FlexRAG: A Flexible and Comprehensive Framework for Retrieval-Augmented Generation

TL;DR

FlexRAG is an open-source, flexible framework that enhances retrieval-augmented generation research by addressing reproducibility, extensibility, and system efficiency challenges across multimodal and network-based RAG applications.

Contribution

It introduces a comprehensive, adaptable framework supporting various RAG modalities with lifecycle management, asynchronous processing, and caching, facilitating rapid development and sharing.

Findings

Supports text, multimodal, and network RAG

Provides efficient asynchronous processing and caching

Enables rapid development and sharing of RAG systems

Abstract

Retrieval-Augmented Generation (RAG) plays a pivotal role in modern large language model applications, with numerous existing frameworks offering a wide range of functionalities to facilitate the development of RAG systems. However, we have identified several persistent challenges in these frameworks, including difficulties in algorithm reproduction and sharing, lack of new techniques, and high system overhead. To address these limitations, we introduce \textbf{FlexRAG}, an open-source framework specifically designed for research and prototyping. FlexRAG supports text-based, multimodal, and network-based RAG, providing comprehensive lifecycle support alongside efficient asynchronous processing and persistent caching capabilities. By offering a robust and flexible solution, FlexRAG enables researchers to rapidly develop, deploy, and share advanced RAG systems. Our toolkit and resources are available at \href{https://github.com/ictnlp/FlexRAG}{https://github.com/ictnlp/FlexRAG}.