ChoiceQuestion interface

Question configuration for a Categorical Choice evaluation.

Signature:

export declare interface ChoiceQuestion 

Properties

Property Type Description
audioSamples Float32Array Optional mono 16kHz PCM audio samples in [-1.0, 1.0] for the context.
context string Optional domain or schema context prepended to instructions.
criteria Record<string, string> Map of choice keys to descriptive phrases or criteria.
imageBytes Uint8Array Optional raw encoded image bytes (PNG, JPEG, WebP, or TGA) for the context.
instructions string Optional task instruction prompt for the model.
normalizePrior boolean Subtracts the memoized empty-context ("[None]") prior distribution in log-probability space to eliminate positional or label bias.
options ClassifierOption[] Ordered list of candidate options with { label, description }. Can be provided instead of or alongside criteria.
scoringMode number Scoring mode (0=SCORING_AUTO, 1=SCORING_SINGLE_TOKEN, 2=SCORING_FULL_OPTION). Defaults to 0 (SCORING_AUTO).
temperature number Softmax temperature override (> 0.0). When unset or <= 0, the model's calibrated temperature is used.

ChoiceQuestion.audioSamples

Optional mono 16kHz PCM audio samples in [-1.0, 1.0] for the context.

Signature:

audioSamples?: Float32Array;

ChoiceQuestion.context

Optional domain or schema context prepended to instructions.

Signature:

context?: string;

ChoiceQuestion.criteria

Map of choice keys to descriptive phrases or criteria.

Signature:

criteria?: Record<string, string>;

ChoiceQuestion.imageBytes

Optional raw encoded image bytes (PNG, JPEG, WebP, or TGA) for the context.

Signature:

imageBytes?: Uint8Array;

ChoiceQuestion.instructions

Optional task instruction prompt for the model.

Signature:

instructions?: string;

ChoiceQuestion.normalizePrior

Subtracts the memoized empty-context ("[None]") prior distribution in log-probability space to eliminate positional or label bias.

Signature:

normalizePrior?: boolean;

ChoiceQuestion.options

Ordered list of candidate options with { label, description }. Can be provided instead of or alongside criteria.

Signature:

options?: ClassifierOption[];

ChoiceQuestion.scoringMode

Scoring mode (0=SCORING_AUTO, 1=SCORING_SINGLE_TOKEN, 2=SCORING_FULL_OPTION). Defaults to 0 (SCORING_AUTO).

Signature:

scoringMode?: number;

ChoiceQuestion.temperature

Softmax temperature override (> 0.0). When unset or <= 0, the model's calibrated temperature is used.

Signature:

temperature?: number;