Exploring SOTA Advanced RAG techniques: This project implements a self reflective RAG, seamlessly integrating multiple knowledge sources (website, SQL, PDFs) while meticulously aligning with business requirements.

RAG with Seach capabilities using Lang graph with question routing and self-reflection.

Agentic RAG system for complex document intelligence using multi-source retrieval across vector search, GraphRAG, and SQL. Includes query transformation, citation-grounded answers, self-reflection, corrective repair, RAGAS-style evaluation, conversational follow-ups, and a deployed frontend on AWS.