RAG_Techniques and rag-cookbooks

These are complementary educational resources that together provide both breadth (NirDiamant's RAG_Techniques covers diverse methodologies) and depth (athina-ai's rag-cookbooks offers practical implementation patterns), allowing practitioners to learn theoretical concepts and then apply them through worked examples.

RAG_Techniques
57
Established
rag-cookbooks
47
Emerging
Maintenance 10/25
Adoption 10/25
Maturity 16/25
Community 21/25
Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 21/25
Stars: 25,887
Forks: 3,041
Downloads:
Commits (30d): 0
Language: Jupyter Notebook
License:
Stars: 2,467
Forks: 310
Downloads:
Commits (30d): 0
Language: Jupyter Notebook
License: MIT
No Package No Dependents
Stale 6m 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 rag-cookbooks

athina-ai/rag-cookbooks

This repository contains various advanced techniques for Retrieval-Augmented Generation (RAG) systems.

Covers advanced RAG patterns including hybrid search (vector + BM25), query rewriting, document compression, and multi-document ranking via RAG Fusion, alongside agentic approaches using LangGraph. Integrates with LangChain, vector databases (Pinecone, Chromadb, Weaviate, Qdrant), and Athina AI's evaluation framework, with runnable Colab notebooks demonstrating end-to-end implementations from indexing through generation and evaluation.

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