document-qa-agent

Document Q&A agent template with per-user JWT auth and a pluggable vector store — FAISS or ChromaDB, one env var to switch. SQLite-backed audit trail included. Intermediate tier of the Document Intel Agent Template family — for real users, not yet a full enterprise deployment.

A zero-infra document Q&A agent template — ChromaDB + your choice of offline or hosted embeddings + OpenAI/Bedrock generation. Clone, pip install, and get a grounded RAG loop running in minutes. POC tier of the Document Intel Agent Template family.

RAG-based PDF Question Answering system using Gemini embeddings, semantic search, and grounded answer generation.

Open-source document Q&A. Upload your PDFs, Word and markdown files, ask questions, and get answers that cite the exact passage. When your documents don't support an answer, it says so

Self-hosted chat for your own PDFs. Every answer cites the exact quote and page, and says so when the answer is not in your documents. FastAPI, React and Postgres with pgvector; works with any OpenAI-compatible model.