Get the latest tech news

Cohere launches Embed 4: New multimodal search model processes 200-page documents


Cohere updated its model Embed 4 so enterprises can make embeddings from multimodal data sources and even longer documents.

Taking advantage of the continued interest in agents, Cohere released the latest version of its embeddings model with longer context windows and more multimodality. “Existing embedding models fail to natively understand complex multimodal business materials,‬‭ leading companies to develop cumbersome data pre-processing pipelines that only slightly‬‭ improve accuracy,” Cohere said in a blog post. Being able to‬ represent our products in a unified embedding makes our search faster and our internal tooling more‬ efficient,” said Param Jaggi, Founder of Agora‬, in the blog post.

Get the Android app

Or read this on Venture Beat

Read more on:

Photo of Cohere launches

Cohere launches

Photo of embed

embed

Photo of page documents

page documents

Related news:

News photo

LLVM Clang 19 Lands Support For C23's #embed

News photo

Cohere launches open weights AI model Aya 23 with support for nearly two dozen languages

News photo

Cohere launches Embed V3 for enterprise LLM applications