> ## Documentation Index
> Fetch the complete documentation index at: https://docs.langchain.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Undatasio integrations

> Integrate with Undatasio using LangChain Python.

> The `undatasio` package from
> [UnDatasIO](https://undatas.io) extracts clean text from raw source documents like
> PDFs.
> This page covers how to use the `undatasio`
> ecosystem within LangChain.

## Installation and setup

* Install the Python SDK with\
  `pip install undatasio`\
  along with\
  `pip install langchain-undatasio`\
  to use the `UnDatasIOLoader` and partition remotely against the UnDatasIO API.
  You will need an API key, which you can generate for free at\
  [undatas.io](https://undatas.io).

* No local system dependencies are required; all processing runs in the cloud.

## Data loaders

The primary usage of `UnDatasIO` is through the **document loader**.

### UnDatasIOLoader

See the [usage example](/oss/python/integrations/document_loaders/undatasio) for single-file parsing and lazy loading.

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

***

<div className="source-links">
  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>

  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/oss/python/integrations/providers/undatasio.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>
</div>