opendatalab / MinerU

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

活跃维护 NOASSERTION Python Tracked
78.8k 6.6k 2 天前
CIPyPI
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
GitHub 项目主页 对比

星标趋势

数据积累中，暂无足够数据生成趋势图

AI 分析

项目摘要

opendatalab/MinerU: Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

为什么值得关注

High popularity with 73,108 stars, active contributor community (98 contributors), frequent releases.

优势

  • Large and active community
  • Continuous integration configured
  • Test suite present

局限性

  • Limited documentation
分析模型：fallback | 分析时间：1 个月前