You're reading from Unlocking Data with Generative AI and RAG Enhance generative AI systems by integrating internal data with large language models using RAG

Product type Paperback

Published in Sep 2024

Publisher Packt

ISBN-13 9781835887905

Length 346 pages

Edition 1st Edition

Concepts

GPT/LLMs

Author (1):

Keith Bourne

View More author details

Table of Contents (20) Chapters

Preface

1. Part 1 – Introduction to Retrieval-Augmented Generation (RAG) FREE CHAPTER

2. Chapter 1: What Is Retrieval-Augmented Generation (RAG)

3. Chapter 2: Code Lab – An Entire RAG Pipeline

4. Chapter 3: Practical Applications of RAG

5. Chapter 4: Components of a RAG System

6. Chapter 5: Managing Security in RAG Applications

7. Part 2 – Components of RAG

8. Chapter 6: Interfacing with RAG and Gradio

9. Chapter 7: The Key Role Vectors and Vector Stores Play in RAG

10. Chapter 8: Similarity Searching with Vectors

11. Chapter 9: Evaluating RAG Quantitatively and with Visualizations

12. Chapter 10: Key RAG Components in LangChain

13. Chapter 11: Using LangChain to Get More from RAG

14. Part 3 – Implementing Advanced RAG

15. Chapter 12: Combining RAG with the Power of AI Agents and LangGraph

16. Chapter 13: Using Prompt Engineering to Improve RAG Efforts

17. Chapter 14: Advanced RAG-Related Techniques for Improving Results

18. Index

Why subscribe?

19. Other Books You May Enjoy

Hybrid RAG/multi-vector RAG for improved retrieval

Hybrid RAG expands on the concept of naïve RAG by utilizing multiple vectors for the retrieval process, as opposed to relying on a single vector representation of queries and documents. We explored hybrid RAG in depth and in code in Chapter 8, not only utilizing the mechanism recommended within LangChain but by re-creating that mechanism ourselves so that we could see its inner workings. Also called multi-vector RAG, hybrid RAG can involve not just semantic and keyword search, as we saw in our code lab, but the mix of any different vector retrieval techniques that make sense for your RAG application.

Our hybrid RAG code lab introduced a keyword search, which expanded our search capabilities, leading to more effective retrieval, particularly when dealing with content that has a weaker context (such as names, codes, internal acronyms, and similar text). This multi-vector approach allows us to consider broader facets of the query...