Projects
Built this: Enterprise Agentic RAG Orchestrator (Multi-Agent-RAG)
A Supervisor → Worker → Validator multi-agent RAG system with LangGraph Corrective RAG, hybrid dense + BM25 retrieval with cross-encoder reranking, a Qdrant semantic cache and a security layer.
- A supervisor LLM routes each query to a retriever, a read-only SQL agent, a human-in-the-loop email tool agent or a chat agent, and a validator re-grounds the answer.
- The README reports RAGAS scores of 0.81 faithfulness, 1.00 context precision, 0.90 context recall and 0.75 answer relevancy.