hienhayho/rag-colls

Collection of recent advanced RAG techniques.

51
/ 100
Established

Implements modular RAG pipelines with pluggable components for document parsing (Docling, MarkItDown, MegaParse), vector storage (Chromadb), and hybrid retrieval (BM25s integration). Supports techniques like ContextualRAG combining dense and sparse retrievers, and RAFT for retriever-augmented fine-tuning to improve answer quality through supervised learning.

Available on PyPI.

Maintenance 6 / 25
Adoption 11 / 25
Maturity 18 / 25
Community 16 / 25

How are scores calculated?

Stars

18

Forks

6

Language

Python

License

MIT

Last pushed

Oct 24, 2025

Monthly downloads

90

Commits (30d)

0

Dependencies

20

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/hienhayho/rag-colls"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.