Google has released Gemini Embedding 2, which for the first time unifies text, images, video, and audio in a single vector space.

Source Brief

Google has released Gemini Embedding 2, which for the first time unifies text, images, video, and audio in a single vector space. This native multimodal embedding model aims to cut costs and speed up processing in enterprise data stacks. It marks a significant advancement in how machines represent and retrieve information across different media types.