昨夜，谷歌宣布推出全新的多模态嵌入模型 Gemini Embedding 2，这是首个基于 Gemini 架构构建的原生多模态嵌入模型。目前，该模型已经通过 Gemini API 和 Vertex AI 向开发者提供公开预览。 与此前仅支持文本向量化的嵌入模型不同，Gemini Embedding 2 可以将文本、图像、视频、音频以及文档等多种数据类型映射到同一个统一的嵌入空间，从而支持跨媒体语义 ...

While previous embedding models were largely restricted to text, this new model natively integrates text, images, video, audio, and documents into a single numerical space — reducing latency by as muc ...

Google unveils Gemini Embedding 2, a multimodal AI model for RAG, semantic search and clustering across 100+ languages.

Google has launched Gemini Embedding 2, its first fully multimodal embedding model based on the Gemini system. This model ...

In a blog post, the tech giant detailed the new AI model. It is the successor to the text-only embedding model that was released last year, and it captures semantic intent across more than 100 ...

Google’s Gemini Embedding 2 is here. The new multimodal model improves how AI understands text, images, and video while cutting storage costs for developers.