hoangsonww/RAG-LangChain-AI-System

🧠 A production-grade, agentic RAG platform for portfolio intelligence, combining LangChain, Chroma/FAISS, Hugging Face embeddings, and Ollama with dynamic entity extraction, backend API tool-chaining, and a real-time interactive assistant across deploy-ready frontend, backend, and infrastructure stacks.

46
/ 100
Emerging

Implements multi-strategy retrieval combining semantic search (Chroma/FAISS), BM25 lexical matching, and optional cross-encoder reranking, with an agentic orchestrator that chains tool calls to backend APIs (team/investment/sector profiles, consultations) for evidence-backed responses. The Flask + Socket.IO RAG service streams completions in real-time to a React frontend while maintaining full request traceability, source attribution, and production controls (rate limiting, liveness probes, request IDs). Includes Docker, Kubernetes, and Terraform assets for end-to-end deployment, plus a MongoDB-backed Express API for structured portfolio data lookup.

No Package No Dependents
Maintenance 13 / 25
Adoption 7 / 25
Maturity 9 / 25
Community 17 / 25

How are scores calculated?

Stars

32

Forks

10

Language

Jupyter Notebook

License

MIT

Last pushed

Mar 13, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/hoangsonww/RAG-LangChain-AI-System"

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