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.
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.
Stars
15
Forks
2
Language
TypeScript
License
MIT
Category
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.
Higher-rated alternatives
mayaradaher/challenge-Amazon
The app uses the Gemini language model to generate personalized book recommendations.
ShowayLiao/OtakuNeko
🐱 你的二次元赛博哈基米 | 基于 LLM 的智能化番剧管理与分析助手。支持 Bangumi 数据同步、AI 深度画像分析、年度总结海报生成与个性化推荐。
VectorInstitute/health-rec
MVP of a recommendation system for health and community services
amine-akrout/llm-based-recommender
AI-powered fashion recommendation system leveraging LLMs, embeddings, and retrieval techniques...
EdIzaguirre/Rosebud
Let's discover films.