RAG_Techniques and Master-Retrieval-Augmented-Generation-RAG-Systems

These are complementary educational resources—one is a hands-on techniques repository for implementing RAG systems, while the other is a structured course/book codebase for learning RAG fundamentals, so they could be used together for both theoretical understanding and practical implementation patterns.

Maintenance 10/25
Adoption 10/25
Maturity 16/25
Community 21/25
Maintenance 6/25
Adoption 6/25
Maturity 9/25
Community 18/25
Stars: 25,887
Forks: 3,041
Downloads:
Commits (30d): 0
Language: Jupyter Notebook
License:
Stars: 21
Forks: 14
Downloads:
Commits (30d): 0
Language: Python
License: MIT
No Package No Dependents
No Package No Dependents

About RAG_Techniques

NirDiamant/RAG_Techniques

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and contextually rich responses.

Covers advanced RAG patterns including agentic retrieval loops, hybrid search strategies (dense-sparse retrieval fusion), query optimization techniques, and multi-document reasoning—beyond basic retrieval pipelines. Implementations target popular frameworks like LangChain and LlamaIndex with code-first Jupyter notebooks, focusing on practical enhancements for production-grade systems.

About Master-Retrieval-Augmented-Generation-RAG-Systems

PacktPublishing/Master-Retrieval-Augmented-Generation-RAG-Systems

This is the code repository for Master Retrieval-Augmented Generation (RAG) Systems, published by Packt Publishing

Covers naive through advanced RAG implementations with hands-on techniques including query expansion, dense passage retrieval, and cross-encoder/bi-encoder re-ranking for optimized document retrieval. Integrates practical optimization strategies for answer generation and demonstrates how to apply these patterns within AI applications through progressive, project-based learning modules.

Scores updated daily from GitHub, PyPI, and npm data. How scores work