dev-k99/RAG-Assistant

Not another tutorial RAG. Hybrid retrieval (BM25 + dense), cross-encoder reranking, RAGAS evaluation, FastAPI backend, persistent ChromaDB — 25–31% better than cosine similarity baseline. Built with Python, Groq, and Streamlit.

14
/ 100
Experimental
No License No Package No Dependents
Maintenance 13 / 25
Adoption 0 / 25
Maturity 1 / 25
Community 0 / 25

How are scores calculated?

Stars

—

Forks

—

Language

Jupyter Notebook

License

—

Category

rag-quality-assurance

Last pushed

Mar 20, 2026

Commits (30d)

0

GitHub
RAG Quality Assurance · 118 tools

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/dev-k99/RAG-Assistant"

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

Higher-rated alternatives

notadev-iamaura/OneRAG

Production-ready RAG Framework (Python/FastAPI). 1-line config swaps: 6 Vector DBs (Weaviate,...

56

pinecone-io/canopy

Retrieval Augmented Generation (RAG) framework and context engine powered by Pinecone

47

teilomillet/raggo

A lightweight, production-ready RAG (Retrieval Augmented Generation) library in Go.

37

electricpipelines/barq

Dabarqus is incredibly fast RAG that runs everywhere.

36

MERakram/Advanced-RAG-monorepo

🚀 Production-ready modular RAG monorepo: Local LLM inference (vLLM) • Hybrid retrieval with...

35

Explore Vector Databases

All categories Trending Vector Database directory Insights