EXPLORE
opendatalab/MinerU MIRROR
Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.
ai4sciencedocument-analysisextract-datalayout-analysisocr
Python 0 0 95
tesseract-ocr/tesseract MIRROR
Tesseract Open Source OCR Engine (main repository)
hacktoberfestlstmmachine-learningocrocr-engine
C++ 0 0 108