polarbear333/rag-llm-based-recommender

Explore a smarter way to shop online with this full-stack project built on the infrastructure of Google Cloud Platform (GCP) for RAG based e-commerce with LLM.

27
/ 100
Experimental

Implements a multi-stage RAG pipeline combining BigQuery vector search with ScaNN for approximate nearest neighbor retrieval, re-ranking, and context assembly before LLM generation using Gemini. The backend uses FastAPI with LangChain integration, while the frontend provides a React/Next.js chat interface for semantic product search grounded in Amazon Reviews data, with offline evaluation metrics (MRR, nDCG@k) and latency optimization.

No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 9 / 25
Community 10 / 25

How are scores calculated?

Stars

15

Forks

2

Language

TypeScript

License

MIT

Last pushed

Sep 26, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/polarbear333/rag-llm-based-recommender"

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