Cohere Embed multimodal embeddings model is now available on Amazon SageMaker JumpStart

This article discusses the availability of the Cohere Embed multimodal embeddings model on Amazon SageMaker JumpStart. Cohere Embed 3 is capable of generating embeddings from both text and images, enabling enterprises to leverage their multimodal data.

Specifically, the article covers:

• Overview of multimodal embeddings and multimodal Retrieval Augmented Generation (RAG) architectures.
• Benefits and capabilities of Cohere's Embed 3 multimodal model, including use cases like ecommerce product catalogs and design file search.
• Solution overview for deploying the model on SageMaker, including prerequisites and subscribing to the model.
• Code examples for inference with text and image inputs, generating embeddings, and similarity search.
• Conclusion highlighting the availability of the model on SageMaker JumpStart.