Multimodal decision input combining text, encoded image bytes, and/or 16kHz mono PCM audio samples.
Signature:
export declare interface DecisionContextInput
Properties
| Property | Type | Description |
|---|---|---|
| audioSamples | Float32Array | Optional mono 16kHz PCM audio samples in [-1.0, 1.0]. |
| imageBytes | Uint8Array | Optional raw encoded image bytes (PNG, JPEG, WebP, or TGA). |
| text | string | Optional text context or query description. |
DecisionContextInput.audioSamples
Optional mono 16kHz PCM audio samples in [-1.0, 1.0].
Signature:
audioSamples?: Float32Array;
DecisionContextInput.imageBytes
Optional raw encoded image bytes (PNG, JPEG, WebP, or TGA).
Signature:
imageBytes?: Uint8Array;
DecisionContextInput.text
Optional text context or query description.
Signature:
text?: string;