The RAG Bootcamp gives you a practical, beginner-friendly introduction to Retrieval Augmented Generation (RAG) - a technique that lets Large Language Models retrieve and use your external data for more accurate answers.
You’ll learn how RAG works end-to-end: from creating embeddings, to storing them in a vector database, to retrieving the right context using semantic search, and finally generating a grounded response.
Throughout the module, each concept is paired with a dedicated lab where you will:
-
Explore different RAG search methods
-
Generate embeddings using modern embedding models
-
Store and query data using a VectorDB
-
Apply multiple chunking strategies, including fixed-size, semantic, overlapping, and agentic chunking
-
Build a complete RAG pipeline from scratch
-
Evaluate retrieval quality using Recall@K, Precision@K, MRR, and NDCG
By the end of this Bootcamp, you’ll have a clear, hands-on understanding of how to design, build, and evaluate real RAG systems for chatbots, knowledge bases, internal tools, and enterprise applications.
