Property PreferredInferenceModality

Namespace

LMKit.Extraction

Assembly

LM-Kit.NET.dll

PreferredInferenceModality

Gets or sets the preferred modality for inference. This determines whether text, image, or both modalities are used when processing input. Defaults to Multimodal.

public InferenceModality PreferredInferenceModality { get; set; }

Property Value

InferenceModality

Examples

var te = new TextExtraction(LM.LoadFromModelID("lmkit-tasks:4b-preview"))
{
    PreferredInferenceModality = InferenceModality.Text // force text-only for plain emails
};

te.Elements = new List<TextExtractionElement>
{
    new TextExtractionElement("Subject", ElementType.String),
    new TextExtractionElement("Sender", ElementType.String)
};

te.SetContent("Subject: Project Kickoff\nFrom: alice@contoso.com");
var result = te.Parse();
Console.WriteLine(result.Json);