deepdoctection and docproc
These are complements: deepdoctection provides the foundational document layout analysis and OCR extraction that docproc builds upon to enable higher-level document intelligence tasks like refinement and RAG-based querying.
About deepdoctection
deepdoctection/deepdoctection
A Repo For Document AI
This tool helps automate the extraction of key information from scanned documents and PDFs. You feed in various document types like invoices, forms, or reports, and it accurately identifies and extracts text, tables, and document structures. It's designed for data analysts, operations managers, or anyone who regularly processes large volumes of documents and needs to digitize their content efficiently.
About docproc
rithulkamesh/docproc
Document Intelligence Platform — Extract, refine, and query documents with vision LLMs and config-driven RAG.
Scores updated daily from GitHub, PyPI, and npm data. How scores work