OptionalenableWhen true, includes a per-label confidence score in the response.
OptionalenableWhen true, includes a rationale explaining each classification in the response.
OptionalinstructionsGlobal description of the task and domain, passed to the model to improve classification quality.
OptionallabelWhere the labels come from. Exactly one source must be set.
Labels listed inline, for a small label set.
OptionalmultilabelWhen true, more than one label can be returned for each input.
OptionalversionThe ai_classify function version to invoke (for example, 2.1).
Configuration for a task that runs the
ai_classifyfunction.The label set comes from exactly one of two places:
inline_labels, which holds up to 10 labels, or a Unity Catalog table named bylabel_table. Uselabel_tablefor a larger label set.