Google released its first fully multimodal embedding model on Tuesday. Dubbed Gemini Embedding 2, the artificial intelligence (AI) model maps text, images, audio, and videos into a single, unified embedding space. This means it uses a architecture to understand concepts whether they are written as words, spoken aloud, or shown in an image or a video.Google released its first fully multimodal embedding model on Tuesday. Dubbed Gemini Embedding 2, the artificial intelligence (AI) model maps text, images, audio, and videos into a single, unified embedding space. This means it uses a architecture to understand concepts whether they are written as words, spoken aloud, or shown in an image or a video.
