flexrag 0.2.0

A RAG Framework for Information Retrieval and Generation.

[ English | 中文 ]

FlexRAG is a highly reproducible, easy-to-use, and high-performance RAG framework designed for both research and application scenarios. It supports text, multimodal, and web-based RAG, providing a complete RAG pipeline and evaluation process. With built-in asynchronous processing and persistent caching, it ensures efficiency and scalability. Easily load retrievers from Hugging Face and quickly build powerful RAG solutions out of the box.

https://github.com/user-attachments/assets/4dfc0ec9-686b-40e2-b1f0-daa2b918e093

📖 Table of Contents

• 📖 Table of Contents
• ✨ Key Features
• 📢 News
• 🚀 Getting Started
• 🏗️ Architecture
• 📊 Benchmarks
• 🏷️ License
• ❤️ Acknowledgements

✨ Key Features

• 🎯 High Reproducibility: FlexRAG comes with a companion repository, flexrag_examples, providing comprehensive reproduction cases for various RAG algorithms. Additionally, unified retrievers available on the HuggingFace Hub ensure easy replication of experimental results under the same environment.
• ✅ Low Learning Curve: Download and load retrievers from the HuggingFace Hub with a single command, eliminating complex setup processes. Moreover, FlexRAG offers carefully optimized default configurations, allowing you to achieve excellent performance right out of the box and streamlining the development process.
• 🌍 Diverse Application Scenarios: FlexRAG supports not only text-based RAG but also multimodal and network-based RAG, enabling broad applications across different data types.
• 🧪 Research-Oriented: Provides a unified evaluation process for various RAG tasks, making it easy to test across different datasets. Official benchmark tests are also available for convenient comparison and reference.
• ⚡ Superior Performance: Leverages persistent caching and asynchronous functions to enhance high-performance RAG development.
• 🔄 End-to-End Support: From document information extraction and segmentation to retrieval, generation, and evaluation of output quality, FlexRAG fully supports every stage of the RAG lifecycle.
• 🛠️ Modular & Flexible Design: With a lightweight modular architecture, FlexRAG accommodates multiple development modes, helping you quickly build customized RAG solutions.

📢 News

• 2025-03-24: The Chinese documentation is now available! Please visit the documentation for more details.
• 2025-2-25: FlexRAG's LocalRetriever now supports loading from the HuggingFace Hub.
• 2025-01-22: A new entrypoint run_retriever and four new information retrieval metrics (e.g., RetrievalMAP) are now available. Check out the documentation for more details.
• 2025-01-08: We provide Windows wheels for FlexRAG. You can install FlexRAG via pip on Windows now.
• 2025-01-08: The benchmark of FlexRAG on Single-hop QA tasks is now available. Check out the benchmarks for more details.
• 2025-01-05: Documentation for FlexRAG is now available. Check out the documentation for more details.

🚀 Getting Started

To install FlexRAG via pip:

pip install flexrag

Visit our documentation to learn more.

• Installation
• Quickstart
• Entrypoints

🏗️ Architecture

FlexRAG is designed with a modular architecture, allowing you to easily customize and extend the framework to meet your specific needs. The following diagram illustrates the architecture of FlexRAG:

📊 Benchmarks

We have conducted extensive benchmarks using the FlexRAG framework. For more details, please refer to the benchmarks page.

🏷️ License

This repository is licensed under the MIT License. See the LICENSE file for details.

❤️ Acknowledgements

This project benefits from the following open-source projects:

• Faiss
• FlashRAG
• LanceDB
• ANN Benchmarks
• Chonkie
• rerankers