Identifying items in images using embeddings generated from the images and ranking candidates using a language model

Abstract

An online system applies a visual language model and an optical character recognition model to a received image to generate descriptive information about unknown items in the image. The online system prompts a generative model with the descriptive information about unknown items in the image to separate the descriptive information into different bins each corresponding to a different unknown item in the image. For each unknown item detected in the image, the online system generates a target embedding from its descriptive information and performs a nearest neighbor search on an item catalog including embeddings for various items to find a set of candidate embeddings matching the target embedding. The online system retrieves item attributes of candidate items each corresponding to a candidate embedding of the set and prompts the generative model with this information to rank candidate items for the unknown item in the image.