01-preview

创建矢量存储。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

请求主体

“内容类型”: application/json

Responses

状态代码：200

说明：确定

Examples

Example

创建矢量存储。

POST https://{endpoint}/openai/vector_stores?api-version=2025-04-01-preview

响应：状态代码：200

{
  "body": {
    "id": "vs_abc123",
    "object": "vector_store",
    "created_at": 1699061776,
    "name": "Support FAQ",
    "bytes": 139920,
    "file_counts": {
      "in_progress": 0,
      "completed": 3,
      "failed": 0,
      "cancelled": 0,
      "total": 3
    }
  }
}

获取 - 矢量存储

GET https://{endpoint}/openai/vector_stores/{vector_store_id}?api-version=2025-04-01-preview

检索矢量存储。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

Responses

状态代码：200

说明：确定

Examples

Example

检索矢量存储。

GET https://{endpoint}/openai/vector_stores/{vector_store_id}?api-version=2025-04-01-preview

响应：状态代码：200

{
  "body": {
    "id": "vs_abc123",
    "object": "vector_store",
    "created_at": 1699061776
  }
}

修改 - 矢量存储

POST https://{endpoint}/openai/vector_stores/{vector_store_id}?api-version=2025-04-01-preview

修改矢量存储。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

请求主体

“内容类型”: application/json

Responses

状态代码：200

说明：确定

Examples

Example

修改矢量存储。

POST https://{endpoint}/openai/vector_stores/{vector_store_id}?api-version=2025-04-01-preview

{
 "name": "Support FAQ"
}

响应：状态代码：200

{
  "body": {
    "id": "vs_abc123",
    "object": "vector_store",
    "created_at": 1699061776,
    "name": "Support FAQ",
    "bytes": 139920,
    "file_counts": {
      "in_progress": 0,
      "completed": 3,
      "failed": 0,
      "cancelled": 0,
      "total": 3
    }
  }
}

删除 - 矢量存储

DELETE https://{endpoint}/openai/vector_stores/{vector_store_id}?api-version=2025-04-01-preview

删除矢量存储。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

Responses

状态代码：200

说明：确定

Examples

Example

删除矢量存储。

DELETE https://{endpoint}/openai/vector_stores/{vector_store_id}?api-version=2025-04-01-preview

响应：状态代码：200

{
  "body": {
    "id": "vs_abc123",
    "object": "vector_store.deleted",
    "deleted": true
  }
}

列出 - 矢量存储文件

GET https://{endpoint}/openai/vector_stores/{vector_store_id}/files?api-version=2025-04-01-preview

返回矢量存储文件列表。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

Responses

状态代码：200

说明：确定

Examples

Example

返回矢量存储文件列表。

GET https://{endpoint}/openai/vector_stores/{vector_store_id}/files?api-version=2025-04-01-preview

响应：状态代码：200

{
  "body": {
    "object": "list",
    "data": [
      {
        "id": "file-abc123",
        "object": "vector_store.file",
        "created_at": 1699061776,
        "vector_store_id": "vs_abc123"
      },
      {
        "id": "file-abc456",
        "object": "vector_store.file",
        "created_at": 1699061776,
        "vector_store_id": "vs_abc123"
      }
    ],
    "first_id": "file-abc123",
    "last_id": "file-abc456",
    "has_more": false
  }
}

创建 - 矢量存储文件

POST https://{endpoint}/openai/vector_stores/{vector_store_id}/files?api-version=2025-04-01-preview

通过将文件附加到矢量存储来创建矢量存储文件。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

请求主体

“内容类型”: application/json

Responses

状态代码：200

说明：确定

Examples

Example

通过将文件附加到矢量存储来创建矢量存储文件。

POST https://{endpoint}/openai/vector_stores/{vector_store_id}/files?api-version=2025-04-01-preview

{
 "file_id": "file-abc123"
}

响应：状态代码：200

{
  "body": {
    "id": "file-abc123",
    "object": "vector_store.file",
    "created_at": 1699061776,
    "usage_bytes": 1234,
    "vector_store_id": "vs_abcd",
    "status": "completed",
    "last_error": null
  }
}

获取 - 矢量存储文件

GET https://{endpoint}/openai/vector_stores/{vector_store_id}/files/{file_id}?api-version=2025-04-01-preview

检索矢量存储文件。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

Responses

状态代码：200

说明：确定

Examples

Example

检索矢量存储文件。

GET https://{endpoint}/openai/vector_stores/{vector_store_id}/files/{file_id}?api-version=2025-04-01-preview

响应：状态代码：200

{
  "body": {
    "id": "file-abc123",
    "object": "vector_store.file",
    "created_at": 1699061776,
    "vector_store_id": "vs_abcd",
    "status": "completed",
    "last_error": null
  }
}

删除 - 矢量存储文件

DELETE https://{endpoint}/openai/vector_stores/{vector_store_id}/files/{file_id}?api-version=2025-04-01-preview

删除矢量存储文件。 这会从矢量存储中删除文件，但不会删除文件本身。 若要删除该文件，请使用删除文件终结点。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

Responses

状态代码：200

说明：确定

Examples

Example

删除矢量存储文件。 这会从矢量存储中删除文件，但不会删除文件本身。 若要删除该文件，请使用删除文件终结点。

DELETE https://{endpoint}/openai/vector_stores/{vector_store_id}/files/{file_id}?api-version=2025-04-01-preview

响应：状态代码：200

{
  "body": {
    "id": "file_abc123",
    "object": "vector_store.file.deleted",
    "deleted": true
  }
}

Updatevectorstorefileattributes

POST https://{endpoint}/openai/vector_stores/{vector_store_id}/files/{file_id}?api-version=2025-04-01-preview

更新向量存储文件的属性。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

请求主体

“内容类型”: application/json

Responses

状态代码：200

说明：确定

检索矢量存储文件内容

GET https://{endpoint}/openai/vector_stores/{vector_store_id}/files/{file_id}/content?api-version=2025-04-01-preview

检索矢量存储文件的已分析内容。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

Responses

状态代码：200

说明：确定

搜索矢量存储

POST https://{endpoint}/openai/vector_stores/{vector_store_id}/search?api-version=2025-04-01-preview

根据查询和文件属性筛选器，在向量存储库中搜索相关的区块。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

请求主体

“内容类型”: application/json

Responses

状态代码：200

说明：确定

创建 - 矢量存储文件批处理

POST https://{endpoint}/openai/vector_stores/{vector_store_id}/file_batches?api-version=2025-04-01-preview

创建矢量存储文件批处理。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

请求主体

“内容类型”: application/json

Responses

状态代码：200

说明：确定

Examples

Example

创建矢量存储文件批处理。

POST https://{endpoint}/openai/vector_stores/{vector_store_id}/file_batches?api-version=2025-04-01-preview

{
 "file_ids": [
  "file-abc123",
  "file-abc456"
 ]
}

响应：状态代码：200

{
  "id": "vsfb_abc123",
  "object": "vector_store.file_batch",
  "created_at": 1699061776,
  "vector_store_id": "vs_abc123",
  "status": "in_progress",
  "file_counts": {
    "in_progress": 1,
    "completed": 1,
    "failed": 0,
    "cancelled": 0,
    "total": 0
  }
}

获取 - 矢量存储文件批处理

GET https://{endpoint}/openai/vector_stores/{vector_store_id}/file_batches/{batch_id}?api-version=2025-04-01-preview

检索矢量存储文件批处理。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

Responses

状态代码：200

说明：确定

Examples

Example

检索矢量存储文件批处理。

GET https://{endpoint}/openai/vector_stores/{vector_store_id}/file_batches/{batch_id}?api-version=2025-04-01-preview

响应：状态代码：200

{
  "body": {
    "id": "vsfb_abc123",
    "object": "vector_store.file_batch",
    "created_at": 1699061776,
    "vector_store_id": "vs_abc123",
    "status": "in_progress",
    "file_counts": {
      "in_progress": 1,
      "completed": 1,
      "failed": 0,
      "cancelled": 0,
      "total": 0
    }
  }
}

取消 - 矢量存储文件批处理

POST https://{endpoint}/openai/vector_stores/{vector_store_id}/file_batches/{batch_id}/cancel?api-version=2025-04-01-preview

取消矢量存储文件批处理。 这会尝试尽快取消此批处理中的文件处理。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

Responses

状态代码：200

说明：确定

Examples

Example

取消矢量存储文件批处理。 这会尝试尽快取消此批处理中的文件处理。

POST https://{endpoint}/openai/vector_stores/{vector_store_id}/file_batches/{batch_id}/cancel?api-version=2025-04-01-preview

响应：状态代码：200

{
  "body": {
    "id": "vsfb_abc123",
    "object": "vector_store.file_batch",
    "created_at": 1699061776,
    "vector_store_id": "vs_abc123",
    "status": "cancelling",
    "file_counts": {
      "in_progress": 12,
      "completed": 3,
      "failed": 0,
      "cancelled": 0,
      "total": 15
    }
  }
}

列出 - 矢量存储文件批处理文件

GET https://{endpoint}/openai/vector_stores/{vector_store_id}/file_batches/{batch_id}/files?api-version=2025-04-01-preview

返回批处理中的矢量存储文件列表。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

Responses

状态代码：200

说明：确定

Examples

Example

返回矢量存储文件列表。

GET https://{endpoint}/openai/vector_stores/{vector_store_id}/file_batches/{batch_id}/files?api-version=2025-04-01-preview

响应：状态代码：200

{
  "body": {
    "object": "list",
    "data": [
      {
        "id": "file-abc123",
        "object": "vector_store.file",
        "created_at": 1699061776,
        "vector_store_id": "vs_abc123"
      },
      {
        "id": "file-abc456",
        "object": "vector_store.file",
        "created_at": 1699061776,
        "vector_store_id": "vs_abc123"
      }
    ],
    "first_id": "file-abc123",
    "last_id": "file-abc456",
    "has_more": false
  }
}

创建 - Realtimesession

POST https://{endpoint}/openai/realtimeapi/sessions?api-version=2025-04-01-preview

创建临时 API 令牌，以便在客户端应用程序中使用实时 API。 可以配置与 session.update 客户端事件相同的会话参数。 它返回一个会话对象，并且 client_secret 是一个包含可用临时 API 令牌的密钥，该令牌可用于对浏览器客户端进行实时 API 认证。

请求主体

“内容类型”: application/json

Responses

状态代码：200

说明：已成功创建会话。

创建 - Transcriptionrealtimesession

POST https://{endpoint}/openai/realtimeapi/transcription_sessions?api-version=2025-04-01-preview

创建临时 API 令牌，以便在客户端应用程序中使用实时 API，专门用于实时听录。 可以配置与 transcription_session.update 客户端事件相同的会话参数。 它返回一个会话对象，并且 client_secret 是一个包含可用临时 API 令牌的密钥，该令牌可用于对浏览器客户端进行实时 API 认证。

请求主体

“内容类型”: application/json

Responses

状态代码：200

说明：已成功创建会话。

Responses

POST https://{endpoint}/openai/responses?api-version=2025-04-01-preview

创建模型响应。

请求主体

“内容类型”: application/json

Responses

状态代码：200

说明：确定

状态代码：默认值

说明：服务不可用

响应 API - 输入项

GET https://{endpoint}/openai/responses/{response_id}?api-version=2025-04-01-preview

检索具有给定 ID 的模型响应。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

Responses

状态代码：200

说明：确定

状态代码：默认值

说明：服务不可用

删除响应

DELETE https://{endpoint}/openai/responses/{response_id}?api-version=2025-04-01-preview

删除具有给定 ID 的模型响应。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

Responses

状态代码：200

说明：确定

状态代码： 404

说明：找不到

状态代码：默认值

说明：服务不可用

响应 API - 响应项列表

GET https://{endpoint}/openai/responses/{response_id}/input_items?api-version=2025-04-01-preview

返回给定响应的输入项的列表。

URI 参数

请求标头

使用基于令牌的身份验证或 API 密钥。 建议使用基于令牌的身份验证进行身份验证，更安全。

Responses

状态代码：200

说明：确定

Components

errorResponse

errorBase

错误