A single question within a multi-question ClassifierSchema. **Signature:** export declare interface ClassifierQuestion ## Properties | Property | Modifiers | Type | Description | |---|---|---|---| | [id](https://developers.google.com/edge/api/mediapipe/js/tasks-decision.classifierquestion#classifierquestionid) | | string | Unique identifier key in the returned ClassifierResult record. | | [type](https://developers.google.com/edge/api/mediapipe/js/tasks-decision.classifierquestion#classifierquestiontype) | | ClassifierQuestionType | Question evaluation type. | | [prompt](https://developers.google.com/edge/api/mediapipe/js/tasks-decision.classifierquestion#classifierquestionprompt) | | string | Task instruction or natural language condition prompt. | | [options](https://developers.google.com/edge/api/mediapipe/js/tasks-decision.classifierquestion#classifierquestionoptions) | | ClassifierOption\[\] | Candidate options (required for categorical and ordinal; optional for binary). | | [threshold](https://developers.google.com/edge/api/mediapipe/js/tasks-decision.classifierquestion#classifierquestionthreshold) | | number | Decision threshold in \[0.0, 1.0\] for binary questions. Defaults to 0.5. | | [temperature](https://developers.google.com/edge/api/mediapipe/js/tasks-decision.classifierquestion#classifierquestiontemperature) | | number | Softmax temperature override (\> 0.0). When unset or \<= 0, the model's calibrated temperature is used. | | [normalizePrior](https://developers.google.com/edge/api/mediapipe/js/tasks-decision.classifierquestion#classifierquestionnormalizeprior) | | boolean | Whether to normalize against the empty-context ("\[None\]") prior. | ## ClassifierQuestion.id {#classifierquestionid} Unique identifier key in the returned ClassifierResult record. **Signature:** id: string; ## ClassifierQuestion.type {#classifierquestiontype} Question evaluation type. **Signature:** type: ClassifierQuestionType; ## ClassifierQuestion.prompt {#classifierquestionprompt} Task instruction or natural language condition prompt. **Signature:** prompt: string; ## ClassifierQuestion.options {#classifierquestionoptions} Candidate options (required for categorical and ordinal; optional for binary). **Signature:** options?: ClassifierOption[]; ## ClassifierQuestion.threshold {#classifierquestionthreshold} Decision threshold in \[0.0, 1.0\] for binary questions. Defaults to 0.5. **Signature:** threshold?: number; ## ClassifierQuestion.temperature {#classifierquestiontemperature} Softmax temperature override (\> 0.0). When unset or \<= 0, the model's calibrated temperature is used. **Signature:** temperature?: number; ## ClassifierQuestion.normalizePrior {#classifierquestionnormalizeprior} Whether to normalize against the empty-context ("\[None\]") prior. **Signature:** normalizePrior?: boolean;