---
title: README
emoji: 🐮
colorFrom: blue
colorTo: gray
sdk: static
pinned: false
---

# Welcome to PyMuPDF4LLM

We provide top of the line solutions for developers building RAG/LLM applications with **PyMuPDF4LLM**, a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.

10× faster PDF parsing with layout analysis.
Trained on structure, not images. CPU-only.

## Demo

- Try the [demo](https://demo.pymupdf.io).


## Resources

- [PyMuPDF](https://pymupdf.readthedocs.io)
- [PyMuPDF4LLM](https://pymupdf.readthedocs.io/en/latest/pymupdf4llm/)
- Try [PyMuPDF Pro](https://pymupdf.pro/try-pro/) - the commercial version of PyMuPDF for free - includes [Office document support](https://pymupdf.readthedocs.io/en/latest/pymupdf-pro/) and PyMuPDF4LLM.



## About Us

[PyMuPDF4LLM](https://pymupdf.readthedocs.io/en/latest/pymupdf4llm/) is run by [Artifex](https://artifex.com) - a trusted name in PDF and PostScript solutions. We’re all about quality, great customer service, and lasting relationships. Questions about licensing? [Contact us](https://artifex.com/contact/)