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

Semantic search algorithms

We have discussed the concept of a semantic search in depth. Our next step is to walk through the different approaches we can take to conduct a semantic search. These are the actual search algorithms that use things such as the distance metrics we’ve already discussed (Euclidean distance, dot product, and cosine similarity) to conduct their search of dense embeddings. We start with k-nearest neighbors (k-NN).

k-NN

One way to find similar vectors is through brute force. With brute force, you find the distances between the query and all the data vectors. Then, you sort the distances from closest to furthest, returning a certain number of results. You can cut off the results based on a threshold, or you can define a set number to return, such as 5. The set number is called k, so you would say k=5. This is known in classical machine learning as the k-NN algorithm. This is a straightforward algorithm, but its performance degrades as the dataset grows...