BGE-M3

BGE-M3 is an open-weight multilingual text embedding model from the Beijing Academy of Artificial Intelligence (BAAI) that unifies dense, sparse, and multi-vector (ColBERT-style) retrieval in a single model. It supports 100+ languages and input sequences up to 8,192 tokens, making it suited for semantic search, keyword retrieval, and hybrid RAG pipelines. Source: supabase.