RAG_Techniques and raggenie

The first is an educational reference implementation of RAG techniques and patterns, while the second is a production-oriented low-code platform for deploying RAG applications—making them complementary resources where one teaches concepts and the other operationalizes them.

RAG_Techniques
57
Established
raggenie
51
Established
Maintenance 10/25
Adoption 10/25
Maturity 16/25
Community 21/25
Maintenance 2/25
Adoption 10/25
Maturity 16/25
Community 23/25
Stars: 25,887
Forks: 3,041
Downloads:
Commits (30d): 0
Language: Jupyter Notebook
License:
Stars: 180
Forks: 67
Downloads:
Commits (30d): 0
Language: Python
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 raggenie

sirocco-ventures/raggenie

RAGGENIE: An open-source, low-code platform to build custom Retrieval-Augmented Generation (RAG) Copilets with your own data. Simplify AI development with ease!

Supports multiple structured (MySQL, PostgreSQL, BigQuery, Airtable) and unstructured data sources with automatic query generation, while integrating with major LLM providers (OpenAI, Together.ai, Ollama, AI71). Features a capabilities framework with intent extraction to bind chatbot actions to database operations, plus a JavaScript UI widget for seamless embedding. Built on Python with Zitadel identity management and Chroma vector database for semantic search.

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