Supabase· 13 FebMatryoshka embeddings: faster OpenAI vector search using Adaptive Retrieval
OpenAI's new embedding models can be shortened via Matryoshka Representation Learning.
New model
Original post · supabase.com ↗Summary by forck
OpenAI released text-embedding-3-small and text-embedding-3-large, which outperform the previous text-embedding-ada-002 model on MTEB and MIRACL benchmarks.
The models include a dimensions API parameter that allows shortening the embedding vector to any size, enabled by Matryoshka Representation Learning (MRL), a training technique that preserves semantic meaning in truncated sub-vectors.
