Guide to Blazor Component Design and Implementation for backend devs

Guide to Blazor Component Design and Implementation for backend devs

Over time, I transitioned to using the first versions of my beloved framework, XAF. As you might know, XAF generates a polished and functional UI out of the box. Using XAF made me more of a backend developer since most of the development work wasn’t visual—especially in the early versions, where the model designer was rudimentary (it’s much better now).

Eventually, I moved on to developing .NET libraries and NuGet packages, diving deep into SOLID design principles. Fun fact: I actually learned about SOLID from DevExpress TV. Yes, there was a time before YouTube when DevExpress posted videos on technical tasks!

Nowadays, I feel confident creating and publishing my own libraries as NuGet packages. However, my “old monster” was still lurking in the shadows: UI components. I finally decided it was time to conquer it, but first, I needed to choose a platform. Here were my options:

  1. Windows Forms: A robust and mature platform but limited to desktop applications.
  2. WPF: A great option with some excellent UI frameworks that I love, but it still feels a bit “Windows Forms-ish” to me.
  3. Xamarin/Maui: I’m a big fan of Xamarin Forms and Xamarin/Maui XAML, but they’re primarily focused on device-specific applications.
  4. Blazor: This was the clear winner because it allows me to create desktop applications using Electron, embed components into Windows Forms, or even integrate with MAUI.

Recently, I’ve been helping my brother with a project in Blazor. (He’s not a programmer, but I am.) This gave me an opportunity to experiment with design patterns to get the most out of my components, which started as plain HTML5 pages.

Without further ado, here are the key insights I’ve gained so far.

Building high-quality Blazor components requires attention to both the C# implementation and Razor markup patterns. This guide combines architectural best practices with practical implementation patterns to create robust, reusable components.

1. Component Architecture and Organization

Parameter Organization

Start by organizing parameters into logical groups for better maintainability:

public class CustomForm : ComponentBase
{
    // Layout Parameters
    [Parameter] public string Width { get; set; }
    [Parameter] public string Margin { get; set; }
    [Parameter] public string Padding { get; set; }
    
    // Validation Parameters
    [Parameter] public bool EnableValidation { get; set; }
    [Parameter] public string ValidationMessage { get; set; }
    
    // Event Callbacks
    [Parameter] public EventCallback<bool> OnValidationComplete { get; set; }
    [Parameter] public EventCallback<string> OnSubmit { get; set; }
}

Corresponding Razor Template

<div class="form-container" style="width: @Width; margin: @Margin; padding: @Padding">
    <form @onsubmit="HandleSubmit">
        @if (EnableValidation)
        {
            <div class="validation-message">
                @ValidationMessage
            </div>
        }
        @ChildContent
    </form>
</div>

2. Smart Default Values and Template Composition

Component Implementation

public class DataTable<T> : ComponentBase
{
    [Parameter] public int PageSize { get; set; } = 10;
    [Parameter] public bool ShowPagination { get; set; } = true;
    [Parameter] public string EmptyMessage { get; set; } = "No data available";
    [Parameter] public IEnumerable<T> Items { get; set; } = Array.Empty<T>();
    [Parameter] public RenderFragment HeaderTemplate { get; set; }
    [Parameter] public RenderFragment<T> RowTemplate { get; set; }
    [Parameter] public RenderFragment FooterTemplate { get; set; }
}

Razor Implementation

<div class="table-container">
    @if (HeaderTemplate != null)
    {
        <header class="table-header">
            @HeaderTemplate
        </header>
    }
    
    <div class="table-content">
        @if (!Items.Any())
        {
            <div class="empty-state">@EmptyMessage</div>
        }
        else
        {
            @foreach (var item in Items)
            {
                @RowTemplate(item)
            }
        }
    </div>
    
    @if (ShowPagination)
    {
        <div class="pagination">
            <!-- Pagination implementation -->
        </div>
    }
</div>

3. Accessibility and Unique IDs

Component Implementation

public class FormField : ComponentBase
{
    private string fieldId = $"field-{Guid.NewGuid():N}";
    private string labelId = $"label-{Guid.NewGuid():N}";
    private string errorId = $"error-{Guid.NewGuid():N}";
    
    [Parameter] public string Label { get; set; }
    [Parameter] public string Error { get; set; }
    [Parameter] public bool Required { get; set; }
}

Razor Implementation

<div class="form-field">
    <label id="@labelId" for="@fieldId">
        @Label
        @if (Required)
        {
            <span class="required" aria-label="required">*</span>
        }
    </label>
    
    <input id="@fieldId" 
           aria-labelledby="@labelId"
           aria-describedby="@errorId"
           aria-required="@Required" />
    
    @if (!string.IsNullOrEmpty(Error))
    {
        <div id="@errorId" class="error-message" role="alert">
            @Error
        </div>
    }
</div>

4. Virtualization and Performance

Component Implementation

public class VirtualizedList<T> : ComponentBase
{
    [Parameter] public IEnumerable<T> Items { get; set; }
    [Parameter] public RenderFragment<T> ItemTemplate { get; set; }
    [Parameter] public int ItemHeight { get; set; } = 50;
    [Parameter] public Func<ItemsProviderRequest, ValueTask<ItemsProviderResult<T>>> ItemsProvider { get; set; }
}

Razor Implementation

<div class="virtualized-container" style="height: 500px; overflow-y: auto;">
    <Virtualize Items="@Items"
                ItemSize="@ItemHeight"
                ItemsProvider="@ItemsProvider"
                Context="item">
        <ItemContent>
            <div class="list-item" style="height: @(ItemHeight)px">
                @ItemTemplate(item)
            </div>
        </ItemContent>
        <Placeholder>
            <div class="loading-placeholder" style="height: @(ItemHeight)px">
                <div class="loading-animation"></div>
            </div>
        </Placeholder>
    </Virtualize>
</div>

Best Practices Summary

1. Parameter Organization

  • Group related parameters with clear comments
  • Provide meaningful default values
  • Use parameter validation where appropriate

2. Template Composition

  • Use RenderFragment for customizable sections
  • Provide default templates when needed
  • Enable granular control over component appearance

3. Accessibility

  • Generate unique IDs for form elements
  • Include proper ARIA attributes
  • Support keyboard navigation

4. Performance

  • Implement virtualization for large datasets
  • Use loading states and placeholders
  • Optimize rendering with appropriate conditions

Conclusion

Building effective Blazor components requires attention to both the C# implementation and Razor markup. By following these patterns and practices, you can create components that are:

  • Highly reusable
  • Performant
  • Accessible
  • Easy to maintain
  • Flexible for different use cases

Remember to adapt these practices to your specific needs while maintaining clean component design principles.

Head Content Injection in .NET 8 Blazor Web Apps

Head Content Injection in .NET 8 Blazor Web Apps

My journey with Microsoft Semantic Kernel marked the beginning of a new adventure: stepping out of my comfort zone as a backend developer to create applications with user interfaces, rather than just building apps for unit and integration testing.

I naturally chose Blazor as my UI framework, and I’ll be sharing my frontend development experiences here. Sometimes it can be frustratingly difficult to accomplish seemingly simple tasks (like centering a div!), but AI assistants like GitHub Copilot have been incredibly helpful in reducing those pain points.

One of my recent challenges involved programmatically including JavaScript and CSS in Blazor applications. I prefer an automated approach rather than manually adding tags to HTML. Back in the .NET 5 era, I wrote an article about using tag helpers for this purpose, which you can find here

However, I recently discovered that my original approach no longer works. I’ve been developing several prototypes using the new DevExpress Chat component, and many of these prototypes include custom components that require JavaScript and CSS. Despite my attempts, I couldn’t get these components to work with the tag helpers, and the reason wasn’t immediately obvious. During the Thanksgiving break, I decided to investigate this issue, and I’d like to share what I found.

With the release of .NET 8, Blazor introduced a new web app template that unifies Blazor Server and WebAssembly into a single project structure. This change affects how we inject content into the document’s head section, particularly when working with Tag Helpers or components.

Understanding the Changes

In previous versions of Blazor, we typically worked with _Host.cshtml for server-side rendering, where traditional ASP.NET Core Tag Helpers could target the <head> element directly. The new .NET 8 Blazor Web App template uses App.razor as the root component and introduces the <HeadOutlet> component for managing head content.

Approach 1: Adapting Tag Helpers

If you’re migrating existing Tag Helpers or creating new ones for head content injection, you’ll need to modify them to target HeadOutlet instead of the head element:


using Microsoft.AspNetCore.Razor.TagHelpers;

namespace YourNamespace
{
    [HtmlTargetElement("HeadOutlet")]
    public class CustomScriptTagHelper : TagHelper
    {
        public override void Process(TagHelperContext context, TagHelperOutput output)
        {
            output.PostContent.AppendHtml(
                "<script src=\"_content/YourLibrary/js/script.js\"></script>"
            );
        }
    }
}
    

Remember to register your Tag Helper in _Imports.razor:

@addTagHelper *, YourLibrary

Approach 2: Using Blazor Components (Recommended)

While adapting Tag Helpers works, Blazor offers a more idiomatic approach using components and the HeadContent component. This approach aligns better with Blazor’s component-based architecture:


@namespace YourNamespace
@implements IComponentRenderMode

<HeadContent>
    <script src="_content/YourLibrary/js/script.js"></script>
</HeadContent>
    

To use this component in your App.razor:


<head>
    <!-- Other head elements -->
    <HeadOutlet @rendermode="RenderModeForPage" />
    <YourScriptComponent @rendermode="RenderModeForPage" />
</head>
    

Benefits of the Component Approach

  • Better Integration: Components work seamlessly with Blazor’s rendering model
  • Render Mode Support: Easy to control rendering based on the current render mode (Interactive Server, WebAssembly, or Auto)
  • Dynamic Content: Can leverage Blazor’s full component lifecycle and state management
  • Type Safety: Provides compile-time checking and better tooling support

Best Practices

  • Prefer the component-based approach for new development
  • Use Tag Helpers only when migrating existing code or when you need specific ASP.NET Core pipeline integration
  • Always specify the @rendermode attribute to ensure proper rendering in different scenarios
  • Place custom head content components after HeadOutlet to ensure proper ordering

Conclusion

While both approaches work in .NET 8 Blazor Web Apps, the component-based approach using HeadContent provides a more natural fit with Blazor’s architecture and offers better maintainability and flexibility. When building new applications, consider using components unless you have a specific need for Tag Helper functionality.

Using DevExpress Chat Component and Semantic Kernel ResponseFormat to show a product carousel

Using DevExpress Chat Component and Semantic Kernel ResponseFormat to show a product carousel

Today, when I woke up, it was sunny but really cold, and the weather forecast said that snow was expected.

So, I decided to order ramen and do a “Saturday at home” type of project. My tools of choice for this experiment are:

1) DevExpress Chat Component for Blazor

I’m thrilled they have this component. I once wrote my own chat component, and it’s a challenging task, especially given the variety of use cases.

2) Semantic Kernel

I’ve been experimenting with Semantic Kernel for a while now, and let me tell you—it’s a fantastic tool if you’re in the .NET ecosystem. It’s so cool to have native C# code to interact with AI services in a flexible way, making your code mostly agnostic to the AI provider—like a WCF for AIs.

Goal of the Experiment

The goal for today’s experiment is to render a list of products as a carousel within a chat conversation.

Configuration

To accomplish this, I’ll use prompt execution settings in Semantic Kernel to ensure that the response from the LLM is always in JSON format as a string.

var Settings = new OpenAIPromptExecutionSettings 
{ 
    MaxTokens = 500, 
    Temperature = 0.5, 
    ResponseFormat = "json_object" 
};

The key part here is the response format. The chat completion can respond in two ways:

  • Text: A simple text answer.
  • JSON Object: This format always returns a JSON object, with the structure provided as part of the prompt.

With this approach, we can deserialize the LLM’s response to an object that helps conditionally render the message content within the DevExpress Chat Component.

Structure

Here’s the structure I’m using:

public class MessageData
{
    public string Message { get; set; }
    public List Options { get; set; }
    public string MessageTemplateName { get; set; }
}

public class OptionSet
{
    public string Name { get; set; }
    public string Description { get; set; }
    public List Options { get; set; }
}

public class Option
{
    public string Image { get; set; }
    public string Url { get; set; }
    public string Description { get; set; }
};
  • MessageData: This structure will always be returned by our LLM.
  • Option: A list of options for a message, which also serves as data for possible responses.
  • OptionSet: A list of possible responses to feed into the prompt execution settings.

Prompt Execution Settings

One more step on the Semantic Kernel side is configuring the prompt execution settings:

var Settings = new OpenAIPromptExecutionSettings 
{ 
    MaxTokens = 500, 
    Temperature = 0.5, 
    ResponseFormat = "json_object" 
};

Settings.ChatSystemPrompt = $"You need to answer using this JSON format with this structure {Structure} " +
                            $"Before giving an answer, check if it exists within this list of option sets {OptionSets}. " +
                            $"If your answer does not include options, the message template value should be 'Message'; otherwise, it should be 'Options'.";

In the prompt, we specify the structure {Structure} we want as a response, provide a list of possible options for the message in the {OptionSets} variable, and add a final line to guide the LLM on which template type to use.

Example Requests and Responses

For example, when executing the following request:

  • Prompt: “Show me a list of Halloween costumes for cats.”

We’ll get this response from the LLM:

{
    "Message": "Please select one of the Halloween costumes for cats",
    "Options": [
        {"Image": "./images/catblack.png", "Url": "https://cat.com/black", "Description": "Black cat costume"},
        {"Image": "./images/catwhite.png", "Url": "https://cat.com/white", "Description": "White cat costume"},
        {"Image": "./images/catorange.png", "Url": "https://cat.com/orange", "Description": "Orange cat costume"}
    ],
    "MessageTemplateName": "Options"
}

With this JSON structure, we can conditionally render messages in the chat component as follows:

<DxAIChat CssClass="my-chat" MessageSent="MessageSent">
    <MessageTemplate>
        <div>
            @{
                if (@context.Typing)
                {
                    <span>Loading...</span>
                }
                else
                {
                    MessageData md = null;
                    try
                    {
                        md = JsonSerializer.Deserialize<MessageData>(context.Content);
                    }
                    catch
                    {
                        md = null;
                    }
                    if (md == null)
                    {
                        <div class="my-chat-content">
                            @context.Content
                        </div>
                    }
                    else
                    {
                        if (md.MessageTemplateName == "Options")
                        {
                            <div class="centered-carousel">
                                <Carousel class="carousel-container" Width="280" IsFade="true">
                                    @foreach (var option in md.Options)
                                    {
                                        <CarouselItem>
                                            <ChildContent>
                                                <div>
                                                    <img src="@option.Image" alt="demo-image" />
                                                    <Button Color="Color.Primary" class="carousel-button">@option.Description</Button>
                                                </div>
                                            </ChildContent>
                                        </CarouselItem>
                                    }
                                </Carousel>
                            </div>
                        }
                        else if (md.MessageTemplateName == "Message")
                        {
                            <div class="my-chat-content">
                                @md.Message
                            </div>
                        }
                    }
                }
            }
        </div>
    </MessageTemplate>
</DxAIChat>

End Solution Example

Here’s an example of the final solution:

You can find the full source code here: https://github.com/egarim/devexpress-ai-chat-samples and a short video here https://youtu.be/dxMnOWbe3KA

 

Async Code Execution in XAF Actions

Async Code Execution in XAF Actions

Lately, I’ve been working extensively on interacting with LLMs using the Semantic Kernel framework. My experiments usually start as NUnit test projects, where I prototype my ideas.

Once an experiment is successful, I move it to XAF. Recently, I faced challenges with executing asynchronous code and updating the XAF UI. This process is tricky because some solutions might appear to work but fail under certain conditions.

Goals

Here’s what I aim to achieve:

  1. Execute asynchronous code within the execute handler of an action.
  2. Notify the UI and access the current view, object, and object space.
  3. Run multiple operations on a background thread.

For more background, check out these links on async executions within XAF actions:

WebForms

Blazor

Complete source code for this test can be found on GitHub.

Common Cases

1. Blocking the UI Thread (this will not work)

If you don’t make your action async, attempting to get the awaiter will block the UI thread, freezing your application.


ActionBlockUIThread = new SimpleAction(this, nameof(ActionBlockUIThread), "View");
ActionBlockUIThread.Execute += ActionBlockUIThread_Execute;

protected virtual void ActionBlockUIThread_Execute(object sender, SimpleActionExecuteEventArgs e) {
    var Tasks = GetTaskList();
    StringBuilder Results = new StringBuilder();
    foreach (var item in Tasks) {
        Results.AppendLine(item.Invoke().GetAwaiter().GetResult().ToString());
    }
    MessageOptions options = new MessageOptions { Duration = 2000, Message = Results.ToString(), Type = InformationType.Success };
    Application.ShowViewStrategy.ShowMessage(options);
}

2. Using Async Modifier (somehow works)

Marking your handler as async prevents blocking but keeps the UI responsive, which can allow the user to modify or navigate away from the current view, causing exceptions.


protected virtual async void ActionWithAsyncModifier_Execute(object sender, SimpleActionExecuteEventArgs e) {
    var Tasks = GetTaskList();
    StringBuilder Results = new StringBuilder();
    foreach (var item in Tasks) {
        var CurrentResult = await item.Invoke();
        Results.AppendLine(CurrentResult.ToString());
    }
    MessageOptions options = new MessageOptions { Duration = 2000, Message = Results.ToString(), Type = InformationType.Success };
    Application.ShowViewStrategy.ShowMessage(options);
}

A slightly modified Blazor version of this code also illustrates similar issues.

Executing Object Space Operations Inside Async Action, things that can happen

This approach still leaves the UI responsive, risking disposal of object space if the user navigates away, if that happens you will end up with an exception


protected virtual async void ActionWithAsyncModifierAndOsOperations_Execute(object sender, SimpleActionExecuteEventArgs e) {
    var Instance = GetInstance();
    var Tasks = GetTaskList();
    StringBuilder Results = new StringBuilder();
    foreach (var item in Tasks) {
        var CurrentResult = await item.Invoke();
        Results.AppendLine(CurrentResult.ToString());
    }
    Instance.Result = Results.ToString();
    ViewCommit();
    MessageOptions options = new MessageOptions { Duration = 3000, Message = Instance.Result, Type = InformationType.Success };
    Application.ShowViewStrategy.ShowMessage(options);
}

Proposed Solution

My solution utilizes a background worker to handle async operations while locking the UI thread with a loading indicator. This allows us to react to progress on the UI thread.

Async Background Worker Example

Here’s how the AsyncBackgroundWorker is set up and used:


protected virtual void AsyncActionWithAsyncBackgroundWorker_Execute(object sender, SimpleActionExecuteEventArgs e) {
    var tasks = GetTaskList();
    var worker = new AsyncBackgroundWorker

Handling Background Worker Events


protected virtual void ProcessingDone(Dictionary<int, object> results) {
    // Interact with UI and object space
}

protected virtual void OnReportProgress(int progress, string status, object result) {
    MessageOptions options = new MessageOptions { Duration = 2000, Message = status, Type = InformationType.Success };
    Application.ShowViewStrategy.ShowMessage(options);
}

Blazor Implementation

The Blazor version manages UI locking by showing a loading indicator and reporting progress through the UI thread:

source here: https://github.com/egarim/XafAsyncActions/blob/master/XafAsyncActions.Blazor.Server/Controllers/MyViewControllerBlazor.cs


protected async override void AsyncActionWithAsyncBackgroundWorker_Execute(object sender, SimpleActionExecuteEventArgs e) {
    loading.Hold("Loading");
    base.AsyncActionWithAsyncBackgroundWorker_Execute(sender, e);
}

protected async override void ProcessingDone(Dictionary<int, object> results) {
    base.ProcessingDone(results);
    loading.Release("Loading");
}

When you run this implementation, it will look like this

As you can see the task are being run on the background worker and every time a task is finish is reported back to the U.I thread where we can execute a notification (this is actually optional)

When all the tasks are finished, I hide the loading indicator, and the user can interact with the view again

I hope this article clarifies async execution in XAF. I will update the repository as new scenarios arise.

Querying Semantic Memory with XAF and the DevExpress Chat Component

Querying Semantic Memory with XAF and the DevExpress Chat Component

A few weeks ago, I received the exciting news that DevExpress had released a new chat component (you can read more about it here). This was a big deal for me because I had been experimenting with the Semantic Kernel for almost a year. Most of my experiments fell into three categories:

  1. NUnit projects with no UI (useful when you need to prove a concept).
  2. XAF ASP.NET projects using a large textbox (String with unlimited size in XAF) to emulate a chat control.
  3. XAF applications using a custom chat component that I developed—which, honestly, didn’t look great because I’m more of a backend developer than a UI specialist. Still, the component did the job.

Once I got my hands on the new Chat component, the first thing I did was write a property editor to easily integrate it into XAF. You can read more about property editors in XAF here.

With the Chat component property editor in place, I had the necessary tool to accelerate my experiments with the Semantic Kernel (learn more about the Semantic Kernel here).

The Current Experiment

A few weeks ago, I wrote an implementation of the Semantic Kernel Memory Store using DevExpress’s XPO as the data storage solution. You can read about that implementation here. The next step was to integrate this Semantic Memory Store into XAF, and that’s now done. Details about that process can be found here.

What We Have So Far

  1. A Chat component property editor for XAF.
  2. A Semantic Kernel Memory Store for XPO that’s compatible with XAF.

With these two pieces, we can create an interesting prototype. The goals for this experiment are:

  1. Saving “memories” into a domain object (via XPO).
  2. Querying these memories through the Chat component property editor, using Semantic Kernel chat completions (compatible with all OpenAI APIs).

Step 1: Memory Collection Object

The first thing we need is an object that represents a collection of memories. Here’s the implementation:

[DefaultClassOptions]
public class MemoryChat : BaseObject
{
    public MemoryChat(Session session) : base(session) {}

    public override void AfterConstruction()
    {
        base.AfterConstruction();
        this.MinimumRelevanceScore = 0.20;
    }

    double minimumRelevanceScore;
    string name;

    [Size(SizeAttribute.DefaultStringMappingFieldSize)]
    public string Name
    {
        get => name;
        set => SetPropertyValue(nameof(Name), ref name, value);
    }

    public double MinimumRelevanceScore
    {
        get => minimumRelevanceScore;
        set => SetPropertyValue(nameof(MinimumRelevanceScore), ref minimumRelevanceScore, value);
    }

    [Association("MemoryChat-MemoryEntries")]
    public XPCollection<MemoryEntry> MemoryEntries
    {
        get => GetCollection<MemoryEntry>(nameof(MemoryEntries));
    }
}

This is a simple object. The two main properties are the MinimumRelevanceScore, which is used for similarity searches with embeddings, and the collection of MemoryEntries, where different memories are stored.

Step 2: Adding Memories

The next task is to easily append memories to that collection. I decided to use a non-persistent object displayed in a popup view with a large text area. When the user confirms the action in the dialog, the text gets vectorized and stored as a memory in the collection. You can see the implementation of the view controller here.

Let me highlight the important parts.

When we create the view for the popup window:

private void AppendMemory_CustomizePopupWindowParams(object sender, CustomizePopupWindowParamsEventArgs e)
{
    var os = this.Application.CreateObjectSpace(typeof(TextMemory));
    var textMemory = os.CreateObject<TextMemory>();
    e.View = this.Application.CreateDetailView(os, textMemory);
}

The goal is to show a large textbox where the user can type any text. When they confirm, the text is vectorized and stored as a memory.

Next, storing the memory:

private async void AppendMemory_Execute(object sender, PopupWindowShowActionExecuteEventArgs e)
{
    var textMemory = e.PopupWindowViewSelectedObjects[0] as TextMemory;
    var currentMemoryChat = e.SelectedObjects[0] as MemoryChat;

    var store = XpoMemoryStore.ConnectAsync(xafEntryManager).GetAwaiter().GetResult();
    var semanticTextMemory = GetSemanticTextMemory(store);
    await semanticTextMemory.SaveInformationAsync(currentMemoryChat.Name, id: Guid.NewGuid().ToString(), text: textMemory.Content);
}

Here, the GetSemanticTextMemory method plays a key role:

private static SemanticTextMemory GetSemanticTextMemory(XpoMemoryStore store)
{
    var embeddingModelId = "text-embedding-3-small";
    var getKey = () => Environment.GetEnvironmentVariable("OpenAiTestKey", EnvironmentVariableTarget.Machine);

    var kernel = Kernel.CreateBuilder()
        .AddOpenAIChatCompletion(ChatModelId, getKey.Invoke())
        .AddOpenAITextEmbeddingGeneration(embeddingModelId, getKey.Invoke())
        .Build();

    var embeddingGenerator = new OpenAITextEmbeddingGenerationService(embeddingModelId, getKey.Invoke());
    return new SemanticTextMemory(store, embeddingGenerator);
}

This method sets up an embedding generator used to create semantic memories.

Step 3: Querying Memories

To query the stored memories, I created a non-persistent type that interacts with the chat component:

public interface IMemoryData
{
    IChatCompletionService ChatCompletionService { get; set; }
    SemanticTextMemory SemanticTextMemory { get; set; }
    string CollectionName { get; set; }
    string Prompt { get; set; }
    double MinimumRelevanceScore { get; set; }
}

This interface provides the necessary services to interact with the chat component, including ChatCompletionService and SemanticTextMemory.

Step 4: Handling Messages

Lastly, we handle message-sent callbacks, as explained in this article:

async Task MessageSent(MessageSentEventArgs args)
{
    ChatHistory.AddUserMessage(args.Content);

    var answers = Value.SemanticTextMemory.SearchAsync(
        collection: Value.CollectionName,
        query: args.Content,
        limit: 1,
        minRelevanceScore: Value.MinimumRelevanceScore,
        withEmbeddings: true
    );

    string answerValue = "No answer";
    await foreach (var answer in answers)
    {
        answerValue = answer.Metadata.Text;
    }

    string messageContent = answerValue == "No answer"
        ? "There are no memories containing the requested information."
        : await Value.ChatCompletionService.GetChatMessageContentAsync($"You are an assistant queried for information. Use this data: {answerValue} to answer the question: {args.Content}.");

    ChatHistory.AddAssistantMessage(messageContent);
    args.SendMessage(new Message(MessageRole.Assistant, messageContent));
}

Here, we intercept the message, query the SemanticTextMemory, and use the results to generate an answer with the chat completion service.

This was a long post, but I hope it’s useful for you all. Until next time—XAF OUT!

You can find the full implementation on this repo