paper-corpus-rag

Build grounded question answering and retrieval-augmented generation (RAG) over your own collection of research papers, with answers that cite the exact paper and passage. Use when a user wants to "chat with" or search a folder of PDFs, synthesize evidence across a literature corpus, find which paper says X, or build a vector/hybrid index with SQLite FTS5, pgvector (Postgres), Chroma, Qdrant or FAISS. Includes a zero-dependency local full-text index with citable hits.

Version

1.0

License

MIT

Compatibility

Python 3.9+ with SQLite FTS5 (standard in CPython builds). Optional pypdf, sentence-transformers, psycopg/pgvector, chromadb or qdrant-client for the vector tiers.