https://www.infoq.com InfoQ retrieval News feed https://www.infoq.com/news/2026/10/embeddinggemma-2-multimodal/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=retrieval-news <img src="https://res.infoq.com/news/2026/10/embeddinggemma-2-multimodal/en/headerimage/cactus-on-device-inference-1792401134408.jpeg"/><p>Based on Gemma 4 and released under the Apache 2.0 license, Google's EmbeddingGemma 2 is a compact, open-weight, multimodal embedding model designed to make semantic search and retrieval-augmented generation (RAG) more efficient while optimizing performance for on-device deployment.</p> <i>By Sergio De Simone</i> retrieval Large language models Mobile Agents Retrieval-Augmented Generation Google AI, ML & Data Engineering Development news Mon, 19 Oct 2026 10:00:00 GMT https://www.infoq.com/news/2026/10/embeddinggemma-2-multimodal/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=retrieval-news Sergio De Simone 2026-10-19T10:00:00Z /news/2026/10/embeddinggemma-2-multimodal/en