Get the latest tech news

Cohere adds vision to its RAG search capabilities


Cohere enhances its embeddings model Embed 3 to now be multimodal, letting enterprises search images on their databases.

“This advancement enables enterprises to unlock real value from their vast amount of data stored in images,” Cohere said in a blog post. Cohere said encoders in Embed 3 “share a unified latent space,” allowing users to include both images and text in a database. Cohere, which was founded by some of the researchers responsible for the Transformer model (Gomez is one of the writers of the famous “Attention is all you need” paper), has struggled to be top of mind for many in the enterprise space.

Get the Android app

Or read this on Venture Beat

Read more on:

Photo of Vision

Vision

Photo of Cohere

Cohere

Photo of RAG

RAG

Related news:

News photo

Tim Cook Admits Truth About Vision Pro Following Lackluster Sales

News photo

Microsoft recruits accessibility app to make its AI more useful to blind and low-vision users

News photo

Hilton and Be My Eyes team up to make hotels more accessible for blind and low-vision users