---
title: "Unstructured Document ETL for LLM Pipelines"
description: "Unstructured is an open source document processing library that converts PDFs, HTML, Office files, emails, and other formats into structured data for downstream AI workflows. It is a practical intake layer for extraction, chunking, and preprocessing before embeddings, search, or agent use."
verification: "security_reviewed"
source: "https://github.com/Unstructured-IO/unstructured"
author: "Unstructured-IO"
category:
  - "Data Extraction & Transformation"
framework:
  - "Multi-Framework"
tool_ecosystem:
  github_repo: "Unstructured-IO/unstructured"
  github_stars: 14443
---

# Unstructured Document ETL for LLM Pipelines

Unstructured is an open source document processing library that converts PDFs, HTML, Office files, emails, and other formats into structured data for downstream AI workflows. It is a practical intake layer for extraction, chunking, and preprocessing before embeddings, search, or agent use.

## Prerequisites

bun, python, pip, uv, docker, go

## Installation

Choose whichever fits your setup:

1. Copy this skill folder into your local skills directory.
2. Clone the repo and symlink or copy the skill into your agent workspace.
3. Add the repo as a git submodule if you manage shared skills centrally.
4. Install it through your internal provisioning or packaging workflow.
5. Download the folder directly from GitHub and place it in your skills collection.

Install command or upstream instructions:

```
from unstructured.partition.auto import partition
```

## Documentation

- https://unstructured-io.github.io/unstructured/installing.html#installation-with-conda-on-windows

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/unstructured-document-etl-for-llm-pipelines/)