Update AI configuration doc

Author: Maryanne Gichohi

articles/azure-app-configuration/concept-ai-configuration.md

@@ -46,6 +46,8 @@ Chat completion is an AI capability that produces human-like dialogue responses
 | Anthropic      | Claude 3.7 Sonnet     |
 | Google         | Gemini 2.5 Pro        |
 | DeepSeek       | DeepSeek-R1           |
+| xAI            | Grok-3                |
+| xAI            | Grok-3 Mini           |
 
 Azure OpenAI Service supports a diverse set of models from OpenAI. For more information, see [Azure OpenAI Service models](/azure/ai-services/openai/concepts/models). To learn more about models from Anthropic, refer to the [Claude models documentation](https://docs.anthropic.com/docs/about-claude/models/overview).  
 For more details about models provided by Google, see the [Gemini models documentation](https://ai.google.dev/gemini-api/docs/models).

articles/azure-app-configuration/howto-chat-completion-config.md

@@ -26,12 +26,9 @@ In this section, you create a chat completion configuration in Azure portal usin
  1. In Azure portal, navigate to your App configuration store. From the **Operations** menu, select **Configuration explorer** > **Create**, and then select **AI configuration**.
 
  1. Specify the following values:
-    - **Key**: Type **ChatApp:Model**.
+    - **Key**: Type **ChatApp:ChatCompletion**.
     - **Label**: Leave this value blank.
     - **Model**: Select **gpt-4o**.
-    - **Message**: Add a new message.
-        - **Role**: Select **user**
-        - **Content**: Type "What is the capital of France?"
 
     > [!div class="mx-imgBorder"]
     > ![Screenshot shows the create new AI configuration form.](./media/create-ai-chat-completion-config.png)
@@ -40,7 +37,7 @@ In this section, you create a chat completion configuration in Azure portal usin
 
 ## Add model connection configuration
 
-You successfully added your chat completion configuration named **ChatApp:Model** in the previous section. In this section, you add the connection details for your model, including the endpoint and deployment name. If required by your authentication method, you can also specify an API key using a Key Vault reference.
+You successfully added your chat completion configuration named **ChatApp:ChatCompletion** in the previous section. In this section, you add the connection details for your model, including the endpoint and deployment name. If required by your authentication method, you can also specify an API key using a Key Vault reference.
 
 > [!NOTE]
 > This tutorial demonstrates how to use chat completion configuration with an Azure OpenAI model. However, the chat completion configuration demonstrated in the tutorial can be applied to any AI model you choose to work with in your application.

articles/azure-app-configuration/media/create-ai-chat-completion-config.png

@@ -112,10 +112,10 @@ In this guide, you build an AI chat application and iterate on the prompt using
     });
     ```
 
-1. Define the `ModelConfiguration` class in _Program.cs_ file:
+1. Define the `ChatCompletionConfiguration` class in _Program.cs_ file:
 
     ```csharp
-    internal class ModelConfiguration
+    internal class ChatCompletionConfiguration
     {
         [ConfigurationKeyName("model")]
         public string? Model { get; set; }
@@ -146,10 +146,10 @@ In this guide, you build an AI chat application and iterate on the prompt using
 1. Update the _Program.cs_ file to add a helper method `GetChatMessages` to process chat messages:
 
     ```csharp
-    // Helper method to convert configuration messages to chat API format
-    static IEnumerable<ChatMessage> GetChatMessages(ModelConfiguration modelConfiguration)
+    // Helper method to convert configuration messages to ChatMessage objects
+    static IEnumerable<ChatMessage> GetChatMessages(ChatCompletionConfiguration chatCompletionConfiguration)
     {
-        return modelConfiguration.Messages.Select<Message, ChatMessage>(message => message.Role switch
+        return chatCompletionConfiguration.Messages.Select<Message, ChatMessage>(message => message.Role switch
         {
             "system" => ChatMessage.CreateSystemMessage(message.Content),
             "user" => ChatMessage.CreateUserMessage(message.Content),
@@ -164,29 +164,44 @@ In this guide, you build an AI chat application and iterate on the prompt using
     ```csharp
     while (true)
     {
+        // Get user input
+        Console.Write("You: ");
+        string? userInput = Console.ReadLine();
+
+        // Exit if user input is empty
+        if (string.IsNullOrEmpty(userInput))
+        {
+            Console.WriteLine("Exiting chat. Goodbye!");
+            break;
+        }
+
         // Refresh the configuration from Azure App Configuration
         await refresher.RefreshAsync();
 
         // Configure chat completion with AI configuration
-        var modelConfiguration = configuration.GetSection("ChatApp:Model").Get<ModelConfiguration>();
+        var chatCompletionConfiguration = configuration.GetSection("ChatApp:ChatCompletion").Get<ChatCompletionConfiguration>();
+
         var requestOptions = new ChatCompletionOptions()
         {
-            MaxOutputTokenCount = modelConfiguration.MaxTokens,
-            Temperature = modelConfiguration.Temperature,
-            TopP = modelConfiguration.TopP
+            MaxOutputTokenCount = chatCompletionConfiguration.MaxTokens,
+            Temperature = chatCompletionConfiguration.Temperature,
+            TopP = chatCompletionConfiguration.TopP
         };
 
-        foreach (var message in modelConfiguration.Messages)
-        {
-            Console.WriteLine($"{message.Role}: {message.Content}");
-        }
+        chatConversation.Add(ChatMessage.CreateUserMessage(userInput));
 
-        // Get chat response from AI
-        var response = await chatClient.CompleteChatAsync(GetChatMessages(modelConfiguration), requestOptions);
-        Console.WriteLine($"AI response: {response.Value.Content[0].Text}");
+        // Get latest system message from AI configuration
+        var chatMessages = new List<ChatMessage>(GetChatMessages(chatCompletionConfiguration));
+        chatMessages.AddRange(chatConversation);
 
-        Console.WriteLine("Press Enter to continue...");
-        Console.ReadLine();
+        // Get AI response and add it to chat conversation
+        var response = await chatClient.CompleteChatAsync(chatMessages, requestOptions);
+        string aiResponse = response.Value.Content[0].Text;
+        
+        Console.WriteLine($"AI: {aiResponse}");
+        chatConversation.Add(ChatMessage.CreateAssistantMessage(aiResponse));
+
+        Console.WriteLine();
     }
     ```
 
@@ -231,37 +246,55 @@ In this guide, you build an AI chat application and iterate on the prompt using
     AzureOpenAIClient azureClient = new(openaiEndpoint, credential);
     ChatClient chatClient = azureClient.GetChatClient(deploymentName);
 
+    // Initialize chat conversation
+    var chatConversation = new List<ChatMessage>();
+    Console.WriteLine("Chat started! What's on your mind?");
+
     while (true)
     {
+        // Get user input
+        Console.Write("You: ");
+        string? userInput = Console.ReadLine();
+
+        // Exit if user input is empty
+        if (string.IsNullOrEmpty(userInput))
+        {
+            Console.WriteLine("Exiting chat. Goodbye!");
+            break;
+        }
+
         // Refresh the configuration from Azure App Configuration
         await refresher.RefreshAsync();
 
         // Configure chat completion with AI configuration
-        var modelConfiguration = configuration.GetSection("ChatApp:Model").Get<ModelConfiguration>();
+        var chatCompletionConfiguration = configuration.GetSection("ChatApp:ChatCompletion").Get<ChatCompletionConfiguration>();
         var requestOptions = new ChatCompletionOptions()
         {
-            MaxOutputTokenCount = modelConfiguration.MaxTokens,
-            Temperature = modelConfiguration.Temperature,
-            TopP = modelConfiguration.TopP
+            MaxOutputTokenCount = chatCompletionConfiguration.MaxTokens,
+            Temperature = chatCompletionConfiguration.Temperature,
+            TopP = chatCompletionConfiguration.TopP
         };
 
-        foreach (var message in modelConfiguration.Messages)
-        {
-            Console.WriteLine($"{message.Role}: {message.Content}");
-        }
+        chatConversation.Add(ChatMessage.CreateUserMessage(userInput));
 
-        // Get chat response from AI
-        var response = await chatClient.CompleteChatAsync(GetChatMessages(modelConfiguration), requestOptions);
-        Console.WriteLine($"AI response: {response.Value.Content[0].Text}");
+        // Get latest system message from AI configuration
+        var chatMessages = new List<ChatMessage>(GetChatMessages(chatCompletionConfiguration));
+        chatMessages.AddRange(chatConversation);
 
-        Console.WriteLine("Press Enter to continue...");
-        Console.ReadLine();
-        
+        // Get AI response and add it to chat conversation
+        var response = await chatClient.CompleteChatAsync(chatMessages, requestOptions);
+        string aiResponse = response.Value.Content[0].Text;
+
+        Console.WriteLine($"AI: {aiResponse}");
+        chatConversation.Add(ChatMessage.CreateAssistantMessage(aiResponse));
+
+        Console.WriteLine();
     }
 
-    static IEnumerable<ChatMessage> GetChatMessages(ModelConfiguration modelConfiguration)
+    // Helper method to convert configuration messages to ChatMessage objects
+    static IEnumerable<ChatMessage> GetChatMessages(ChatCompletionConfiguration chatCompletionConfiguration)
     {
-        return modelConfiguration.Messages.Select<Message, ChatMessage>(message => message.Role switch
+        return chatCompletionConfiguration.Messages.Select<Message, ChatMessage>(message => message.Role switch
         {
             "system" => ChatMessage.CreateSystemMessage(message.Content),
             "user" => ChatMessage.CreateUserMessage(message.Content),
@@ -270,7 +303,7 @@ In this guide, you build an AI chat application and iterate on the prompt using
         });
     }
 
-    internal class ModelConfiguration
+    internal class ChatCompletionConfiguration
     {
         [ConfigurationKeyName("model")]
         public string? Model { get; set; }
@@ -326,26 +359,17 @@ In this guide, you build an AI chat application and iterate on the prompt using
     You should see the following output:
 
     ```Output
-    system: You are a helpful assistant.
-    user: What is the capital of France ?
-    AI response: The capital of France is **Paris**.
-    Press Enter to continue...
-
+    Chat started! What's on your mind?
     ```
 
-1. In Azure portal, select the App Configuration store instance that you created. From the **Operations** menu, select **Configuration explorer** and select the **ChatApp:Model** key. Update the value of the Messages property:
+1. In Azure portal, select the App Configuration store instance that you created. From the **Operations** menu, select **Configuration explorer** and select the **ChatApp:ChatCompletion** key. Update the value of the Messages property:
     - Role: **system**
-    - Content: "You are a cheerful tour guide".
+    - Content: "You are a pirate and your name is Eddy."
 
-1. Wait a few moments for the refresh interval to elapse, and then press the Enter key to see the updated AI response in the output.
+1. Type your message when prompted with "You:". Be sure to wait a few moments for the refresh interval to elapse, and then press the Enter key to see the updated AI response in the output
 
     ```Output
-    system: You are a cheerful tour guide
-    user: What is the capital of France ?
-    AI response: Oh là là! The capital of France is the magnificent **Paris**!
-    Known as the "City of Light" (*La Ville Lumière*), it's famous for its romantic ambiance,
-    iconic landmarks like the Eiffel Tower, the Louvre Museum, and Notre-Dame Cathedral,
-    as well as its delicious pastries and charming cafés.
-    Have you ever been, or is it on your travel bucket list? 😊✨
-    Press Enter to continue...
+    Chat started! What's on your mind?
+    You: Hello, what is your name ?
+    AI: Ahoy, matey! Me name be Captain Eddy, the most fearsome pirate to ever sail the seven seas! What be yer name, landlubber?
     ```