Rensa is a high-performance MinHash suite written in Rust with Python bindings. It's designed for efficient similarity estimation and deduplication of large datasets. It offers R-MinHash, C-MinHash, and OptDensMinHash variants, significantly faster than datasketch while maintaining comparable accuracy.
An open-source project offering a functional RAG UI for document QA, suitable for both end-users and developers. It supports various LLM providers, is customizable, and offers multi-modal QA, citations, and complex reasoning methods.