README

_AI Agents Made Simple_ reached 1 in Software Development, Software Engineering and Software Design Tools on Amazon.com's Kindle Store.
A decision guide to building AI agents that work: 28 chapters, 148 illustrations, no code.
Get the book on Amazon →






 Advanced RAG Techniques 🚀
 Elevating Your Retrieval-Augmented Generation Systems

A community-driven hub of 42+ runnable notebooks covering RAG techniques from foundational to cutting-edge - the intuition, the code, and the references to build more accurate, context-rich retrieval systems.



---








📖 Go deeper: the book





RAG Made Simple - the 400-page visual companion to this repo.
Amazon Bestseller in Generative AI

Get it on Amazon (paperback · Kindle · free on Kindle Unlimited) → · Read Chapter 1 free



 Sponsors ❤️

We gratefully acknowledge the organizations and individuals who have made significant contributions to this project.

Company Sponsors




  
    
      
        
        
      
    
    
      
        
        
      
    
    
      
        
      
    
  



Individual Sponsors



 📫 Stay Updated!




🚀Cutting-edgeUpdates
💡ExpertInsights
🎯Top 0.1%Content






Join over 50,000 AI enthusiasts getting unique cutting-edge insights and free tutorials! Plus, subscribers get exclusive early access and special 33% discounts on my books!




🎬 Prefer video?



I break these ideas down into short, one-idea-per-episode explainers on YouTube.


  
    
    🆕 AI Is Rewarded for Guessing [Hallucination]
  
  why a model guesses instead of saying I don't know, watched on its own token probabilities, and where retrieval moves the fact out of the guess





  
    
    RAG Explained: Why AI Gets Your Own Documents Wrong
  
  why chunks overlap, what "meaning space" is, and where simple RAG breaks down


  
    
    How Do You Search a Spreadsheet by Meaning?
  
  turn each row into one labelled line and search the table by meaning


  
    
    How Do You Know Your RAG Answer Isn't Made Up?
  
  three checkpoints that catch a bad chunk on the way in and an unsupported claim on the way out


  
    
    Why Does RAG Return a Paragraph When You Asked for One Fact?
  
  why a paragraph's embedding is a blend that points at nothing in particular




   Browse every episode →



 Introduction

Retrieval-Augmented Generation (RAG) is revolutionizing the way we combine information retrieval with generative AI. This repository showcases a curated collection of advanced techniques designed to supercharge your RAG systems, enabling them to deliver more accurate, contextually relevant, and comprehensive responses.

Our goal is to provide a valuable resource for researchers and practitioners looking to push the boundaries of what's possible with RAG. By fostering a collaborative environment, we aim to accelerate innovation in this exciting field.

 Related Projects

🚀 Agents Towards Production - code-first tutorials for shipping production-grade GenAI agents, prototype to