fed-rag and FlexRAG
These are competitors offering different approaches to RAG system development—fed-rag emphasizes fine-tuning existing RAG architectures while FlexRAG provides a flexible framework for building information retrieval and generation pipelines from scratch.
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 FlexRAG
ictnlp/FlexRAG
FlexRAG: A RAG Framework for Information Retrieval and Generation.
Supports text, multimodal, and web-accessible RAG scenarios through a modular pipeline architecture with integrated retrieval metrics and reranking components. Built on vectorized indexing (Faiss, LanceDB) with pre-trained retrievers available on HuggingFace Hub, enabling end-to-end workflows from corpus preparation through system evaluation and benchmarking.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work