Skip to content
TopicTracker
From HackerNewsView original
TranslationTranslation

Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini

Google introduces Gemini Embedding 2, a native multimodal embedding model that processes text, images, audio, and video into unified embeddings. It achieves state-of-the-art performance on multilingual and multimodal retrieval benchmarks, outperforming prior text-only and multimodal models.

Related stories