Kymata Labs/The Living IndexesBuilt by tekvisions ↗
The Document Index / Document Parsing / #2
opendatalab

opendatalab/MinerU

by opendatalab · Document Parsing · updated 1d ago

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

86
momentum
67,412
stars
5,679
forks
#2
rank
ai4sciencedocument-analysisdocxextract-datalayout-analysisocrparserpdfpdf-converterpdf-extractor-llmpdf-extractor-pretrainpdf-extractor-rag
View on GitHub →