opendatalab/MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Python78K stars6.6K forks+380 today
Topics
#extract-data#layout-analysis#ocr#parser#pdf#pdf-converter#python#document-analysis#pdf-parser#pdf-extractor-llm#pdf-extractor-pretrain#pdf-extractor-rag#ai4science#docx#pptx#xlsx
What it does
MinerU is a high-accuracy document parsing engine that converts complex documents into structured Markdown/JSON, essential for AI workflows like RAG and agent systems. It supports multiple languages and integrates with various development frameworks.
Star history
Not enough history yet — 1 day(s) recorded. The daily snapshot builds this up.
Tracking
- Last trending
- 2026-07-20
Creator kit
Hook
Transform your documents into LLM-friendly formats effortlessly with MinerU! 🚀 #MinerU #AI
Content angles
- How to integrate MinerU into existing AI workflows for improved data processing.
- A deep dive into the OCR and VLM dual engine technology behind MinerU's high accuracy.
- Comparative analysis of different deployment options in MinerU for optimal performance.
Who should care
AI developers, researchers, and content creators working with large language models and RAG frameworks.