MinerU
One-stop tool for high-quality PDF extraction to Markdown or JSON.
About
MinerU by OpenDataLab is a one-stop tool for converting PDFs into machine-readable Markdown or structured JSON for LLM and RAG pipelines. It handles complex layouts, reading order, formulas, tables, and images by combining several OCR and layout-analysis models, and offers a command-line tool, a web demo, and a Python package. It targets clean extraction from scientific and technical documents. Released under the AGPL-3.0 license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- OCR & Document Processing
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Easy (2/5)
- License
- AGPL-3.0
- Added
- Apr 3, 2026
Related Tools
Document parsing library by IBM for converting PDFs and documents to structured data.
Deep learning based OCR library in Python and TensorFlow/PyTorch.
Python bindings for MuPDF library for fast PDF text and image extraction.
Tool for extracting tables from PDF files into CSV or DataFrame format.
Ready-to-use OCR library supporting 80+ languages with simple Python API.
Python library for extracting tables from PDF files.