$vector in collections (Java)

When you insert or update a document, you can use the $vector field to store a vector embedding for the document. For an example, see Insert documents with vector embeddings.

All vector embeddings in a collection should be generated by the same model with the same dimensions. Using mismatched embeddings produces unreliable and incorrect results in vector searches. The Data API only checks that the dimensions are the same; it doesn’t check whether the embeddings are from different models.

If your collection has an embedding provider integration, you can use the $vectorize field to automatically generate a vector embedding from a string. The Data API stores the generated vector embedding in the document’s $vector field. However, you can’t include both the $vector and $vectorize fields in the same insert or update operation.

When you find, update, replace, or delete documents, you can use the $vector field to perform a vector search. For an example, see Use vector search to find documents.

Similarly, when you find and rerank documents, you can use the $vector field to perform a hybrid search. For an example, see Find documents with a hybrid search.

By default, the Data API excludes the $vector field from returned documents. If you want the Data API to return the $vector field, you must use a projection to explicitly include the $vector field in the response.

When inserting or updating documents, you can specify the $vector field as an array of floats or use the DataAPIVector class to represent and encode the vector embedding. Similarly, for vector searches, you can provide the search vector as an array of floats or use the DataAPIVector class. DataAPIVector is a wrapper around an array of floats.

When you send a DataAPIVector object, the vector embeddings are binary-encoded by default. DataStax recommends that you always use a DataAPIVector object instead of a list of floats to improve performance.

For more information, see DataAPIVector.