> ## 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.

# LangGraph v1 迁移指南

本指南概述了 LangGraph v1 中的变更以及如何从之前的版本进行迁移。有关变更的概览，请参阅 [更新内容](/oss/python/releases/langgraph-v1) 页面。

要升级：

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

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

## 变更摘要

LangGraph v1 与之前的版本在很大程度上向后兼容。主要变更是弃用 [`create_react_agent`](https://reference.langchain.com/python/langchain-classic/agents/react/agent/create_react_agent)，转而使用 LangChain 的新 [`create_agent`](https://reference.langchain.com/python/langchain/agents/factory/create_agent) 函数。

## 弃用项

下表列出了 LangGraph v1 中所有已弃用的项目：

| 弃用项                                        | 替代方案                                                                                                                                                                                                             |
| ------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `create_react_agent`                       | [`langchain.agents.create_agent`](https://reference.langchain.com/python/langchain/agents/factory/create_agent)                                                                                                  |
| `AgentState`                               | [`langchain.agents.AgentState`](https://reference.langchain.com/python/langchain/agents/middleware/types/AgentState)                                                                                             |
| `AgentStatePydantic`                       | `langchain.agents.AgentState`（不再需要 pydantic 状态）                                                                                                                                                                  |
| `AgentStateWithStructuredResponse`         | `langchain.agents.AgentState`                                                                                                                                                                                    |
| `AgentStateWithStructuredResponsePydantic` | `langchain.agents.AgentState`（不再需要 pydantic 状态）                                                                                                                                                                  |
| `HumanInterruptConfig`                     | `langchain.agents.middleware.human_in_the_loop.InterruptOnConfig`                                                                                                                                                |
| `ActionRequest`                            | `langchain.agents.middleware.human_in_the_loop.InterruptOnConfig`                                                                                                                                                |
| `HumanInterrupt`                           | `langchain.agents.middleware.human_in_the_loop.HITLRequest`                                                                                                                                                      |
| `ValidationNode`                           | 工具在使用 [`create_agent`](https://reference.langchain.com/python/langchain/agents/factory/create_agent) 时会自动验证输入                                                                                                    |
| `MessageGraph`                             | 带有 `messages` 键的 [`StateGraph`](https://reference.langchain.com/python/langgraph/graph/state/StateGraph)，类似于 [`create_agent`](https://reference.langchain.com/python/langchain/agents/factory/create_agent) 所提供的 |

## create\_react\_agent → create\_agent

LangGraph v1 弃用了 [`create_react_agent`](https://reference.langchain.com/python/langchain-classic/agents/react/agent/create_react_agent) 预构建组件。请使用 LangChain 的 [`create_agent`](https://reference.langchain.com/python/langchain/agents/factory/create_agent)，它在 LangGraph 上运行并添加了灵活的中间件系统。

有关详细信息，请参见 LangChain v1 文档：

* [发布说明](/oss/python/releases/langchain-v1#createagent)
* [迁移指南](/oss/python/migrate/langchain-v1#migrate-to-create_agent)

<CodeGroup>
  ```python v1 (new) theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  from langchain.agents import create_agent

  agent = create_agent(  # [!code highlight]
      model,
      tools,
      system_prompt="You are a helpful assistant.",
  )
  ```

  ```python v0 (old) theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  from langgraph.prebuilt import create_react_agent

  agent = create_react_agent(  # [!code highlight]
      model,
      tools,
      prompt="You are a helpful assistant.",  # [!code highlight]
  )
  ```
</CodeGroup>

## 破坏性变更

### 不再支持 Python 3.9

所有 LangChain 包现在都需要 **Python 3.10 或更高版本**。Python 3.9 已于 2025 年 10 月达到 [生命周期结束](https://devguide.python.org/versions/)。

***

<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\python\migrate\langgraph-v1.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>