Google releases a 740M-parameter embedding model for local multimodal search

EmbeddingGemma 2 maps text, code, images, video and audio into one vector space; Google says its weights are available under Apache 2.0.

By · Published · Updated

A small computer sits among text, code, a photograph, film frames, and headphones, with glass filaments joining them into one form to represent Google’s EmbeddingGemma.

EmbeddingGemma 2 maps text, code, images, video and audio into one vector space; Google says its weights are available under Apache 2.0.