MultimodalOutput<T>
Models & Types · AiDotNet.Interfaces
Represents an output from unified multimodal models.
Constructors
| Constructor |
Summary |
MultimodalOutput() |
|
Properties
| Property |
Summary |
Dictionary<string, object> Metadata { get; set; } |
Optional metadata about the output. |
ModalityType Modality { get; set; } |
The modality type of this output. |
T Confidence { get; set; } |
Confidence score for the output. |
string TextContent { get; set; } |
Text content (for text outputs). |
Methods
| Method |
Summary |
ValueTuple<int, int, int, int>? GetVideoDimensions() |
Gets the dimensions of video output data. |
ValueTuple<int, int, int>? GetImageDimensions() |
Gets the dimensions of image output data. |
Vector<T> GetAudioSamples() |
Gets audio data as waveform samples for audio outputs. |
Vector<T> GetImagePixels() |
Gets image data as pixel values for image outputs. |
Vector<T> GetVideoFrames() |
Gets video frame data for video outputs. |