Xenova/bge-m3 is a port of the BGE-M3 embedding model designed to run in the browser via Transformers.js. It provides high-quality dense vector embeddings for text in multiple languages. The model is optimized for on-device or client-side semantic search, retrieval, and RAG applications where sending data to a remote server is undesirable.
In the Embeddings & retrieval space, Bge M3 takes a focused approach. It focuses on running high-quality text embedding models directly in web browsers and JavaScript environments without server dependencies. It is built as an open-source project for developers. The project is open source (Open Source). Bge M3 is available on the web, the command line, and API.
Behind Bge M3 is Xenova. Key capabilities include text embeddings, multilingual, and browser compatible.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do