ChatGPT for Conversational AI and Chatbots

7

Vector Stores as Knowledge Bases for Retrieval-augmented Generation

Retrieval-augmented generation (RAG) is easily the most common use case for LLMs that has emerged since the explosion of ChatGPT. In this chapter, we’re going to look at the key steps and concepts involved in creating a RAG system. Once you have an understanding of what’s involved with each step, we’ll look at how these processes and techniques can be carried out using LangChain. Going further, we’ll work through our own RAG system with a real-world example.

This chapter aims to be an introduction to the core concepts of RAG so that you have a solid base for mastering it.

In this chapter, we’ll cover the following topics:

• Why do we need RAG?
• Understanding the steps needed ...