> ## 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.

# Undatasio 集成

> 使用 LangChain Python 集成 Undatasio 文档加载器。

本 notebook 提供了 the **UnDatasIO document loader**. UnDatasIO enables efficient loading and parsing of various document formats including PDF, PNG, JPG, JPEG, and JFIF, with features like document lazy loading and native async support, all through UnDatasIO's secure cloud API. These capabilities make the processed data ready for generative AI workflows like RAG 的快速入门概览。

For detailed documentation on all features and configurations, refer to the official API reference.

## 概述

### 加载器特性

|       Source      | Document Lazy Loading | Native Async Support |
| :---------------: | :-------------------: | :------------------: |
| `UnDatasIOLoader` |           ✅           |           ✅          |

## 设置

### 凭证

UnDatasIO requires an API token.
Generate a free token at [undatas.io](https://undatas.io) and set it in the cell below:

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import getpass
import os

if "UNDATASIO_TOKEN" not in os.environ:
    os.environ["UNDATASIO_TOKEN"] = getpass.getpass(
        "Enter your UnDatasIO API token: "
    )
```

### 安装

#### Normal installation

运行此 notebook 的其余部分需要以下包。

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# Install package, compatible with API partitioning
pip install langchain-undatasio
```

### 初始化

The **UnDatasIOLoader** supports single-file upload & parsing via the UnDatasIO cloud API.

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

loader = UnDatasIOLoader(
    token=os.environ["UNDATASIO_TOKEN"],
    file_path="demo.pdf"
)
```

### 加载

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
docs = loader.load()
docs[0]
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
Document(
    metadata={'source': 'demo.pdf', 'task_id': 't1', 'file_id': 'f1'},
    page_content='Growing a Tail: Increasing Output Diversity in Large Language Models\n\nAuthors: Michal Shur-Ofry1, Bar Horowitz-Amsalem1†, Adir Rahamim2, Yonatan Belinkov2*\n\nAffiliations:\n\n1Law Faculty, Hebrew University of Jerusalem; Jerusalem, Israel.\n\n2Faculty of Computer Science, Technion – I'
)
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
print(docs[0].page_content[:300])
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
Growing a Tail: Increasing Output Diversity in Large Language Models

Authors: Michal Shur-Ofry1, Bar Horowitz-Amsalem1†, Adir Rahamim2, Yonatan Belinkov2*

Affiliations:

1Law Faculty, Hebrew University of Jerusalem; Jerusalem, Israel.

2Faculty of Computer Science, Technion – I
```

### 惰性加载

**UnDatasIOLoader** supports lazy loading for memory-efficient iteration.

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
pages = []
for doc in loader.lazy_load():
    pages.append(doc)

pages[0]
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
Document(
    metadata={'source': 'demo.pdf', 'task_id': 't1', 'file_id': 'f1'},
    page_content='Growing a Tail: Increasing Output Diversity in Large Language Models\n\nAuthors: Michal Shur-Ofry1, Bar Horowitz-Amsalem1†, Adir Rahamim2, Yonatan Belinkov2*\n\nAffiliations:\n\n1Law Faculty, Hebrew University of Jerusalem; Jerusalem, Israel.\n\n2Faculty of Computer Science, Technion – I'
)
```

## See also

* [UnDatasIO](https://undatas.io)
* [langchain-undatasio](https://pypi.org/project/langchain-undatasio/)

***

<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/undatasio.mdx) 或 [提交 issue](https://github.com/langchain-ai/docs/issues/new/choose)。
  </Callout>
</div>