You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
@elliotsayes I think this is the case where the model being used to encode in the search_image endpoint does not match the model being used for unsplash_images. For matching the images found in unsplash images, I believe the model being used there is https://hub.getvectorai.com/model/image%2Fbit-medium and then using the search API or SDK method
Is there a way to select the model for the search_image endpoint? I want to generate the vector on the server, and ideally not bother with transferring the vector back and forth.
Using the
unsplash-images
collection: https://playground.getvectorai.com/collections/?collection=unsplash-imagesresult for:
vi_client.search_image('unsplash-images', image_url, ['image_url_vector_'])
with
image_url
as:https://www.rover.com/blog/wp-content/uploads/2020/06/siberian-husky-4735878_1920.jpg
https://davidkerrphotography.co.nz/wp-content/uploads/2016/10/Slide01.jpg
identical result for both:
The text was updated successfully, but these errors were encountered: