fed-rag and RAGHub

Fed-RAG is a specialized fine-tuning framework that could be integrated into or benchmarked against RAGHub's broader collection of RAG implementations and resources.

fed-rag
65
Established
RAGHub
56
Established
Maintenance 10/25
Adoption 10/25
Maturity 25/25
Community 20/25
Maintenance 10/25
Adoption 10/25
Maturity 16/25
Community 20/25
Stars: 141
Forks: 28
Downloads:
Commits (30d): 0
Language: Python
License: Apache-2.0
Stars: 1,590
Forks: 150
Downloads:
Commits (30d): 0
Language:
License: MIT
No risk flags
No Package No Dependents

About fed-rag

VectorInstitute/fed-rag

A framework for fine-tuning retrieval-augmented generation (RAG) systems.

This is a framework for developers and machine learning engineers to improve the accuracy and relevance of their Retrieval-Augmented Generation (RAG) systems. It helps fine-tune these systems to produce better responses by integrating external data sources, whether that data is stored centrally or distributed across different locations. Users provide their RAG models and data, and the framework outputs an enhanced RAG system.

Machine Learning Engineering Generative AI Federated Learning Natural Language Processing AI System Optimization

About RAGHub

Andrew-Jang/RAGHub

A community-driven collection of RAG (Retrieval-Augmented Generation) frameworks, projects, and resources. Contribute and explore the evolving RAG ecosystem.

This is a living directory of tools, frameworks, and resources for Retrieval-Augmented Generation (RAG). It helps you navigate the rapidly changing landscape of RAG by providing a curated list of new and emerging solutions. You'll find frameworks for building RAG applications, evaluation tools, and data preparation frameworks. Developers and AI engineers who are building or evaluating RAG systems would use this to stay informed and choose appropriate tools.

LLM development AI engineering RAG systems Generative AI AI tools directory

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