MongoDB - Build AI That Scales
Mini toolsGemini Embedding 2
Model family: Gemini
Gemini Embedding 2 is Google’s first multimodal Gemini API embedding model. It maps text, images, video, audio, PDFs, and documents into a unified embedding space for cross-modal search, classification, clustering, RAG, recommendation, and retrieval across more than 100 languages, with Google Cloud listing 3072-dimensional vectors.
Multimodal
Gen 3
Overview
Gemini Embedding 2 is Google’s multimodal embedding model for unified text, image, video, audio, and document search.
About Google DeepMind
AI research lab within Google developing frontier models, scientific AI systems, reinforcement learning methods, and products that support Google services and research.
Industry:
Artificial Intelligence
Company Size:
6000
Location:
London, England, GB
Website:
deepmind.com
Tools using Gemini Embedding 2
-
Tealgreen🙏 404 karmaMar 29, 2025@GeminiThey nailed it. It’s better than 3.7 at coding.
Last updated: June 2, 2026
