Chapter 5: Intermediate: Retrieval-Augmented Generation and Knowledge Integration
Synopsis
This chapter introduces one of the most important patterns in applied GenAI: grounding model outputs in external knowledge. Learners explore document ingestion, embeddings, vector search, retrieval strategies, and the full RAG pipeline for building knowledge-aware applications.
Sessions
- 1. Why LLMs Need External Knowledge
- 2. Embeddings and Vector Databases
- 3. Building a RAG Pipeline in Python
- 4. Improving Retrieval Quality and Relevance