Google Ships Gemini Embedding 2, Its First Natively Multimodal Embedding Model
Gemini Embedding 2 puts text, images, video, audio, and documents into a single embedding space — a technical milestone that could reshape how RAG pipelines and search systems handle mixed-modality data.
Google released Gemini Embedding 2, which it describes as the first fully multimodal embedding model built on the Gemini architecture. The model maps text, images, video, audio, and documents into a shared embedding space, as @OfficialLoganK announced. It's available in preview through both the Gemini API and Vertex AI.
Unlock the full briefing
Get every story in today's briefing, the full archive, and the daily AI intelligence brief.
All stories today
Full archive
Daily brief
Cancel anytime. Payments powered by Stripe.