Closed radao closed 2 years ago
Hi @radao, I haven't tested that scenario, but since EuclidesDB has to return only IDs, distances and model name, it should work fine, it might be a little slow only if you have a very slow connection. Please let me know later how the test was because I'm curious as well, thanks for testing that !
I see the main sorting function exposed is
db.find_similar_image
which takes as input an image, a model, and atopk
parameter and returns thetopk
most similar images. If we would like to sort the entire database on a query image, would settingtopk
to the number of images added to the database for a particular model space work or would this be prohibitively slow for large databases (500k+ images)? I plan on testing this myself but wanted to see if you did similar tests already.