#modular framework

This RAG framework offers an enhanced modular structure ensuring reliable inputs and trusted outputs for high-quality retrieval-augmented generation. It allows flexible adjustments to cater to diverse application needs, featuring latest updates such as multi-file type support, improved DenseRetriever, and new functionalities like ReRank and Judge. Users can choose between pip and source installation, aided by accessible quick start guides.

OmniSafe is a framework that facilitates safe reinforcement learning research. It offers a modular and extensible design, integrating advanced algorithms and high-performance parallel computing to improve training efficiency. The toolkits support a variety of tasks including benchmarking, which are suitable for both new and experienced researchers. The platform prioritizes risk reduction and safety, making it applicable across various fields in the SafeRL community.