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

Code lab 11.2 – Text splitters

The file you need to access from the GitHub repository is titled CHAPTER11-2_TEXT_SPLITTERS.ipynb.

Text splitters split a document into chunks that can be used for retrieval. Larger documents pose a threat to many parts of our RAG application and the splitter is our first line of defense. If you were able to vectorize a very large document, the larger the document, the more context representation you will lose in the vector embedding. But this assumes you can even vectorize a very large document, which you often can’t! Most embedding models have relatively small limits on the size of documents we can pass to it compared to the large documents many of us work with. For example, the context length for the OpenAI model we are using to generate our embeddings is 8,191 tokens. If we try to pass a document larger than that to the model, it will generate an error. These are the main reasons splitters exist, but these are not the only complexities...