RAG_Techniques and MiniRAG
These are complements: the techniques repository provides advanced RAG methodologies and patterns that can be implemented using smaller, open-source LMs like those optimized in MiniRAG, making them naturally paired for building efficient RAG systems with constrained resources.
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 MiniRAG
HKUDS/MiniRAG
"MiniRAG: Making RAG Simpler with Small and Open-Sourced Language Models"
Constructs a semantic-aware heterogeneous graph combining text chunks and named entities to reduce dependency on complex semantic understanding, then retrieves knowledge via lightweight topology-aware graph traversal rather than dense embeddings. Supports 10+ graph databases (Neo4j, PostgreSQL, TiDB) and achieves comparable performance to LLM-based RAG with 75% less storage while running small models like Phi-3.5-mini and Qwen2.5-3B on-device.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work