Cohere Embed 4 представляет собой передовую мультимодальную модель эмбеддингов, оптимизированную для корпоративного поиска и RAG-систем. Она позволяет ИИ-агентам мгновенно находить нужную информацию, понимая бизнес-контекст через текст и изображения одновременно.
Today we’re releasing Embed 4: our latest state-of-the-art multimodal embedding model that enables enterprises to add frontier search and retrieval capabilities to AI applications — a necessity for businesses building assistants or agents that need to understand their business context. 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.