As we’re getting started with LlamaIndex, it’s time to understand some of the key concepts and components that make up its architecture. You may consider this chapter as a quick introduction to the typical retrieval-augmented generation (RAG) architecture with LlamaIndex and an overview of the most important tools provided by this framework. It should give you a basic understanding of how to build a simple RAG application. In the next chapters, we’ll take it step by step and explore in detail each one of the components presented here.

At a high level, LlamaIndex helps connect external data sources to LLMs. To do this effectively, it needs to ingest, structure, and organize your data in a way that allows for efficient retrieval and querying. In this first part of our chapter, we’ll explore the core elements that enable LlamaIndex to augment LLMs – Documents...