RAG & Vector Databases: Learn by Building with Ritwik Raj

RAG is one of the most in-demand GenAI skills, and most tutorials stop at a toy demo. In this 60-minute session, I'll teach you how real RAG systems work and we'll build one together.

What we'll cover:

• How RAG works end to end: ingest, chunk, embed, store, retrieve, generate

• Chunking strategies and choosing an embedding model

• Vector databases: FAISS, Chroma, pgvector and Pinecone, and when to use which

• Better retrieval: hybrid search, metadata filters and re-ranking

• Evaluating answers and reducing hallucinations

• Building a working "chat with your documents" app

Who it's for: developers and data engineers who know basic Python and want hands-on RAG skills for projects or interviews.

Before the call, share your use case or the documents you'd like to work with. You'll leave with working code and a clear plan to take it further.

Learn from an engineer who has built production-grade data and AI systems at Apple, Amazon and MakeMyTrip.