Real-world uses

Created for this library

1. 1.

   A retail recommender team uses cosine similarity as the similarity measure between user and product embeddings in its candidate generator.

2. 2.

   A search team uses dot-product similarity as the similarity measure in its retrieval index for efficient nearest-neighbor lookup.

3. 3.

   A help-desk team uses an embedding-based similarity measure to retrieve past tickets similar to a new one for resolution suggestions.