Built a full-stack Retrieval-Augmented Generation (RAG) web application using Next.js, React, and FastAPI.
Integrated LangChain,VertexAI and Gemini API for LLM-based query answering with semantic search powered
by Pinecone vector database. Deployed on AWS EC2 with Nginx reverse proxy, SSL (Let’s Encrypt), and PM2 for
process management. Configured custom subdomain and optimized backend for low-latency query performance.