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

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

19. Other Books You May Enjoy

Common areas to target with red teaming

Consider these categories for your red team RAG attack strategy:

Bias and stereotypes: The chatbot may be manipulated to give biased answers, which can harm the company’s reputation if shared on social media.
Sensitive information disclosure: Competitors or cybercriminals may attempt to obtain sensitive information, such as prompts or private data, through the chatbot.
Service disruption: Ill-intentioned individuals may send long or crafted requests to disrupt the chatbot’s availability for legitimate users.
Hallucinations: The chatbot may provide incorrect information due to suboptimal retrieval mechanisms, low-quality documents, or the LLM’s tendency to agree with the user.

Techniques you can employ to make these attacks include the following:

Bypassing safeguards:
- Text completion: Red teaming techniques for bypassing safeguards in LLM applications include exploiting text completion by...