Bbs1412/rag-with-gemma3

This project is a modular Retrieval-Augmented Generation (RAG) system built with Google DeepMind's - Gemma 3 served locally using Ollama.

28
/ 100
Experimental

Implements end-to-end document processing with vector embeddings via FAISS, history summarization for context-aware retrieval, and streaming responses through FastAPI Server-Sent Events. The modular LangChain-based system handles multi-file ingestion, user-specific document storage with SQLite authentication, and supports thinking models for transparent reasoning. Fully containerized with Docker for deployment on Hugging Face Spaces, using locally-served mxbai embeddings and Gemma-3 via Ollama to maintain privacy and low latency.

No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 9 / 25
Community 12 / 25

How are scores calculated?

Stars

11

Forks

2

Language

Python

License

GPL-3.0

Last pushed

Jul 04, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/Bbs1412/rag-with-gemma3"

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