BAAI/bge-small-en-v1.5

BGE-small-en-v1.5 is a compact English text-embedding model from the Beijing Academy of Artificial Intelligence that encodes sentences into 384-dimensional vectors for semantic search, retrieval, and RAG pipelines. It is the smallest model in the BGE v1.5 English family, optimized for low-latency, resource-constrained deployments. Source: supabase.