Bring multimodal semantic search to the edge with EmbeddingGemma 2

T1Covered by 1 source · first reported by Google — The Keyword / AI / Research / DeepMind / Developers at 06 Oct, 16:21 UTC

EmbeddingGemma 2 is a new 740M open-weight multimodal model that maps text, images, video, and audio into a unified vector space for privacy-first, on-device retrieval. Developers can easily integrate these capabilities cross-platform using MediaPipe Tasks or optimize fine-grained performance…

Sources

• T1Bring multimodal semantic search to the edge with EmbeddingGemma 2Google — The Keyword / AI / Research / DeepMind / Developers06 Oct, 16:21