Follow up question on my earlier one https://typesense-community.slack.com/archives/C01P749MET0/p1696928604553359, I’ve got embedding vectors working from CLIP now - when using CLIP to get the custom embedding would I pass the image and text (product name in this case) into CLIP or just the image to get the custom embedding? Unsure if there is a difference from Typesense perspective? Thanks! (Use case initially will be “similar products” & “you might also like” on ecommerce sites)

> would I pass the image and text (product name in this case) into CLIP You want to do this, since CLIP embeds both the text and image