Sofia Vasileva
Product Marketing Manager
A picture is worth 1.5x the words: What we learned benchmarking product search embeddings
We benchmarked two embedding models on 5,000 real products and found that combining image and text beats either alone by up to 50%. Here's the data and the model that won.
jina-embeddings-v5-text: Compact state-of-the-art text embeddings for search and intelligent applications
Introducing jina-embeddings-v5-text models, including jina-embeddings-v5-text-small and jina-embeddings-v5-text-nano, and explaining how to use these multilingual embedding models via Elastic Inference Service (EIS).