Retrieval Augmented Generation, The Seminal Papers

Get a free eBook (PDF or ePub) from Manning as well as access to the online liveBook format (and its AI assistant that will answer your questions in any language) when you purchase the print book.

Retrieval Augmented Generation (RAG) is a standard process for grounding LLM prompts in user-specified content rather than relying only on a model’s training data. RAG has grown from a simple prompt engineering workflow into a sophisticated set of data analysis, storage, and retrieval techniques. This book explores 12 foundational research papers that explain why RAG works, how it’s built, and what makes it different from other approaches.

This authoritative book explores the papers that define RAG’s enduring architectural pattern. Author Ben Auffarth traces RAG’s evolution from the foundational breakthroughs of REALM, RAG, and DPR to advanced architectures like FiD and Atlas. Designed to be both interesting and practical, this book illuminates techniques that empower systems to retrieve intelligently, evaluate themselves, and recover from errors. Over 40 code samples, architectural diagrams, and industry case studies make each concept easy to understand. As you master the patterns behind RAG, you’ll better understand tradeoffs, diagnose failures, and effectively evaluate and improve your own RAG implementations.

What's inside

• 12 seminal papers explained with practical code
• RAG’s evolution from Naïve to Advanced to Modular
• Evaluation frameworks (RAGAS) for measuring RAG quality
• Decision frameworks for choosing the right RAG approach

About the reader

For ML engineers, data scientists, and software developers comfortable with Python and the basics of deep learning. No advanced math is required.

About the author

Ben Auffarth, Ph.D., is an enterprise AI leader with 15+ years of experience architecting mission-critical AI systems across insurance, finance, and technology. He holds a PhD in computational neuroscience with 300+ research citations, and has built systems processing 100,000+ daily decisions and managing £60M+ in fraud detection. An Amazon bestselling author, Ben currently leads production RAG implementations at his company Chelsea AI, giving him direct insight into the challenges of scaling RAG from research to robust, enterprise deployments.