What is PyMuPDF?
PyMuPDF is a layout-aware document engine for AI and a feature-rich Python toolkit for extracting, rendering and editing PDFs and other documents. Since version 2.0, its ML-based layout analysis turns PDFs and Office files into high-quality Markdown for RAG and agents, running fast on CPU and grounding every result to its source page.
Last updated
Key facts
- Type
- Python library for PDF and document processing
- Developer
- Artifex Software, Inc., which also develops MuPDF and Ghostscript
- Built on
- MuPDF, a C engine for PDF and document processing
- Install
pip install pymupdf- Import
import pymupdf- Platforms
- Windows, macOS and Linux
- Licence
- Open source under AGPL-3.0, or a commercial licence from Artifex for proprietary use
- Hardware
- Runs on CPU. No GPU, cloud service or API key needed.
- Input formats
- PDF, XPS, EPUB, CBZ, MOBI, FB2, SVG, TXT, Markdown and images. Microsoft Office and Hangul files need PyMuPDF Office.
- Output formats
- Markdown, JSON, plain text, HTML, images, SVG and PDF
- Integrations
- LangChain and LlamaIndex document loaders
- Documentation
- pymupdf.readthedocs.io
- Source code
- github.com/pymupdf/PyMuPDF
- Package
- pypi.org/project/pymupdf