Skip to content

FedRAG

Simplified RAG fine-tuning across centralized or federated architectures

Read the paper (Accepted in CODEML Workshop at ICML 2025, Vancouver)

  • Advanced RAG fine-tuning

    Comprehensive support for state-of-the-art RAG fine-tuning methods that can be federated with ease.

    Getting started

  • Work with your tools

    Seamlessly integrates with popular frameworks including HuggingFace, and LlamaIndex — use the tools you already know.

    In-Depth Examples

  • Lightweight abstractions

    Clean, intuitive abstractions that simplify RAG fine-tuning while maintaining full flexibility and control.

    API Reference