AI Text Translator

BptAITextPrompt

The BptAITextPrompt tool lets you translate, create and otherwise handle text requirements by using ONNX Runtime models.

Note: AI models are not included with this component. The models available on this demo page are for testing purposes only. Feel free to use your own models. In Server mode, the ONNX model runs locally on the server using Microsoft.ML.OnnxRuntimeGenAI. The model is automatically downloaded from Hugging Face on first use if not already present.

This AI component can run with or without its built-in UI. Set ShowBuiltInUI="false" to use it as a purely technical component — load the model, push data in, and receive results through events.

AI Text Prompt Parameters

Feedback window

Current Configuration

📋

<BptAITextPrompt @ref="BptAITextComponent"
    Mode="BptAITextPromptMode.Server"
    Debug="true"
    UseGPU="true"
    ModelPath="@ModelPath"
    AutoProvision="true"
    AutoProvisionModel="@CurrentModel"
    HuggingFaceApiKey="@HuggingFaceApiKey"
    OnResponseTokenPartComplete="@TextResponseTokenPartComplete"
    OnResponseCompleted="TextResponseCompleted"
    OnStatusUpdate="@HandleStatusUpdate"
    OnModelLoaded="@HandleModelLoaded">
</BptAITextPrompt>

@code {
// Fields
private String UserPrompt { set; get; } = "";
private String AIResponseText { set; get; } = "";
private String StatusText { set; get; } = "";
private String ModelPath { set; get; } = @"/data/models/phi-4-mini-instruct";
private Boolean _isModelLoaded { set; get; } = false;
private BptAITextPrompt? BptAITextComponent;

// Event handlers
private async Task HandleStatusUpdate(string status)
{
    StatusText = status;
    await InvokeAsync(StateHasChanged);
}

private async Task HandleModelLoaded(bool success)
{
    _isModelLoaded = success;
    await InvokeAsync(StateHasChanged);
}

private async Task TextResponseCompleted(String complete_response)
{
    AIResponseText = complete_response;
}
}