你当前正在访问 Microsoft Azure Global Edition 技术文档网站。如果需要访问由世纪互联运营的 Microsoft Azure 中国技术文档网站，请访问 https://docs.azure.cn。

适用于 JavaScript 的 Azure AI 代理客户端库 - 版本 1.0.0

2025-07-01

使用 AI Agents 客户端库可以：

使用 Azure AI 代理服务开发代理，利用 OpenAI、Microsoft 和其他 LLM 提供商提供的大量模型、工具和功能生态系统。 Azure AI 代理服务支持为各种生成式 AI 用例构建代理。

注意： 虽然此包可以独立使用，但我们建议使用 Azure AI Projects 客户端库来增强体验。 Projects 库提供了对高级功能的简化访问，例如创建和管理代理、枚举 AI 模型、使用数据集和管理搜索索引、评估生成式 AI 性能以及启用 OpenTelemetry 跟踪。

产品文档 | 样品 | 包（npm） | API 参考文档

入门
主要概念
- 创建和验证客户端
示例
- 代理
  - 使用以下项创建代理：
    - 文件搜索
    - 代码解释器
    - 必应地面
    - Azure AI 搜索
    - 函数调用
  - 使用创建线程
    - 工具资源
  - 使用以下方法创建消息：
    - 文件搜索附件
    - 代码解释器附件
    - 图像输入
  - 执行运行、创建线程和运行，或流
  - 检索消息
  - 检索文件
  - 通过删除资源来拆解
故障排除
参与

入门指南

先决条件

LTS 版本的 Node.js
一个 Azure 订阅。
Azure AI Foundry中的项目。

授权

需要 Entra ID 来验证客户端。应用程序需要实现 TokenCredential 接口的对象。此处的代码示例使用 DefaultAzureCredential。若要使该工作正常，需要：
- Contributor 角色。可以通过 Azure 门户中 Azure AI 项目资源的“访问控制（IAM）”选项卡完成分配的角色。在此处了解有关角色分配的更多信息。
- 已安装 Azure CLI。
- 通过运行 az login登录到 Azure 帐户。
- 请注意，如果有多个 Azure 订阅，则包含 Azure AI 项目资源的订阅必须是默认订阅。运行 az account list --output table 列出所有订阅，并查看默认订阅。运行 az account set --subscription "Your Subscription ID or Name" 以更改默认订阅。

安装软件包

npm install @azure/ai-agents @azure/identity

重要概念

创建客户端并对其进行身份验证

用于 AgentsClient 构造客户端。目前，我们建议您通过 client.agents使用 AgentsClient。

要获取项目终端节点，您可以参考文档。下面我们假设环境变量 PROJECT_ENDPOINT 保存此值。

import { AgentsClient } from "@azure/ai-agents";
import { DefaultAzureCredential } from "@azure/identity";

const projectEndpoint = process.env["PROJECT_ENDPOINT"] || "<project endpoint>";
const modelDeploymentName = process.env["MODEL_DEPLOYMENT_NAME"] || "gpt-4o";
const client = new AgentsClient(projectEndpoint, new DefaultAzureCredential());

例子

代理人

Azure AI Projects 客户端库中的代理旨在促进 AI 项目中的各种交互和操作。它们充当管理和执行任务的核心组件，利用不同的工具和资源来实现特定目标。以下步骤概述了与代理交互的典型顺序。有关其他代理示例，请参阅包示例。

创建代理

下面是有关如何创建代理的示例：

const agent = await client.createAgent("gpt-4o", {
  name: "my-agent",
  instructions: "You are a helpful assistant",
});

若要允许代理访问资源或自定义函数，需要工具。可以将工具传递给 createAgenttools 和 toolResources 参数。

可以使用 ToolSet 执行此操作：

import { ToolSet } from "@azure/ai-agents";

// Upload file for code interpreter tool
const filePath1 = "./data/syntheticCompanyQuarterlyResults.csv";
const fileStream1 = fs.createReadStream(filePath1);
const codeInterpreterFile = await client.files.upload(fileStream1, "assistants", {
  fileName: "myLocalFile",
});
console.log(`Uploaded local file, file ID : ${codeInterpreterFile.id}`);
// Upload file for file search tool
const filePath2 = "./data/sampleFileForUpload.txt";
const fileStream2 = fs.createReadStream(filePath2);
const fileSearchFile = await client.files.upload(fileStream2, "assistants", {
  fileName: "sampleFileForUpload.txt",
});
console.log(`Uploaded file, file ID: ${fileSearchFile.id}`);
// Create vector store for file search tool
const vectorStore = await client.vectorStores
  .createAndPoll({
    fileIds: [fileSearchFile.id],
  })
  .pollUntilDone();
// Create tool set
const toolSet = new ToolSet();
toolSet.addFileSearchTool([vectorStore.id]);
toolSet.addCodeInterpreterTool([codeInterpreterFile.id]);

// Create agent with tool set
const agent = await client.createAgent("gpt-4o", {
  name: "my-agent",
  instructions: "You are a helpful agent",
  tools: toolSet.toolDefinitions,
  toolResources: toolSet.toolResources,
});
console.log(`Created agent, agent ID: ${agent.id}`);

使用文件搜索创建代理

若要按代理执行文件搜索，首先需要上传文件、创建向量存储并将该文件关联到向量存储。下面是一个示例：

import { ToolUtility } from "@azure/ai-agents";

const filePath = "./data/sampleFileForUpload.txt";
const localFileStream = fs.createReadStream(filePath);
const file = await client.files.upload(localFileStream, "assistants", {
  fileName: "sampleFileForUpload.txt",
});
console.log(`Uploaded file, file ID: ${file.id}`);

const vectorStore = await client.vectorStores.create({
  fileIds: [file.id],
  name: "myVectorStore",
});
console.log(`Created vector store, vector store ID: ${vectorStore.id}`);

const fileSearchTool = ToolUtility.createFileSearchTool([vectorStore.id]);

const agent = await client.createAgent("gpt-4o", {
  name: "File Search Agent",
  instructions: "You are helpful agent that can help fetch data from files you know about.",
  tools: [fileSearchTool.definition],
  toolResources: fileSearchTool.resources,
});
console.log(`Created agent, agent ID : ${agent.id}`);

使用代码解释器创建代理

下面是上传文件并将其用于代理的代码解释器的示例：

import { ToolUtility } from "@azure/ai-agents";

const filePath = "./data/syntheticCompanyQuarterlyResults.csv";
const localFileStream = fs.createReadStream(filePath);
const localFile = await client.files.upload(localFileStream, "assistants", {
  fileName: "localFile",
});

console.log(`Uploaded local file, file ID : ${localFile.id}`);

const codeInterpreterTool = ToolUtility.createCodeInterpreterTool([localFile.id]);

// Notice that CodeInterpreter must be enabled in the agent creation, otherwise the agent will not be able to see the file attachment
const agent = await client.createAgent("gpt-4o", {
  name: "my-agent",
  instructions: "You are a helpful agent",
  tools: [codeInterpreterTool.definition],
  toolResources: codeInterpreterTool.resources,
});
console.log(`Created agent, agent ID: ${agent.id}`);

使用必应地面创建代理

若要使代理能够通过必应搜索 API 执行搜索，请使用 ToolUtility.createBingGroundingTool() 以及连接。请参阅此处以了解有关使用 Bing Search 进行 Grounding 的更多信息。

下面是一个示例：

import { ToolUtility } from "@azure/ai-agents";

const connectionId = process.env["AZURE_BING_CONNECTION_ID"] || "<connection-name>";

// Initialize agent bing tool with the connection id
const bingTool = ToolUtility.createBingGroundingTool([{ connectionId: connectionId }]);

// Create agent with the bing tool and process assistant run
const agent = await client.createAgent("gpt-4o", {
  name: "my-agent",
  instructions: "You are a helpful agent",
  tools: [bingTool.definition],
});
console.log(`Created agent, agent ID : ${agent.id}`);

使用 Azure AI 搜索创建代理

Azure AI 搜索是适用于高性能应用程序的企业搜索系统。它与 Azure OpenAI 服务和 Azure 机器学习集成，提供高级搜索技术，如矢量搜索和全文搜索。非常适合知识库见解、信息发现和自动化

下面是集成 Azure AI 搜索的示例：

import { ToolUtility } from "@azure/ai-agents";

const connectionName = process.env["AZURE_AI_SEARCH_CONNECTION_NAME"] || "<connection-name>";

// Initialize Azure AI Search tool
const azureAISearchTool = ToolUtility.createAzureAISearchTool(connectionName, "search-index", {
  queryType: "simple",
  topK: 3,
  filter: "", // Add string here to filter results
  indexConnectionId: connectionName,
  indexName: "search-index",
});

// Create agent with the Azure AI search tool
const agent = await client.createAgent("gpt-4o", {
  name: "my-agent",
  instructions: "You are a helpful agent",
  tools: [azureAISearchTool.definition],
  toolResources: azureAISearchTool.resources,
});
console.log(`Created agent, agent ID : ${agent.id}`);

使用函数调用创建代理

可以通过将回调函数定义为函数工具来增强代理。可以通过 createAgent 和 tools的组合提供这些内容来 toolResources。只有函数定义和说明提供给 createAgent，而不提供实现。 Run 或 event handler of stream 将根据函数定义引发 requires_action 状态。代码必须处理此状态并调用相应的函数。

下面是一个示例：

import {
  FunctionToolDefinition,
  ToolUtility,
  RequiredToolCall,
  ToolOutput,
} from "@azure/ai-agents";

class FunctionToolExecutor {
  private functionTools: {
    func: Function;
    definition: FunctionToolDefinition;
  }[];

  constructor() {
    this.functionTools = [
      {
        func: this.getUserFavoriteCity,
        ...ToolUtility.createFunctionTool({
          name: "getUserFavoriteCity",
          description: "Gets the user's favorite city.",
          parameters: {},
        }),
      },
      {
        func: this.getCityNickname,
        ...ToolUtility.createFunctionTool({
          name: "getCityNickname",
          description: "Gets the nickname of a city, e.g. 'LA' for 'Los Angeles, CA'.",
          parameters: {
            type: "object",
            properties: {
              ___location: { type: "string", description: "The city and state, e.g. Seattle, Wa" },
            },
          },
        }),
      },
      {
        func: this.getWeather,
        ...ToolUtility.createFunctionTool({
          name: "getWeather",
          description: "Gets the weather for a ___location.",
          parameters: {
            type: "object",
            properties: {
              ___location: { type: "string", description: "The city and state, e.g. Seattle, Wa" },
              unit: { type: "string", enum: ["c", "f"] },
            },
          },
        }),
      },
    ];
  }

  private getUserFavoriteCity(): {} {
    return { ___location: "Seattle, WA" };
  }

  private getCityNickname(_location: string): {} {
    return { nickname: "The Emerald City" };
  }

  private getWeather(_location: string, unit: string): {} {
    return { weather: unit === "f" ? "72f" : "22c" };
  }

  public invokeTool(toolCall: RequiredToolCall & FunctionToolDefinition): ToolOutput | undefined {
    console.log(`Function tool call - ${toolCall.function.name}`);
    const args: any[] = [];
    if (toolCall.function.parameters) {
      try {
        const params = JSON.parse(toolCall.function.parameters);
        for (const key in params) {
          if (Object.prototype.hasOwnProperty.call(params, key)) {
            args.push(params[key]);
          }
        }
      } catch (error) {
        console.error(`Failed to parse parameters: ${toolCall.function.parameters}`, error);
        return undefined;
      }
    }
    // Create a mapping of function names to their implementations
    const functionMap = new Map(
      this.functionTools.map((tool) => [tool.definition.function.name, tool.func]),
    );
    const result = functionMap.get(toolCall.function.name)?.(...args);
    return result
      ? {
          toolCallId: toolCall.id,
          output: JSON.stringify(result),
        }
      : {
          toolCallId: toolCall.id,
          output: JSON.stringify({
            error: `No matching tool found for function: ${toolCall.function.name}`,
          }),
        };
  }

  public getFunctionDefinitions(): FunctionToolDefinition[] {
    return this.functionTools.map((tool) => {
      return tool.definition;
    });
  }
}
const functionToolExecutor = new FunctionToolExecutor();
const functionTools = functionToolExecutor.getFunctionDefinitions();
const agent = await client.createAgent("gpt-4o", {
  name: "my-agent",
  instructions:
    "You are a weather bot. Use the provided functions to help answer questions. Customize your responses to the user's preferences as much as possible and use friendly nicknames for cities whenever possible.",
  tools: functionTools,
});
console.log(`Created agent, agent ID: ${agent.id}`);

使用 OpenAPI 创建代理

OpenAPI 规范描述针对特定终结点的 REST作。代理 SDK 可以读取 OpenAPI 规范、从中创建函数，并针对 REST 终结点调用该函数，而无需执行其他客户端。下面是创建 OpenAPI 工具（使用匿名身份验证）的示例：

import { ToolUtility } from "@azure/ai-agents";

// Read in OpenApi spec
const filePath = "./data/weatherOpenApi.json";
const openApiSpec = JSON.parse(fs.readFileSync(filePath, "utf-8"));

// Define OpenApi function
const openApiFunction = {
  name: "getWeather",
  spec: openApiSpec,
  description: "Retrieve weather information for a ___location",
  auth: {
    type: "anonymous",
  },
  default_params: ["format"], // optional
};

// Create OpenApi tool
const openApiTool = ToolUtility.createOpenApiTool(openApiFunction);

// Create agent with OpenApi tool
const agent = await client.createAgent("gpt-4o", {
  name: "myAgent",
  instructions: "You are a helpful agent",
  tools: [openApiTool.definition],
});
console.log(`Created agent, agent ID: ${agent.id}`);

创建线程

对于每个会话或对话，需要一个线程。下面是一个示例：

const thread = await client.threads.create();
console.log(`Created thread, thread ID: ${thread.id}`);

使用工具资源创建线程

在某些情况下，可能需要将特定资源分配给单个线程。为此，请提供 toolResourcesthreads.create 参数。在下面的示例中，创建矢量存储并上传文件，使用 tools 参数启用代理进行文件搜索，然后使用 toolResources 参数将该文件与线程相关联。

import { ToolUtility } from "@azure/ai-agents";

const filePath = "./data/syntheticCompanyQuarterlyResults.csv";
const localFileStream = fs.createReadStream(filePath);
const file = await client.files.upload(localFileStream, "assistants", {
  fileName: "sample_file_for_upload.csv",
});
console.log(`Uploaded file, ID: ${file.id}`);

const vectorStore = await client.agents.vectorStores.create()({
  fileIds: [file.id],
});
console.log(`Created vector store, ID: ${vectorStore.id}`);

const fileSearchTool = ToolUtility.createFileSearchTool([vectorStore.id]);

const agent = await client.agents.createAgent("gpt-4o", {
  name: "myAgent",
  instructions: "You are helpful agent that can help fetch data from files you know about.",
  tools: [fileSearchTool.definition],
});
console.log(`Created agent, agent ID : ${agent.id}`);

// Create thread with file resources.
// If the agent has multiple threads, only this thread can search this file.
const thread = await client.threads.create({ toolResources: fileSearchTool.resources });

列出线程

要列出附加到给定代理的所有线程，请使用 threads.list：

const threads = client.threads.list();
console.log(`Threads for agent ${agent.id}:`);
for await (const t of threads) {
  console.log(`Thread ID: ${t.id}`);
  console.log(`Created at: ${t.createdAt}`);
  console.log(`Metadata: ${t.metadata}`);
  console.log(`---- `);
}

创建消息

若要为助手创建要处理的消息，请将 user 作为 role 传递，并将问题作为 content传递：

const message = await client.messages.create(thread.id, "user", "hello, world!");
console.log(`Created message, message ID: ${message.id}`);

使用文件搜索附件创建邮件

若要将文件附加到消息进行内容搜索，请使用 ToolUtility.createFileSearchTool() 和 attachments 参数：

import { ToolUtility } from "@azure/ai-agents";

const fileSearchTool = ToolUtility.createFileSearchTool();
const message = await client.messages.create(
  thread.id,
  "user",
  "What feature does Smart Eyewear offer?",
  {
    attachments: [
      {
        fileId: file.id,
        tools: [fileSearchTool.definition],
      },
    ],
  },
);

使用代码解释器附件创建消息

若要将文件附加到消息以供数据分析，请使用 ToolUtility.createCodeInterpreterTool() 和 attachment 参数。

下面是一个示例：

import { ToolUtility } from "@azure/ai-agents";

// notice that CodeInterpreter must be enabled in the agent creation,
// otherwise the agent will not be able to see the file attachment for code interpretation
const codeInterpreterTool = ToolUtility.createCodeInterpreterTool();
const agent = await client.agents.createAgent("gpt-4o", {
  name: "my-assistant",
  instructions: "You are helpful assistant",
  tools: [codeInterpreterTool.definition],
});
console.log(`Created agent, agent ID: ${agent.id}`);

const thread = await client.threads.create();
console.log(`Created thread, thread ID: ${thread.id}`);

const message = await client.messages.create(
  thread.id,
  "user",
  "Could you please create a bar chart in the TRANSPORTATION sector for the operating profit from the uploaded CSV file and provide the file to me?",
  {
    attachments: [
      {
        fileId: file.id,
        tools: [codeInterpreterTool.definition],
      },
    ],
  },
);
console.log(`Created message, message ID: ${message.id}`);

使用图像输入创建消息

可以通过以下方式将消息发送到包含映像输入的 Azure 代理：

使用存储为上传文件的图像
使用可通过 URL 访问的公共映像
使用 base64 编码的图像字符串

以下示例演示了 base64 方法：

使用 base64 编码的图像输入创建消息

function imageToBase64DataUrl(imagePath: string, mimeType: string): string {
  try {
    // Read the image file as binary
    const imageBuffer = fs.readFileSync(imagePath);
    // Convert to base64
    const base64Data = imageBuffer.toString("base64");
    // Format as a data URL
    return `data:${mimeType};base64,${base64Data}`;
  } catch (error) {
    console.error(`Error reading image file at ${imagePath}:`, error);
    throw error;
  }
}

// Convert your image file to base64 format
const filePath = "./data/image_file.png";
const imageDataUrl = imageToBase64DataUrl(filePath, "image/png");

// Create a message with both text and image content
console.log("Creating message with image content...");
const inputMessage = "Hello, what is in the image?";
const content = [
  {
    type: "text",
    text: inputMessage,
  },
  {
    type: "image_url",
    image_url: {
      url: imageDataUrl,
      detail: "high",
    },
  },
];

const message = await client.messages.create(thread.id, "user", content);
console.log(`Created message, message ID: ${message.id}`);

创建运行、Run_and_Process或流

下面是在运行完成之前 runs.create 和轮询的示例：

// Create and poll a run
console.log("Creating run...");
const run = await client.runs.createAndPoll(thread.id, agent.id, {
  pollingOptions: {
    intervalInMs: 2000,
  },
  onResponse: (response): void => {
    console.log(`Received response with status: ${response.parsedBody.status}`);
  },
});
console.log(`Run finished with status: ${run.status}`);

若要代表你轮询 SDK，请使用 createThreadAndRun 方法。

下面是一个示例：

const run = await client.runs.createThreadAndRun(agent.id, {
  thread: {
    messages: [
      {
        role: "user",
        content: "hello, world!",
      },
    ],
  },
});

使用流式处理时，也无需考虑轮询。

下面是一个示例：

const streamEventMessages = await client.runs.create(thread.id, agent.id).stream();

事件处理可以按如下方式完成：

import { RunStreamEvent, MessageStreamEvent, ErrorEvent, DoneEvent } from "@azure/ai-agents";

const streamEventMessages = await client.runs.create(thread.id, agent.id).stream();

for await (const eventMessage of streamEventMessages) {
  switch (eventMessage.event) {
    case RunStreamEvent.ThreadRunCreated:
      console.log(`ThreadRun status: ${eventMessage.data.status}`);
      break;
    case MessageStreamEvent.ThreadMessageDelta:
      {
        const messageDelta = eventMessage.data;
        messageDelta.delta.content.forEach((contentPart) => {
          if (contentPart.type === "text") {
            const textContent = contentPart;
            const textValue = textContent.text?.value || "No text";
            console.log(`Text delta received:: ${textValue}`);
          }
        });
      }
      break;
    case RunStreamEvent.ThreadRunCompleted:
      console.log("Thread Run Completed");
      break;
    case ErrorEvent.Error:
      console.log(`An error occurred. Data ${eventMessage.data}`);
      break;
    case DoneEvent.Done:
      console.log("Stream completed.");
      break;
  }
}

检索消息

若要从代理检索消息，请使用以下示例：

const messagesIterator = client.messages.list(thread.id);
const allMessages = [];
for await (const m of messagesIterator) {
  allMessages.push(m);
}
console.log("Messages:", allMessages);

// The messages are following in the reverse order,
// we will iterate them and output only text contents.
const messages = await client.messages.list(thread.id, {
  order: "asc",
});

for await (const dataPoint of messages) {
  const textContent = dataPoint.content.find((item) => item.type === "text");
  if (textContent && "text" in textContent) {
    console.log(`${dataPoint.role}: ${textContent.text.value}`);
  }
}

检索文件

无法检索代理上传的文件。如果用例需要访问代理上传的文件内容，建议保留应用程序可访问的其他副本。但是，代理生成的文件可通过 files.getContent检索。

下面是从消息检索文件 ID 的示例：

import { isOutputOfType, MessageTextContent, MessageImageFileContent } from "@azure/ai-agents";

const messagesIterator = client.messages.list(thread.id);
const allMessages = [];
for await (const m of messagesIterator) {
  allMessages.push(m);
}
console.log("Messages:", allMessages);

// Get most recent message from the assistant
const assistantMessage = allMessages.find((msg) => msg.role === "assistant");
if (assistantMessage) {
  const textContent = assistantMessage.content.find((content) =>
    isOutputOfType<MessageTextContent>(content, "text"),
  ) as MessageTextContent;
  if (textContent) {
    console.log(`Last message: ${textContent.text.value}`);
  }
}

const imageFile = (allMessages[0].content[0] as MessageImageFileContent).imageFile;
const imageFileName = (await client.agents.files.get(imageFile.fileId)).filename;

const fileContent = await (await client.files.getContent(imageFile.fileId).asNodeStream()).body;
if (fileContent) {
  const chunks: Buffer[] = [];
  for await (const chunk of fileContent) {
    chunks.push(Buffer.isBuffer(chunk) ? chunk : Buffer.from(chunk));
  }
  const buffer = Buffer.concat(chunks);
  fs.writeFileSync(imageFileName, buffer);
} else {
  console.error("Failed to retrieve file content: fileContent is undefined");
}
console.log(`Saved image file to: ${imageFileName}`);

拆卸

若要在完成任务后删除资源，请使用以下函数：

await client.vectorStores.delete(vectorStore.id);
console.log(`Deleted vector store, vector store ID: ${vectorStore.id}`);

await client.files.delete(file.id);
console.log(`Deleted file, file ID : ${file.id}`);

await client.deleteAgent(agent.id);
console.log(`Deleted agent, agent ID: ${agent.id}`);

故障排除

例外

发出服务调用的客户端方法会引发 RestError，以响应来自该服务的非成功 HTTP 状态代码响应。异常 code 将保留 HTTP 响应状态代码。异常 error.message 包含可能有助于诊断问题的详细消息：

import { RestError } from "@azure/core-rest-pipeline";

try {
  const thread = await client.threads.create();
} catch (e) {
  if (e instanceof RestError) {
    console.log(`Status code: ${e.code}`);
    console.log(e.message);
  } else {
    console.error(e);
  }
}

例如，提供错误的凭据时：

Status code: 401 (Unauthorized)
Operation returned an invalid status 'Unauthorized'

报告问题

若要报告客户端库问题或请求其他功能，请在此处打开 GitHub 问题

后续步骤

查看包示例文件夹，其中包含完全可运行的代码。

贡献

此项目欢迎贡献和建议。大多数贡献要求你同意参与者许可协议（CLA），声明你有权（实际这样做）授予我们使用你的贡献的权利。有关详细信息，请访问 https://cla.microsoft.com。

提交拉取请求时，CLA 机器人会自动确定是否需要提供 CLA 并适当修饰 PR（例如标签、注释）。只需按照机器人提供的说明进行操作。只需使用 CLA 在所有存储库中执行此操作一次。

该项目已采用 Microsoft开源行为准则。有关详细信息，请参阅《行为准则常见问题解答》或联系 opencode@microsoft.com，了解任何其他问题或意见。

通过

适用于 JavaScript 的 Azure AI 代理客户端库 - 版本 1.0.0

目录

入门指南

先决条件

授权

安装软件包

重要概念

创建客户端并对其进行身份验证

例子

代理人

创建代理

使用文件搜索创建代理

使用代码解释器创建代理

使用必应地面创建代理

使用 Azure AI 搜索创建代理

使用函数调用创建代理

使用 OpenAPI 创建代理

创建线程

使用工具资源创建线程

列出线程

创建消息

使用文件搜索附件创建邮件

使用代码解释器附件创建消息

使用图像输入创建消息

使用 base64 编码的图像输入创建消息

创建运行、Run_and_Process或流

检索消息

检索文件

拆卸

故障排除

例外

报告问题

后续步骤

贡献

反馈

其他资源