Multimodal
-

Google Debuts Gemini Embedding 2 for Unified Multimodal AI
Google has launched Gemini Embedding 2, a natively multimodal AI model capable of mapping text, images, video, and audio into a single unified space.

Google has launched Gemini Embedding 2, a natively multimodal AI model capable of mapping text, images, video, and audio into a single unified space.