> ## Documentation Index
> Fetch the complete documentation index at: https://nvd-54.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Roam 集成

> 使用 LangChain Python 集成 Roam 文档加载器。

> [ROAM](https://roamresearch.com/) is a note-taking tool for networked thought, designed to create a personal knowledge base.

本 notebook 介绍如何load documents from a Roam database. This takes a lot of inspiration from the [Roam QA example repository](https://github.com/JimmyLv/roam-qa).

## 🧑 Instructions for ingesting your own dataset

Export your dataset from Roam Research. You can do this by clicking on the three dots in the upper right hand corner and then clicking `Export`.

导出时，请确保选择 `Markdown & CSV` 格式选项。

这将在你的下载文件夹中生成一个 `.zip` 文件。将 `.zip` 文件移到此仓库中。

运行以下命令解压 zip 文件（根据需要将 `Export...` 替换为你自己的文件名）。

```shell theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
unzip Roam-Export-1675782732639.zip -d Roam_DB
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_community.document_loaders import RoamLoader
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
loader = RoamLoader("Roam_DB")
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
docs = loader.load()
```

***

<div className="source-links">
  <Callout icon="terminal-2">
    [通过 MCP 将这些文档连接到](/use-these-docs) Claude、VSCode 等工具以获取实时答案。
  </Callout>

  <Callout icon="edit">
    [在 GitHub 上编辑此页面](https://github.com/langchain-ai/docs/edit/main/src/oss/python/integrations/document_loaders/roam.mdx) 或 [提交 issue](https://github.com/langchain-ai/docs/issues/new/choose)。
  </Callout>
</div>