Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Python ai4sciencedocument-analysisdocxextract-datalayout-analysisocrparserpdfpdf-converterpdf-extractor-llmpdf-extractor-pretrainpdf-extractor-ragpdf-parserpptxpythonxlsx
Commits on master
fix(layout): restore output thresholds and position absorbed images
1d18404 myhloli committed 16 days ago
fix: preserve footnote formulas and deduplicate nested text layouts
c5ee779 myhloli committed 17 days ago