A curated collection of 42+ Jupyter notebook tutorials covering foundational to advanced Retrieval-Augmented Generation techniques. It serves as a learning library for developers and researchers to understand and implement various RAG methods using provided code and documentation.
Project overview
A curated collection of 42+ Jupyter notebook tutorials covering foundational to advanced Retrieval-Augmented Generation techniques. It serves as a learning library for developers and researchers to understand and implement various RAG methods using provided code and documentation.
Project type
RAG
Use cases
Knowledge Q&A
Deployment
Refer to project documentation
License
License pending
Best for
Developers, researchers, and AI engineers seeking practical, runnable examples of advanced prompt research and RAG components.
Key capabilities
A collection of 42+ Jupyter notebooks providing tutorials on various RAG techniques from foundational to advanced, including code and references.
Standalone Python scripts accompanying some of the notebooks for executing RAG techniques.
Tutorials covering query transformations, HyDE, and HyPE to improve retrieval effectiveness.
Tutorials demonstrating semantic chunking, proposition chunking, and contextual chunk headers to improve retrieval accuracy.
Limitations and risks
The project is licensed under a custom non-commercial license, restricting its use in commercial applications.
Getting started
Getting started is easy: clone this repository, navigate to the technique you are interested in, and follow the detailed implementation guide in each technique's directory.
Evidence and sources
GitHub project description: This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.
README: 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…
README: This repository showcases a curated collection of advanced techniques designed to supercharge your RAG systems, enabling them to deliver more accurate, contextually relevant, and…
README: Our goal is to provide a valuable resource for researchers and practitioners looking to push the boundaries of what's possible with RAG.
README: - 🧠 State-of-the-art RAG enhancements - 📚 Comprehensive documentation for each technique - 🛠️ Practical implementation guidelines - 🌟 Regular updates with the latest advancements