Rag Chat Bot with Langchain LLM
My role. Full Stack Developer
Built an AI-powered application using LangChain with Retrieval-Augmented Generation (RAG) to provide accurate, context-aware responses from custom data. Implemented the system in Node.js with OpenAI APIs, enabling efficient document ingestion, embedding, and retrieval. Designed a scalable pipeline for vector search + LLM reasoning, improving response quality over standalone LLMs. Focused on clean architecture and reliable performance for real-world usage.