Review Changes addressed

Author: ManjuDhanasekaran2001

MAUI/Autocomplete/AI-Powered-Smart-Searching.md

@@ -10,10 +10,148 @@ documentation: ug
 # Implementing AI-Powered Smart Search in .NET MAUI Autocomplete
 
 This document will walk you through the implementation of an advanced search functionality in the Syncfusion [.NET MAUI Autocomplete](https://help.syncfusion.com/cr/maui/Syncfusion.Maui.Inputs.SfAutocomplete.html) control. The example leverages the power of Azure OpenAI for an intelligent, AI-driven search experience.
+
+## Integrating Azure OpenAI with your .NET MAUI App
+
+First, ensure you have access to [Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/overview) and have created a deployment in the Azure portal.
+
+If you don’t have access, please refer to the [create and deploy Azure OpenAI service](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/create-resource?pivots=web-portal) guide to set up a new account.
+
+Note down the deployment name, endpoint URL, and API key.
+
+we’ll use the [Azure.AI.OpenAI](https://www.nuget.org/packages/Azure.AI.OpenAI/1.0.0-beta.12) NuGet package from the [NuGet Gallery](https://www.nuget.org/). So, before getting started, install the Azure.AI.OpenAI NuGet package in your .NET MAUI app.
+
+In your base service class (AzureBaseService), initialize the OpenAIClient. Replace the Endpoint, DeploymentName, Key with actual values from your Azure OpenAI resource.
+
+This creates a chat client using your endpoint, API key, and deployment name. It’s stored in the Client property for use in other methods.
+
+ComboBoxAzureAIService use this Client to send prompts and receive completions.
+
+In the `GetCompletion` method, we will construct the prompt and send it to the Azure OpenAI Service. The ChatHistory helps maintain context but is cleared for each new prompt in this implementation to ensure each search is independent.
+
+{% tabs %}
+{% highlight c# %}
+
+// AzureBaseService.cs
+    public abstract class AzureBaseService
+    {        
+        internal const string Endpoint = "YOUR_END_POINT_NAME";
+
+        internal const string DeploymentName = "DEPLOYMENT_NAME";
+
+        internal const string Key = "API_KEY";
+
+        public AzureBaseService()
+        {
+            ValidateCredential();
+        }
+                        
+        private async void ValidateCredential()
+        {
+            this.GetAzureOpenAIKernal();
+
+            if (isAlreadyValidated)
+            {
+                return;
+            }
+
+            try
+            {
+                if (Client != null)
+                {
+                    await Client!.CompleteAsync("Hello, Test Check");
+                    ChatHistory = string.Empty;
+                    IsCredentialValid = true;
+                    isAlreadyValidated = true;
+                }
+                else
+                {
+                    ShowAlertAsync();
+                }
+            }
+            catch (Exception)
+            {
+                return;
+            }
+        }
+
+        /// <summary>
+        /// To get the Azure open ai kernal method
+        /// </summary>
+        private void GetAzureOpenAIKernal()
+        {
+            try
+            {
+                var client = new AzureOpenAIClient(new Uri(Endpoint), new AzureKeyCredential(Key)).AsChatClient(modelId: DeploymentName);
+                this.Client = client;
+            }
+            catch (Exception)
+            {
+            }
+        }
+        
+    }
+
+{% endhighlight %}
+
+{% endtabs %}
+
+{% tabs %}
+{% highlight c# %}
+
+//AzureAIService.cs
+
+public class AzureAIService : AzureBaseService
+    {
+        /// <summary>
+        /// Gets a completion response from the AzureAI service based on the provided prompt.
+        /// </summary>
+        /// <param name="prompt"></param>
+        /// <param name="cancellationToken"></param>
+        /// <returns></returns>
+        public async Task<string> GetCompletion(string prompt, CancellationToken cancellationToken)
+        {
+            ChatHistory = string.Empty;
+            if(ChatHistory != null)
+            {
+                ChatHistory = ChatHistory + "You are a filtering assistant.";
+                ChatHistory = ChatHistory + prompt;
+                try
+                {
+                    if (Client != null)
+                    {
+                        cancellationToken.ThrowIfCancellationRequested();
+                        var chatresponse = await Client.CompleteAsync(prompt);
+                        return chatresponse.ToString();
+                    }
+                }
+                catch (RequestFailedException ex)
+                {
+                    // Log the error message and rethrow the exception or handle it appropriately
+                    Debug.WriteLine($"Request failed: {ex.Message}");
+                    throw;
+                }
+                catch (Exception ex)
+                {
+                    // Handle other potential exceptions
+                    Debug.WriteLine($"An error occurred: {ex.Message}");
+                    throw;
+                }
+            }
+            return "";
+        }
+    }
+
+{% endhighlight %}
+
+{% endtabs %}
+
 ## Implementing custom filtering in .NET MAUI Autocomplete
 
 The [.NET MAUI Autocomplete](https://help.syncfusion.com/cr/maui/Syncfusion.Maui.Inputs.SfAutocomplete.html) control allows you to apply custom filter logic to suggest items based on your specific filter criteria by utilizing the `FilterBehavior` property, which is the entry point for our smart search logic.
 
+**Step 1:** Let’s create a new business model to search country names. Refer to the following code example.
+
 {% tabs %}
 {% highlight c# %}
 
@@ -63,9 +201,9 @@ internal class CountryViewModel : INotifyPropertyChanged
 
 {% endtabs %}
 
-### Connecting the Custom Filter to Azure OpenAI
+**Step 2:** Connecting the Custom Filter to Azure OpenAI
 
- Implement the `GetMatchingItemsAsync` method from the interface. This method is the heart of the custom filter. It is invoked every time the text in the [Autocomplete](https://help.syncfusion.com/cr/maui/Syncfusion.Maui.Inputs.SfAutocomplete.html) control changes. 
+Implement the `GetMatchingItemsAsync` method from the interface. This method is the heart of the custom filter. It is invoked every time the text in the [Autocomplete](https://help.syncfusion.com/cr/maui/Syncfusion.Maui.Inputs.SfAutocomplete.html) control changes. 
 
 The logic within [Autocomplete](https://help.syncfusion.com/cr/maui/Syncfusion.Maui.Inputs.SfAutocomplete.html) intelligently decides whether to perform an online AI search based on the availability of Azure credentials.
 
@@ -198,10 +336,12 @@ public class CustomFilter : IAutocompleteFilterBehavior
 
 {% endtabs %}
 
+**Step:3** Applying Custom Filtering to AutoComplte
+
 Applying custom filtering to the [Autocomplete](https://help.syncfusion.com/cr/maui/Syncfusion.Maui.Inputs.SfAutocomplete.html) control by using the `FilterBehavior` property.
 
 {% tabs %}
-{% highlight c# %}
+{% highlight xaml %}
 
     <editors:SfAutocomplete x:Name="autoComplete" 
                               DropDownPlacement="Bottom"
@@ -219,64 +359,6 @@ Applying custom filtering to the [Autocomplete](https://help.syncfusion.com/cr/m
 
 {% endtabs %}
 
-## Online Search: Integrating with Azure OpenAI
-
-When Azure credentials are available, the application performs a real-time, intelligent search using AI.
-
-### The Azure AI Service
-
-In the `GetCompletion` method, we will construct the prompt and send it to the Azure OpenAI Service. The ChatHistory helps maintain context but is cleared for each new prompt in this implementation to ensure each search is independent.
-
-{% tabs %}
-{% highlight c# %}
-
-//AzureAIService.cs
-
-public class AzureAIService : AzureBaseService
-    {
-        /// <summary>
-        /// Gets a completion response from the AzureAI service based on the provided prompt.
-        /// </summary>
-        /// <param name="prompt"></param>
-        /// <param name="cancellationToken"></param>
-        /// <returns></returns>
-        public async Task<string> GetCompletion(string prompt, CancellationToken cancellationToken)
-        {
-            ChatHistory = string.Empty;
-            if(ChatHistory != null)
-            {
-                ChatHistory = ChatHistory + "You are a filtering assistant.";
-                ChatHistory = ChatHistory + prompt;
-                try
-                {
-                    if (Client != null)
-                    {
-                        cancellationToken.ThrowIfCancellationRequested();
-                        var chatresponse = await Client.CompleteAsync(prompt);
-                        return chatresponse.ToString();
-                    }
-                }
-                catch (RequestFailedException ex)
-                {
-                    // Log the error message and rethrow the exception or handle it appropriately
-                    Debug.WriteLine($"Request failed: {ex.Message}");
-                    throw;
-                }
-                catch (Exception ex)
-                {
-                    // Handle other potential exceptions
-                    Debug.WriteLine($"An error occurred: {ex.Message}");
-                    throw;
-                }
-            }
-            return "";
-        }
-    }
-
-{% endhighlight %}
-
-{% endtabs %}
-
 The following image demonstrates the output of the above AI-based search using a custom filtering sample.
 
 ![.NET MAUI AutoComplete With AI Smart Search.](Images/AISmartSearch/ai_smart_search.png)