Cohere Launches Embed 4 to Supercharge Search and Retrieval for AI Agents and Enterprises

Cohere has launched Embed 4, its most advanced embedding model to date, designed to boost the performance of AI applications like virtual assistants, agents, and enterprise search systems by enabling faster and more accurate data retrieval.

At the core of retrieval-augmented generation (RAG) — a technique that allows generative AI models to fetch and incorporate real-time information — are embedding models.

Embed 4 converts a wide variety of content, including documents, images, tables, code, and diagrams, into numerical vectors that represent the context and meaning of the data, making it easier for AI to understand and use.

Embed 4 offers customers:

• State-of-the-art multimodality: Embed 4 is uniquely capable at accurately and quickly searching multifaceted documents such as intricate PDF reports and dynamic presentation slides — whether the document is text-based or includes images, tables, graphs, code, and diagrams.
• Breakthrough context length: Embed 4 can generate embeddings for documents up to 128K tokens (around 200 pages) in length such as annual financial reports, product manuals, or detailed legal contracts.
• Leading multilingual capabilities: Embed 4 is multilingual across 100+ languages including key business languages such as Arabic, Japanese, Korean, and French to support global enterprises.
• Enhancements for security-minded industries: Embed 4 is optimized with domain-specific understanding of data from regulated industries such as finance, healthcare, and manufacturing. It can be deployed in virtual private cloud (VPC) and on-premise environments to keep data secure.

Cohere said Embed 4 was built with industries such as finance, healthcare, and manufacturing in mind, offering tailored capabilities for processing business-critical documents like investor briefings, product specs, and medical records.

"Agora is an AI search engine that makes it easy to shop across 35,000 online stores in one place. We are blown away by Embed 4’s ability to accurately surface relevant products to search queries. E-commerce data is complex, containing images and multifaceted text descriptions. Being able to represent our products in a unified embedding makes our search faster and our internal tooling more efficient."
- Param Jaggi, Founder, Agora

Embed 4 also powers semantic search within Cohere’s AI agent platform, North, and its Compass product.

The model is available starting today through Microsoft Azure AI Foundry, Amazon SageMaker, and for private enterprise deployments.