Building with Gemini Embedding 2: Agentic multimodal RAG and beyond

Source: Google Developers Blog

Gemini Embedding 2 now generally available

Google has announced the general availability of Gemini Embedding 2, a unified model that maps text, images, video, audio, and documents into a single semantic space. This model allows developers to process interleaved multimodal inputs in a single request, significantly improving performance for tasks like agentic RAG, visual search, and content moderation. By supporting over 100 languages and offering features such as task‑specific prefixes and Matryoshka dimensionality reduction, the model provides a highly efficient and accurate foundation for building complex AI agents.