Getting Started with Blazor Inline AI Assist in Blazor WASM App
20 Jul 202611 minutes to read
This section briefly explains how to include the Blazor Inline AI Assist component in a Blazor WebAssembly App using Visual Studio, Visual Studio Code, and the .NET CLI.
Create a new Blazor WebAssembly (Standalone) App
Create a Blazor WebAssembly App using Visual Studio via Microsoft Templates or the Syncfusion® Blazor Extension.
Run the following command to create a new Blazor WebAssembly App.
dotnet new blazorwasm -o BlazorApp
cd BlazorAppAlternatively, create a Blazor WebAssembly App using Visual Studio Code via Microsoft Templates or the Syncfusion® Blazor Extension, or the C# Dev Kit extension.
Run the following command to create a new Blazor WebAssembly App.
dotnet new blazorwasm -o BlazorApp
cd BlazorAppInstall the required Blazor packages
Install the Syncfusion.Blazor.InteractiveChat and Syncfusion.Blazor.Themes NuGet packages. All Syncfusion Blazor packages are available on nuget.org. See the NuGet packages topic for details.
- Go to Tools → NuGet Package Manager → Manage NuGet Packages for Solution.
- Search the required NuGet packages (
Syncfusion.Blazor.InteractiveChatandSyncfusion.Blazor.Themes) and install them.
Alternatively, you can install the same packages using the Package Manager Console with the following commands.
Install-Package Syncfusion.Blazor.InteractiveChat -Version 34.1.29
Install-Package Syncfusion.Blazor.Themes -Version 34.1.29Open the terminal and run the following commands.
dotnet add package Syncfusion.Blazor.InteractiveChat -v 34.1.29
dotnet add package Syncfusion.Blazor.Themes -v 34.1.29Open the command prompt and run the following commands.
dotnet add package Syncfusion.Blazor.InteractiveChat -v 34.1.29
dotnet add package Syncfusion.Blazor.Themes -v 34.1.29Add import namespaces
After the packages are installed, open the ~/_Imports.razor file and import the Syncfusion.Blazor and Syncfusion.Blazor.InteractiveChat namespaces.
@using Syncfusion.Blazor
@using Syncfusion.Blazor.InteractiveChatRegister the Blazor service
Open the Program.cs file in Blazor WebAssembly App and register the Blazor service.
....
using Syncfusion.Blazor;
....
builder.Services.AddSyncfusionBlazor();
....Add stylesheet and script resources
The theme stylesheet and script can be accessed from NuGet through Static Web Assets. Include the stylesheet and script references in the ~wwwroot/index.html file.
...
<link href="_content/Syncfusion.Blazor.Themes/fluent2.css" rel="stylesheet" />
...
<script src="_content/Syncfusion.Blazor.Core/scripts/syncfusion-blazor.min.js" type="text/javascript"></script>Add Blazor Inline AI Assist component
Open a Razor file located in the ~/Pages/*.razor (for example, Home.razor) and add the Blazor Inline AI Assist component inside the razor file.
@using Syncfusion.Blazor.InteractiveChat
<style>
#editableText {
width: 100%;
min-height: 120px;
max-height: 300px;
overflow-y: auto;
font-size: 16px;
padding: 12px;
border-radius: 4px;
border: 1px solid;
}
</style>
<div id="container" style="height: 350px; width: 650px;">
<button id="summarizeButton" style="margin-bottom: 10px;" @onclick="ShowPopup"> Content Summarize </button>
<div id="editableText" contenteditable="true">
<p>
Inline AI Assist component provides intelligent text processing
capabilities that enhance user productivity. It leverages advanced
natural language processing to understand context and deliver
precise suggestions. Users can seamlessly integrate AI-powered
features into their applications.
</p>
<p>
With real-time response streaming and customizable prompts,
developers can create interactive experiences. The component
supports multiple response modes including inline editing and
popup-based interactions.
</p>
</div>
<SfInlineAIAssist @ref="inlineAssist"
RelateTo="#summarizeButton"
Target="#container"
PromptRequested="PromptRequest">
</SfInlineAIAssist>
</div>
@code
{
private SfInlineAIAssist inlineAssist = new();
private async Task PromptRequest(PromptRequestedEventArgs args)
{
await Task.Delay(1000);
string defaultResponse =
"For real-time prompt processing, connect the Inline AI Assist component to your preferred AI service, such as OpenAI or Azure Cognitive Services. Ensure you obtain the necessary API credentials to authenticate and enable seamless integration.";
await inlineAssist.UpdateResponseAsync(defaultResponse);
}
private async Task ShowPopup()
{
await inlineAssist.ShowPopupAsync();
}
}
Run the application
Press Ctrl+F5 (Windows) or ⌘+F5 (macOS) to launch the application. The Blazor Inline AI Assist component will render in your default web browser.
Open the terminal and run the following command.
dotnet runOpen the command prompt and run the following command.
dotnet runResponse display modes
Responses can be shown in two modes: Inline (updates content in-place) and Popup (shows responses in a floating popup). Toggle this behavior with the ResponseMode property.
@using Syncfusion.Blazor.InteractiveChat
@using Syncfusion.Blazor.Buttons
<style>
#editableText {
width: 100%;
min-height: 120px;
max-height: 300px;
overflow-y: auto;
font-size: 16px;
padding: 12px;
border-radius: 4px;
border: 1px solid;
}
</style>
<div class="container" style="height: 350px; width: 650px;">
<div style="margin-bottom: 10px;">
<label for="responseMode">Response Mode:</label>
<select id="responseMode" @onchange="OnResponseModeChangeAsync">
<option value="Popup">Popup</option>
<option value="Inline">Inline</option>
</select>
</div>
<SfButton id="summarizeButton" IsPrimary="true" Style="margin-bottom: 10px;" @onclick="OnSummarizeClick">Content Summarize</SfButton>
<div id="editableText" contenteditable="true">
@((MarkupString)editableContent)
</div>
<SfInlineAIAssist @ref="inlineAssist" ResponseMode="@currentResponseMode" RelateTo="#summarizeButton" PromptRequested="OnPromptRequestAsync"> <ResponseActions ItemSelect="OnItemSelectAsync"></ResponseActions>
</SfInlineAIAssist>
</div>
@code
{
private SfInlineAIAssist inlineAssist = new SfInlineAIAssist();
private ResponseDisplayMode currentResponseMode = ResponseDisplayMode.Popup;
private string editableContent = @"<p>Inline AI Assist component provides intelligent text processing capabilities that enhance user productivity. It leverages advanced natural language processing to understand context and deliver precise suggestions. Users can seamlessly integrate AI-powered features into their applications.</p>
<p>With real-time response streaming and customizable prompts, developers can create interactive experiences. The component supports multiple response modes including inline editing and popup-based interactions.</p>";
private async Task OnPromptRequestAsync(PromptRequestedEventArgs args)
{
await Task.Delay(1000);
string defaultResponse = "For real-time prompt processing, connect the Inline AI Assist component to your preferred AI service, such as OpenAI or Azure Cognitive Services. Ensure you obtain the necessary API credentials to authenticate and enable seamless integration.";
await inlineAssist.UpdateResponseAsync(defaultResponse);
}
private async Task OnItemSelectAsync(ResponseItemSelectEventArgs args)
{
if (args.Item.Label == "Accept")
{
var lastPrompt = inlineAssist?.Prompts.LastOrDefault();
if (lastPrompt != null && !string.IsNullOrEmpty(lastPrompt.Response))
{
editableContent = $"<p>{lastPrompt.Response}</p>";
}
await inlineAssist!.HidePopupAsync();
}
else if (args.Item.Label == "Discard")
{
await inlineAssist!.HidePopupAsync();
}
}
private async Task OnSummarizeClick()
{
await inlineAssist.ShowPopupAsync();
}
private async Task OnResponseModeChangeAsync(ChangeEventArgs args)
{
if (Enum.TryParse<ResponseDisplayMode>(args.Value?.ToString(), out var mode))
{
currentResponseMode = mode;
await InvokeAsync(StateHasChanged);
await inlineAssist.ShowPopupAsync();
}
}
}
Note: Starting from version 33.1x, when a user submits a prompt to the Inline AI Assist, the component automatically scrolls and focuses on the latest prompt and response. This behavior eliminates the need for users to manually scroll down to see the new response, ensuring they always view the most recent AI response without interruption. Prior to version 33.1x, the previous responses remained visible when new responses were added.