Google launches Gemini Embedding 2 — multimodal RAG and agentic AI

AI Impact Summary

Google has released Gemini Embedding 2, a unified model capable of embedding text, images, video, audio, and documents into a single semantic space. This unlocks agentic multimodal RAG, visual search, and content moderation use cases, offering developers a powerful tool for processing interleaved inputs. The model’s support for over 100 languages and features like task-specific prefixes and dimensionality reduction enable efficient and accurate AI agent development.