How recommend method works in Nearest Neighbour Models?

[DmitriyPershukov]

Are there any papers that explain how recommending items to user works initem-item Nearest Neighbour Models?

This page https://benfred.github.io/implicit/api/models/cpu/knn.html# refers to this blog post https://www.benfrederickson.com/distance-metrics/. But as i understand it only explains how you find similiar items.

[DmitriyPershukov]

My only idea is that it maybe finds similiar items for items user interacted with and then sorts them by similarity and recommends top k. But im not sure if it is correct.