README.md

Blazor AI Chat - How to add the DevExpress Blazor AI Chat component to your next Blazor, MAUI, WPF, and WinForms application

The DevExpress Blazor AI Chat component (DxAIChat) allows you to incorporate AI-powered interactions into any Blazor/MAUI/WPF/WinForms application. Our AI Chat component ships with a variety of high impact features, including:

• Customizable message appearance and empty message area
• Text or markdown response
• Manual message processing
• Streaming response

Implementation Details

This example adds a DxAIChat to a Blazor application, customizes its settings, and integrates it into WinForms, WPF, and .NET MAUI applications.

Register AI Service

Note

DevExpress AI-powered extensions follow the "bring your own key" principle. DevExpress does not offer a REST API and does not ship any built-in LLMs/SLMs. You need an active Azure/Open AI subscription to obtain the REST API endpoint, key, and model deployment name. These variables must be specified at application startup to register AI clients and enable DevExpress AI-powered Extensions in your application.

Add the following code to the Program.cs file to register the AI Chat service in your application:

using Azure.AI.OpenAI;
using DevExpress.AIIntegration;
using Microsoft.Extensions.AI;
using System.ClientModel;

string azureOpenAIEndpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT");
string azureOpenAIKey = Environment.GetEnvironmentVariable("AZURE_OPENAI_API_KEY");
string deploymentName = string.Empty;
...
var azureClient = new AzureOpenAIClient(
    new Uri(azureOpenAIEndpoint),
    new ApiKeyCredential(azureOpenAIKey));

builder.Services.AddDevExpressBlazor();
builder.Services.AddChatClient(cfg => 
    cfg.Use(azureClient.AsChatClient((deploymentName)))
);

File to review: Program.cs

Add DxAIChat component to a Blazor Application

Add a <DxAIChat>…</DxAIChat> markup to a .razor file:

@using DevExpress.AIIntegration.Blazor.Chat
@using AIIntegration.Services.Chat;

<DxAIChat CssClass="my-chat" />

.my-chat {
    width: 700px;
    margin: 20px;
}

File to review: Chat.razor

Customize message appearance and empty message area

DxAIChat component includes the following message customization properties:

• MessageTemplate - specifies the template used for message bubbles.
• MessageContentTemplate - specifies the template used for message bubble content.
• EmptyMessageAreaTemplate - specifies the template used for the empty message area.

<DxAIChat CssClass="my-chat">
    <EmptyMessageAreaTemplate>
        <div class="my-chat-ui-description">
            AI Assistant is ready to answer your questions.
        </div>
    </EmptyMessageAreaTemplate>
    <MessageTemplate>
        <div class="@GetMessageClasses(context)">
            @if(context.Typing) {
                <span>Loading...</span>
            } else {
                <div class="my-chat-content">
                    @context.Content
                </div>
            }
        </div>
    </MessageTemplate>
</DxAIChat>

File to review: Chat-CustomMessage.razor, Chat-CustomEmptyState.razor

Text or markdown response

The AI service uses plain text as the default response format.

To display rich formatted messages, set the ResponseContentFormat property to Markdown. Use a markdown processor to convert response content to HTML code.

@using Markdig;

<DxAIChat CssClass="my-chat" RenderMode="AnswerRenderMode.Markdown">
    <MessageContentTemplate>
        <div class="my-chat-content">
            @ToHtml(context.Content)
        </div>
    </MessageContentTemplate>
</DxAIChat>

@code {
    MarkupString ToHtml(string text) {
        return (MarkupString)Markdown.ToHtml(text);
    }
}

Manual message processing

When a user sends a message to the chat, the MessageSent event fires. Handle the event to manually process this action. You can use the Content event argument to access user input and call the SendMessage method to send another message to the chat.

<DxAIChat CssClass="my-chat" MessageSent="MessageSent" />

@code {
    async Task MessageSent(MessageSentEventArgs args) {
        await args.Chat.SendMessage($"Processed: {args.Content}", Microsoft.Extensions.AI.ChatRole.Assistant);
    }
}

File to review: Chat-MessageSent.razor

Streaming response

After a user sends a request, the AI client generates and sends the entire response back. This operation may be time consuming. To make the chat appear more responsive, set the UseStreaming property to true. In this instance, the AI client transmits parts of the response as it becomes available and the chat component adds these parts to the display message.

<DxAIChat CssClass="my-chat" UseStreaming="true" />

File to review: Chat-Streaming.razor

Compatibility with OpenAI assistants

The DevExpress AI Chat (DxAIChat) component supports OpenAI Assistants. This allows you to specify a model and supply supplementary documents (external knowledge). OpenAI parses these documents and searches through them to retrieve relevant content to answer user queries.

Add the following code to the Program.cs file to register AI Assistant service in the application:

builder.Services.AddDevExpressAI((config) => {
    //Reference the DevExpress.AIIntegration.OpenAI NuGet package to use Open AI Assistants
    config.RegisterOpenAIAssistants(azureClient, "gpt4o"); 
});

Include a supplementary document in the project file as an EmbeddedResource:

<EmbeddedResource Include="Data\Restaurant Menu.pdf" />

Handle the Initialized event and call the SetupAssistantAsync method to supply a file to the Open AI Assistant.

<DxAIChat CssClass="my-chat" Initialized="Initialized" />

@code {
    const string DocumentResourceName = "DevExpress.AI.Samples.Blazor.Data.Restaurant Menu.pdf";
    const string prompt = "...";

    async Task Initialized(IAIChat chat) {
        await chat.SetupAssistantAsync(new OpenAIAssistantOptions(
            $"{Guid.NewGuid().ToString("N")}.pdf",
            Assembly.GetExecutingAssembly().GetManifestResourceStream(DocumentResourceName),
            prompt)
        );
    }
}

File to review: Chat-Assistant.razor

Integrate AI Chat into WinForms, WPF and .NET MAUI Apps

Thanks to both Blazor Hybrid technology and the BlazorWebView component, you can integrate DevExpress AI Chat (DxAIChat) into your next great WinForms, WPF, and .NET MAUI application.

Keys to implementation are as follows:

• The ISelfEncapsulationService interface allows you to work directly with the DxAIChat component instance/properties from your desktop or mobile app.
• Built-in DxAIChat wrappers initialize required Blazor Theme scripts.
• Custom CSS classes hide the built-in input field and the Send button (see index.html).

Folders to review: DevExpress.AI.Samples.MAUIBlazor, DevExpress.AI.Samples.WPFBlazor For more information on how to use AI extensions in WPF apps, refer to the following help topic: AI-powered Extensions for WPF

For WinForms apps, use the built-in AIChatControl component. Refer to the following help topic to learn more about the integration steps: AI Chat Control Documentation

Folders to review: DevExpress.AI.Samples.WinBlazor

Files to Review

• Chat.razor
• Chat-CustomMessage.razor
• Chat-CustomEmptyState.razor
• Chat-MessageSent.razor
• Chat-Streaming.razor
• Chat-Assistant.razor
• Program.cs

Folders to Review

• DevExpress.AI.Samples.MAUIBlazor
• DevExpress.AI.Samples.WinBlazor
• DevExpress.AI.Samples.WPFBlazor

Documentation

• Create a Blazor Hybrid Project

More Examples

• Rich Text Editor and HTML Editor for Blazor - How to integrate AI-powered extensions

Does this example address your development requirements/objectives?

(you will be redirected to DevExpress.com to submit your response)