Google introduces Gemini Embedding model: Experimental AI for text processing

SAN FRANCISCO, March 8 — Google has added a new, experimental “embedding” model for text, Gemini Embedding, to its Gemini developer API, the company announced on Friday, reported Xinhua.

“Trained on the Gemini model itself, this embedding model has inherited Gemini’s understanding of language and nuanced context, making it applicable for a wide range of uses,” Google said in a blog post.

“We’ve trained our model to be remarkably general, delivering exceptional performance across diverse domains, including finance, science, legal, search, and more.”

The company noted that Gemini Embedding is in an “experimental phase” with limited capacity and it’s “working towards a stable, generally available release in the months to come”.

Companies including Amazon, Cohere, and OpenAI offer embedding models through their respective APIs. Gemini Embedding is Google’s first embedding model trained on the Gemini family of AI models. — Bernama-Xinhua