> ## 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.

# 安装 LangGraph

要安装基础的 LangGraph 包：

<CodeGroup>
  ```bash pip theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  pip install -U langgraph
  ```

  ```bash uv theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  uv add langgraph
  ```
</CodeGroup>

使用 LangGraph 时，通常需要访问大语言模型（LLMs）并定义工具。你可以按自己的方式实现这一点。

一种方法（我们将在文档中使用）是使用 [LangChain](/oss/python/langchain/overview)。

安装 LangChain：

<CodeGroup>
  ```bash pip theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  pip install -U langchain
  # 需要 Python 3.10+
  ```

  ```bash uv theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  uv add langchain
  # 需要 Python 3.10+
  ```
</CodeGroup>

如需使用特定 LLM 供应商的包，你需要单独安装它们。

请参考 [集成](/oss/python/integrations/providers/overview) 页面获取供应商特定的安装说明。

***

<div className="source-links">
  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/i18n\zh-CN\oss\langgraph\install.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>