perf: fully async DB - results in 5-7s, background check+save 8f86a3c GSoumyajit2005 commited on 17 days ago
perf: async DB save with duplicate check for faster extraction 4bdd01c GSoumyajit2005 commited on 17 days ago
feat: PDF preview, database integration, and improved error handling 2a944a5 GSoumyajit2005 commited on 17 days ago
Refactor: Replace Tesseract with DocTR and integrate LayoutLMv3-DocTR model ec0b507 GSoumyajit2005 commited on 19 days ago
feat: add AI detection overlay visualization with bounding boxes on extracted entities 343b0c3 GSoumyajit2005 commited on 20 days ago
feat: Update Dockerfile and requirements for PDF processing, add new dependencies, and refactor API structure faa3050 GSoumyajit2005 commited on 22 days ago
feat: Enhance pipeline with smart PDF handling, Pydantic validation, and semantic hashing, and refactor API to src. f74e17e GSoumyajit2005 commited on Dec 20, 2025
feat: Add Phase 3 generalization scripts and clean up legacy files d79b7f7 GSoumyajit2005 commited on Dec 1, 2025
feat: LayoutLMv3 integration, Streamlit UI toggle, README refresh, .gitignore 42e1c04 GSoumyajit2005 commited on Nov 5, 2025
Complete Version 0.5 with Streamlit UI and full pipeline 566dc81 GSoumyajit2005 commited on Nov 2, 2025
GSoumyajit2005
commited on
