---
id: pymupdf4llm
version: "1.28.2"
license: Dual Licensed - GNU AFFERO GPL 3.0 or Artifex Commercial License
license_treatment: agpl
maintenance: active
---

# pymupdf4llm — PyMuPDF Utilities for LLM/RAG

License: agpl · Maintenance: active · Popularity: top 1,000 on PyPI

## Install

pip install pymupdf4llm
uv add pymupdf4llm
poetry add pymupdf4llm

## Description

<p align="center">
  <a href="https://pymupdf.io?utm_source=github&utm_medium=referral&utm_campaign=pymupdf4llm_github&utm_content=logo&utm_term=website">
    <img loading="lazy" alt="PyMuPDF" src="https://pymupdf.pro/images/py-mupdf4llm-github-icon.png" width="96px" alt="PyMuPDF logo"/>
  </a>
</p>

# PyMuPDF4LLM

<p align="center">
 <a href="https://trendshift.io/repositories/11536" target="_blank"><img src="https://trendshift.io/api/badge/repositories/11536" alt="pymupdf%2FPyMuPDF | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
</p>


[![Docs](https://img.shields.io/badge/docs-live-brightgreen)](https://pymupdf.readthedocs.io/en/latest/pymupdf4llm?utm_source=github&utm_medium=referral&utm_campaign=pymupdf4llm_github&utm_content=badges&utm_term=docs)
[![PyPI Version](https://img.shields.io/pypi/v/pymupdf4llm?color=blue&label=PyPI)](https://pypi.org/project/pymupdf4llm)
[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/pymupdf4llm)](https://pypi.org/project/pymupdf4llm/)
[![License AGPL](https://img.shields.io/github/license/pymupdf/pymupdf4llm)](https://github.com/pymupdf/pymupdf4llm/blob/master/LICENSE)
[![PyPI...

## AI interpretation — verify before relying

Converts PDFs and documents into structured Markdown, JSON, and plain text optimized for LLM ingestion and RAG pipelines, with automatic layout analysis, table detection, and selective OCR.

Verdict: Production-ready tool for document-to-LLM pipelines with no GPU or cloud dependency. Active maintenance, low install friction, and zero known vulnerabilities make it reliable for RAG workflows. AGPL licensing requires attention: open-source projects are compatible, but commercial deployments need explicit licensing review or a commercial license purchase.

[View on SkillFed](https://skillfed.io/packages/pymupdf4llm) · [View on PyPI](https://pypi.org/project/pymupdf4llm/)