Cohere

We used Cohere multi-modal embeddings to select the images for the articles. We found that this works better than GPT-Vision to select high-quality images that are contextually relevant to the surrounding text. This was a hard problem to solve, and Cohere's multi-modal embedding quality helped improve the quality of the selected images.

We are blown away by Cohere 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.

We used Cohere as it was a cost-effective document indexing solution that provided efficient embedding generation for knowledge base features.