RAG — Retrieval-Augmented Generation

In this lesson, we will learn RAG. We will explain what RAG is, how it differs from a standalone LLM, how retrieval and generation work, and how document chunks, embeddings, vector search, source-based answers and hallucination reduction work with practical examples. ## Lesson objective In this lesson, we will learn RAG — Retrieval-Augmented Generation. In the previous lesson, we covered embeddings and vector search. We explained converting text into vectors, semantic search, similarity, cosine similarity, chunking, vector database and metadata filtering.