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

Adapting prompts for different LLMs

As the AI landscape evolves, people are no longer solely relying on OpenAI for their language modeling needs. Other players, such as Anthropic with their Claude models, have gained popularity due to their ability to handle long context windows. Google is also releasing (and will continue to release) powerful models. Moreover, the open source model community is catching up, with models such as Llama proving to be viable alternatives.

However, it’s important to note that prompts do not seamlessly transfer from one LLM to another. Each LLM may have specific tricks and techniques that work best for its architecture. For example, Claude-3 prefers XML encoding when prompting, while Llama3 uses a specific syntax when labeling different parts of your prompt, such as SYS and INST. Here is an example prompt for Llama models using the SYS and INST tags: