Google unveils new multimodal Gemini Embedding 2 model

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

Google Gemini Embedding 2 Supports Text, Images, Audio, PDFs & Short Videos

Google Gemini Embedding 2 unifies text, images, audio, PDFs, and video; it supports 3,072-dimension vectors, simplifying retrieval stacks.

Gemini Embedding 2 Supports Search Across 100+ Languages

Gemini Embedding 2 ships cross-modality retrieval with Matryoshka vectors, offering flexible dimensions for cost and accuracy tradeoffs.

Google's Gemini Embedding 2 arrives with native multimodal support to cut costs and speed up your enterprise data stack

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 ...
VentureBeat

What is an embedding for AI?

Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More When a question is presented to an artificial intelligence (AI) algorithm ...