Amazon Bedrock now supports compressed embeddings from Cohere Embed

This article announces that Amazon Bedrock now supports compressed embeddings (int8 and binary) from the Cohere Embed model, allowing developers to build more efficient generative AI applications without sacrificing performance.

Specifically, the article covers:

• Cohere Embed is a leading text embedding model used for Retrieval-Augmented Generation (RAG) and semantic search systems.
• Cohere's compression-aware model training allows Cohere Embed to output embeddings in smaller int8 and binary formats, reducing storage costs while maintaining accuracy.
• This enables faster, cheaper, and more efficient enterprise search applications, especially for large-scale, multi-tenant setups.
• Cohere's compressed embeddings help build scalable AI applications to support employees and customers.
• Cohere Embed int8 and binary embeddings are now available in Amazon Bedrock across regions where the Cohere Embed model is available.
• Links are provided to learn more and get started with Cohere models in Amazon Bedrock.