> ## 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.

# Graph RAG 集成

> 使用 LangChain Python 与 Graph RAG 进行集成。

## 概述

[Graph RAG](https://datastax.github.io/graph-rag/) 提供了一个检索器接口，将向量上的**非结构化**相似性搜索与元数据属性的**结构化**遍历相结合。这使得能够在**现有**向量存储上进行基于图的检索。

## 安装和设置

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

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

## 检索器

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_graph_retriever import GraphRetriever
```

有关更多信息，请参阅 [Graph RAG 集成指南](/oss/python/integrations/retrievers/graph_rag)。

***

<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\integrations\providers\graph_rag.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>