A very common workflow is to index some data based on its embeddings and then given a new query embedding retrieve the most similar examples with k-Nearest Neighbor search. For example, you can imagine embedding a large collection of papers by their abstracts and then given a new paper of interest retrieve the most similar papers to it.
TLDR in my experience it ~always works better to use an SVM instead of kNN, if you can afford the slight computational hit
B. Hidasi, A. Karatzoglou, L. Baltrunas, and D. Tikk. (2015)cite arxiv:1511.06939Comment: Camera ready version (17th February, 2016) Affiliation update (29th March, 2016).