Part 1 Foundations

This first part of the book introduces the core idea behind retrieval-augmented generation (RAG) and the high-level design of a RAG system.

Chapter 1 deals with various challenges that AI systems based on large language models (LLMs) face. Furthermore, it illustrates the ways RAG addresses these challenges to improve the reliability of such systems. The chapter also provides a brief overview of the workings of LLMs and some popular RAG use cases.

Chapter 2 discusses the steps involved in building a RAG system. This chapter details the basics of two core RAG pipelines and other essential components of a RAG system.

By the end of the first part of the book, you should have a foundational understanding of a RAG system and be ready to dive deep into the intricacies of RAG.