fed-rag and RAG_Techniques
Fed-RAG provides a federated fine-tuning framework for optimizing RAG systems, while RAG_Techniques is an educational repository demonstrating implementation patterns—making them **complements** where techniques from the latter could inform the training approaches in the former.
About fed-rag
VectorInstitute/fed-rag
A framework for fine-tuning retrieval-augmented generation (RAG) systems.
Supports federated learning architectures alongside centralized setups, enabling distributed RAG fine-tuning across multiple clients. Integrates seamlessly with HuggingFace, LlamaIndex, and LangChain, providing state-of-the-art fine-tuning methods through lightweight abstractions that maintain full flexibility and control.
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.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work