An enterprise-grade, serverless RAG pipeline transforming multi-page PDF documents into interactive, context-aware knowledge networks using modern LangChain (LCEL) architectures.

A production-ready Advanced RAG API featuring background ingestion, schema-driven routing, and dynamic metadata filtering. Built with FastAPI, ChromaDB, and Ollama, it utilizes RabbitMQ workers for scalable, idempotent document processing and autonomous query expansion.

a multi-step web research agent over the web, Wikipedia, and arXiv - built with LangGraph + LCEL, streams each step in real-time, and grounds every report in sources it actually fetches and reads.