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

Factors in selecting a vectorization option

Selecting the right vectorization option is a crucial decision when building a RAG system. Key considerations include the quality of the embeddings for your specific application, the associated costs, network availability, speed of embedding generation, and compatibility between embedding models. There are numerous other options beyond what we shared above that you can explore for your specific needs when it comes to selecting an embedding model. Let’s review these considerations.

Quality of the embedding

When considering the quality of your embeddings, you cannot rely on just the generic metrics you have seen for each model. For example, OpenAI has been tested on the Massive Text Embedding Benchmark (MTEB), scoring 61.0% with their 'text-embedding-ada-002' model, whereas the 'text-embedding-3-large' model scored 64.6%. The metrics can be useful, especially when trying to hone in on a model of a certain quality...