> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-zh.cn/llms.txt
> Use this file to discover all available pages before exploring further.

# 记录多模态追踪

LangSmith 支持在追踪中记录和渲染图像。目前该功能支持多模态 LLM 运行。

要记录图像，请分别在 Python 或 TypeScript 中使用 `wrap_openai`/`wrapOpenAI`，并在输入中传入图像 URL 或 base64 编码的图像。

<CodeGroup>
  ```python Python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  from openai import OpenAI
  from langsmith.wrappers import wrap_openai
  client = wrap_openai(OpenAI())
  response = client.chat.completions.create(
      model="gpt-4-turbo",
      messages=[
        {
          "role": "user",
          "content": [
            {"type": "text", "text": "这张图片里有什么？"},
            {
              "type": "image_url",
              "image_url": {
                "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
              },
            },
          ],
        }
      ],
  )
  print(response.choices[0])
  ```

  ```typescript TypeScript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  import OpenAI from "openai";
  import { wrapOpenAI } from "langsmith/wrappers";
  // 包装 OpenAI 客户端以自动记录追踪
  const wrappedClient = wrapOpenAI(new OpenAI());
  const response = await wrappedClient.chat.completions.create({
    model: "gpt-4-turbo",
    messages: [
      {
        role: "user",
        content: [
          { type: "text", text: "这张图片里有什么？" },
          {
            type: "image_url",
            image_url: {
              "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
            },
          },
        ],
      },
    ],
  });
  console.log(response.choices[0]);
  ```
</CodeGroup>

图像将在 LangSmith 用户界面中作为追踪的一部分进行渲染。

<img src="https://mintcdn.com/hhh-8c10bf0c/lQoj_T05pUgIcyPg/langsmith/images/multimodal.png?fit=max&auto=format&n=lQoj_T05pUgIcyPg&q=85&s=bdebe242904e9eb56bcb089936513d79" alt="多模态" width="1600" height="1216" data-path="langsmith/images/multimodal.png" />

***

<div className="source-links">
  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/i18n\zh-CN\langsmith\log-multimodal-traces.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>

  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>
</div>