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

# 记录多模态追踪

LangSmith 支持将图像作为追踪的一部分进行记录和渲染。目前此功能支持多模态 LLM 运行。

要记录图像，请在 Python 或 TypeScript 中分别使用 `wrap_openai`/ `wrapOpenAI`，并将图像 URL 或 base64 编码图像作为输入的一部分传递。

<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": "What's in this image?"},
            {
              "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: "What's in this image?" },
          {
            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 UI 中作为追踪的一部分进行渲染。

<img src="https://mintcdn.com/other-405835d4/X4LKQZjW6RjHveuz/langsmith/images/multimodal.png?fit=max&auto=format&n=X4LKQZjW6RjHveuz&q=85&s=0b45bf4eca6e4b5333af28d16a8c7c10" alt="多模态" width="1600" height="1216" data-path="langsmith/images/multimodal.png" />

***

<div className="source-links">
  <Callout icon="terminal-2">
    [连接这些文档](/use-these-docs) 到 Claude、VSCode 等，通过 MCP 获取实时答案。
  </Callout>

  <Callout icon="edit">
    [在 GitHub 上编辑此页面](https://github.com/langchain-ai/docs/edit/main/src/langsmith/log-multimodal-traces.mdx) 或 [提交问题](https://github.com/langchain-ai/docs/issues/new/choose)。
  </Callout>
</div>