$vectorSearch (aggregation)

$vectorSearch performs a semantic search on data in your Atlas cluster. If you store vector embeddings that are less than or equal to 4096 dimensions in width for any kind of data along with other data in your collection on the Atlas cluster, you can seamlessly index the vector data along with your other data. You can then use the $vectorSearch stage to pre-filter your data and perform semantic search against the indexed fields. See:

• Index Vector Embeddings to learn more about creating Atlas Vector Search indexes.

• Vector Search Queries to learn more about $vectorSearch pipeline stage syntax and usage.