11 projects
docx-scalpel
Anchor-addressed DOCX editing for LLM agents — a thin client over Docxodus' DocxSession.
python-redlines-ooxmlpowertools
Open-XML-PowerTools redline engine binary for python-redlines.
python-redlines-docxodus
Docxodus redline engine binary for python-redlines.
python-redlines
Open-source DOCX comparison tool to generate native Word tracked changes (redlines) in Python without MS Word dependencies.
warp-ingest
Pure-Python, RAG-friendly document parsers (PDF/HTML/text/XML/Markdown). Java- and Tika-free.
matter2
A version control system for office documents
pdfredact
None
plasmapdf
Annotation generator and search tools for PDF
pdftokenizer
Tool to extract PAWLs tokens from PDFs
BotsOnRails
BotsOnRails makes it easy to write LLM-controlled programs without outsourcing all of the logic and decisions to stochastic models. It facilitates the seamless integration of function-based nodes into an execution tree, enabling conditional and sequential task execution tailored to complex, resumable processing flows.
OCRUSREX
OCRUSREX takes a PDF (either by path or as a file-like object) and makes it searchable using Tesseract 4. It has an enterprise-friendly license.
