What is EmbeddingGemma 2?

Search tools and AI assistants need a way to find content by meaning, not just exact words. A common approach turns each piece of content into a list of numbers (a vector) so that items with similar meaning end up close together, and retrieval-augmented generation lets an AI model look up relevant documents before it answers. EmbeddingGemma 2 is an open embedding model from Google DeepMind that places text (including code), images, video and audio in one shared vector space (every item becomes a list of 768 numbers). The maker describes it as designed to run on consumer hardware such as mobile devices and laptops, for uses like search, retrieval, classification and clustering.

Written from primary sources and reference pages, and checked against them by an independent AI fact-checker. Drafted with AI assistance.