Demystifying RAG
In the previous chapter, we explored the evolution of LLMs and how they have changed the GenAI landscape. We also discussed some of their pitfalls. We will explore how we can avoid these pitfalls using Retrieval-Augmented Generation (RAG) in this chapter. We will take a look at what RAG means, what its architecture is, and how it fits into the LLM workflow in building improved intelligent applications.
In this chapter, we are going to cover the following main topics:
- Understanding the power of RAG
- Deconstructing the RAG flow
- Retrieving external information for your RAG
- Building an end-to-end RAG flow
