OptionaldescriptionOptional description for this field, at most 256 bytes. null in responses when none was set.
OptionaldimensionThe dimension of the vectors the model produces. null for models that produce sparse vectors.
OptionalmetricThe distance metric used for similarity search. Defaults to the model's preferred metric if not specified.
Possible values: cosine, dotproduct, or euclidean.
The name of the integrated embedding model to use for this field.
OptionalreadModel-specific parameters applied at query time, such as input_type.
Identifies this as a semantic text field. Must be semantic_text.
OptionalwriteModel-specific parameters applied at write time, such as input_type.
A semantic text field, as returned when describing an index created with an integrated embedding model. Backed by an integrated embedding model that embeds text at write and query time, enabling semantic similarity search without separate embedding calls. Cannot be declared when creating an index; use the create-for-model operation.
Export
SemanticTextField