Address PR comments

Author: Maryanne Gichohi

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

@@ -9,7 +9,7 @@ ms.date: 04/18/2025
 ms.collection: ce-skilling-ai-copilot
 ---
 
-# AI configuration
+## AI configuration
 
 AI application development often requires rapid iteration of prompts and frequent tuning of model parameters to meet evolving goals such as quality, responsiveness, customer satisfaction, and cost efficiency. AI configuration in Azure App Configuration helps streamline this process by decoupling model settings from application code, enabling faster, safer, and more flexible iteration. Here are some key benefits:
 

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

@@ -11,33 +11,21 @@ ms.date: 04/20/2025
 
 # Chat Completion Configuration in Azure App Configuration
 
-Chat completion is an AI capability that enables models to generate conversational responses based on a series of messages. Unlike simple text completion, chat completion maintains context across multiple exchanges, simulating a natural conversation. This capability powers many AI assistants, chatbots, and interactive applications. Azure App Configuration enhances this experience by providing built in validation for chat completion models, ensuring configurations meet required specifications. Additionaly, App Configuration facilitates the discoverability of new models making it easier for developers to find and implement the latest AI models while maintaining a centralized control over model configurations across their applications.
-
-## Chat Completion Parameters
-
-Azure OpenAI chat models support several [parameters](/azure/ai-services/openai/reference#request-body-2) that control how responses are generated. Common parameters include:
-
-| Parameter | Description |
-|-----------|-------------|
-| max_tokens | Maximum number of tokens that can be generated in the chat completion. |
-| temperature | What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. |
-| top_p | An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. |
-| frequency_penalty | Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. |
-| presence_penalty | Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. |
-| stop | Up to four sequences where the API will stop generating further tokens |
-| response_format | Specifies the format that the model must output. |
-
-## Create a chat completion configuration
+Chat completion is an AI capability that enables models to generate conversational responses based on a series of messages. Unlike simple text completion, chat completion maintains context across multiple exchanges, simulating a natural conversation. Chat completion configuration allows you to define and manage how AI models generate responses in your application. A simple configuration includes the model selection and basic prompts. Azure OpenAI chat models support several [configuration options](/azure/ai-services/openai/reference#request-body-2) that control how responses are generated.
 
 ## Prerequisites
 - An Azure account with an active subscription. [Create one for free](https://azure.microsoft.com/free)
 - An App Configuration store. [Create a store](./quickstart-azure-app-configuration-create.md#create-an-app-configuration-store).
 - [Azure OpenAI access](/azure/ai-services/openai/overview#get-started-with-azure-openai-service)
 
 > [!NOTE]
-> This tutorial demonstrates chat completion configuration management using Azure OpenAI models. However the configuration management demonstrated in the tutorial can be applied to any AI model you choose to work with in your application. Users are not limited to using only Azure OpenAI models.
+> This tutorial demonstrates chat completion configuration management using Azure OpenAI models. However the configuration management demonstrated in the tutorial can be applied to any AI model you choose to work with in your application.
 >
 
+## Create a chat completion configuration
+    
+In this section, we will create a chat completion configuration in Azure Portal using the GPT-4o model as our example.
+
  1. In Azure portal, navigate to your App configuration store. From the **Operations** menu, select **Configuration explorer** > **Create**. Then select **AI configuration**.
 
  1. Specify the following values:

articles/azure-app-configuration/media/create-model-endpoint.png

@@ -66,15 +66,15 @@ In this quickstart you will create a .NET console app that retrieves chat comple
 
 1. Connect to your App Configuration store by calling the `AddAzureAppConfiguration` method in the _Program.cs_ file.
 
-    You can connect to App Configuration using **Microsoft Entra ID (recommended)**, or a connection string. In this example, you use Microsoft Entra ID, the `DefaultAzureCredential` to authenticate to your App Configuration store. Follow the [instructions](./concept-enable-rbac.md#authentication-with-token-credentials) to assign your credential the **App Configuration Data Reader** role. Be sure to allow sufficient time for the permission to propagate before running your application.
+    You can connect to App Configuration using **Microsoft Entra ID (recommended)**, or a connection string. In this example, you use Microsoft Entra ID, the `DefaultAzureCredential` to authenticate to your App Configuration store. Follow the [instructions](./concept-enable-rbac.md#authentication-with-token-credentials) to assign your user account the **App Configuration Data Reader** role. Be sure to allow sufficient time for the permission to propagate before running your application.
 
     ```csharp
     var credential = new DefaultAzureCredential();
 
     IConfiguration configuration = new ConfigurationBuilder()
         .AddAzureAppConfiguration(options =>
         {
-            string endpoint = Environment.GetEnvironmentVariable("AZURE_APPCONFIG_ENDPOINT");
+            string endpoint = Environment.GetEnvironmentVariable("AZURE_APPCONFIGURATION_ENDPOINT");
 
             options.Connect(new Uri(endpoint), credential);
         }).Build();
@@ -85,7 +85,7 @@ In this quickstart you will create a .NET console app that retrieves chat comple
     Console.WriteLine($"Hello, I am your AI assistant powered by Azure App Configuration ({model})");
     ```
 
-1. Create an instance of the `AzureOpenAIClient`. Use the existing instance of `DefaultAzureCredential` we created in the previous step to authenticate to your Azure OpenAI resource. Assign your credential the [Cognitive Services OpenAI User](../role-based-access-control/built-in-roles/ai-machine-learning.md#cognitive-services-openai-user) or [Cognitive Services OpenAI Contributor](../role-based-access-control/built-in-roles/ai-machine-learning.md#cognitive-services-openai-contributor). For detailed steps, see [Role-based access control for Azure OpenAI service](/azure/ai-services/openai/how-to/role-based-access-control). Be sure to allow sufficient time for the permission to propagate before running your application.
+1. Create an instance of the `AzureOpenAIClient`. Use the existing instance of `DefaultAzureCredential` we created in the previous step to authenticate to your Azure OpenAI resource. Assign your user account the [Cognitive Services OpenAI User](../role-based-access-control/built-in-roles/ai-machine-learning.md#cognitive-services-openai-user) role or [Cognitive Services OpenAI Contributor](../role-based-access-control/built-in-roles/ai-machine-learning.md#cognitive-services-openai-contributor) role. For detailed steps, see [Role-based access control for Azure OpenAI service](/azure/ai-services/openai/how-to/role-based-access-control). Be sure to allow sufficient time for the permission to propagate before running your application.
 
     ```csharp
     // Existing code to connect to your App configuration store
@@ -162,7 +162,7 @@ In this quickstart you will create a .NET console app that retrieves chat comple
     IConfiguration configuration = new ConfigurationBuilder()
         .AddAzureAppConfiguration(options =>
         {
-            string endpoint = Environment.GetEnvironmentVariable("AZURE_APPCONFIG_ENDPOINT");
+            string endpoint = Environment.GetEnvironmentVariable("AZURE_APPCONFIGURATION_ENDPOINT");
 
             options.Connect(new Uri(endpoint), credential);
 
@@ -215,22 +215,22 @@ In this quickstart you will create a .NET console app that retrieves chat comple
 
 ## Build and run the app locally
 
-1. Set the environment variable named **AZURE_APPCONFIG_ENDPOINT** to the endpoint of your App Configuration store found under the *Overview* of your store in the Azure portal.
+1. Set the environment variable named **AZURE_APPCONFIGURATION_ENDPOINT** to the endpoint of your App Configuration store found under the *Overview* of your store in the Azure portal.
 
     If you use the Windows command prompt, run the following command and restart the command prompt to allow the change to take effect:
 
     ```cmd
-    setx AZURE_APPCONFIG_ENDPOINT "<endpoint-of-your-app-configuration-store>"
+    setx AZURE_APPCONFIGURATION_ENDPOINT "<endpoint-of-your-app-configuration-store>"
     ```
 
     If you use PowerShell, run the following command:
     ```pwsh
-    $Env:AZURE_APPCONFIG_ENDPOINT = "<endpoint-of-your-app-configuration-store>"
+    $Env:AZURE_APPCONFIGURATION_ENDPOINT = "<endpoint-of-your-app-configuration-store>"
     ```
 
     If you use macOS or Linux run the following command:
     ```
-    export AZURE_APPCONFIG_ENDPOINT='<endpoint-of-your-app-configuration-store>'
+    export AZURE_APPCONFIGURATION_ENDPOINT ='<endpoint-of-your-app-configuration-store>'
     ```
 
 1. After the environment variable is properly set, run the following command to run and build your app locally:

articles/azure-app-configuration/quickstart-chat-completion-dotnet.md

@@ -52,19 +52,19 @@ In this quickstart you will create a Node js console app that retrieves chat com
     const { DefaultAzureCredential, getBearerTokenProvider } = require("@azure/identity");
     const { AzureOpenAI } = require("openai");
 
-    const endpoint = process.env.AZURE_APPCONFIG_ENDPOINT;
+    const endpoint = process.env.AZURE_APPCONFIGURATION_ENDPOINT;
     ```
 
 1. Connect to your App Configuration store by calling the `load` method in the `app.js` file.
 
-    You can connect to App Configuration using **Microsoft Entra ID (recommended)**, or a connection string. In this example, you use Microsoft Entra ID, the `DefaultAzureCredential` to authenticate to your App Configuration store. Follow the [instructions](./concept-enable-rbac.md#authentication-with-token-credentials) to assign your credential the **App Configuration Data Reader** role. Be sure to allow sufficient time for the permission to propagate before running your application.
+    You can connect to App Configuration using **Microsoft Entra ID (recommended)**, or a connection string. In this example, you use Microsoft Entra ID, the `DefaultAzureCredential` to authenticate to your App Configuration store. Follow the [instructions](./concept-enable-rbac.md#authentication-with-token-credentials) to assign your user account the **App Configuration Data Reader** role. Be sure to allow sufficient time for the permission to propagate before running your application.
 
     ```javascript
     const { load } = require("@azure/app-configuration-provider");
     const { DefaultAzureCredential, getBearerTokenProvider  } = require("@azure/identity");
     const { AzureOpenAI } = require("openai");
 
-    const endpoint = process.env.AZURE_APPCONFIG_ENDPOINT;
+    const endpoint = process.env.AZURE_APPCONFIGURATION_ENDPOINT;
     
     async function run() {
         const credential = new DefaultAzureCredential();
@@ -80,7 +80,7 @@ In this quickstart you will create a Node js console app that retrieves chat com
     }
     ```
 
-1. Create an instance of the `AzureOpenAI` client. Use the existing instance of `DefaultAzureCredential` we created in the previous step to authenticate to your Azure OpenAI resource. Assign your credential the [Cognitive Services OpenAI User](../role-based-access-control/built-in-roles/ai-machine-learning.md#cognitive-services-openai-user) or [Cognitive Services OpenAI Contributor](../role-based-access-control/built-in-roles/ai-machine-learning.md#cognitive-services-openai-contributor). For detailed steps, see [Role-based access control for Azure OpenAI service](/azure/ai-services/openai/how-to/role-based-access-control). Be sure to allow sufficient time for the permission to propagate before running your application.
+1. Create an instance of the `AzureOpenAI` client. Use the existing instance of `DefaultAzureCredential` we created in the previous step to authenticate to your Azure OpenAI resource. Assign your user account the [Cognitive Services OpenAI User](../role-based-access-control/built-in-roles/ai-machine-learning.md#cognitive-services-openai-user) role or [Cognitive Services OpenAI Contributor](../role-based-access-control/built-in-roles/ai-machine-learning.md#cognitive-services-openai-contributor) role. For detailed steps, see [Role-based access control for Azure OpenAI service](/azure/ai-services/openai/how-to/role-based-access-control). Be sure to allow sufficient time for the permission to propagate before running your application.
 
     ```javascript
     // Existing code to connect to your App configuration store
@@ -130,7 +130,7 @@ In this quickstart you will create a Node js console app that retrieves chat com
     const { DefaultAzureCredential, getBearerTokenProvider } = require("@azure/identity");
     const { AzureOpenAI } = require("openai");
 
-    const endpoint = process.env.AZURE_APPCONFIG_ENDPOINT;
+    const endpoint = process.env.AZURE_APPCONFIGURATION_ENDPOINT;
 
     async function run(){
         const credential = new DefaultAzureCredential();
@@ -174,22 +174,22 @@ In this quickstart you will create a Node js console app that retrieves chat com
 
 ## Build and run the app locally
 
-1. Set the environment variable named **AZURE_APPCONFIG_ENDPOINT** to the endpoint of your App Configuration store found under the *Overview* of your store in the Azure portal.
+1. Set the environment variable named **AZURE_APPCONFIGURATION_ENDPOINT** to the endpoint of your App Configuration store found under the *Overview* of your store in the Azure portal.
 
     If you use the Windows command prompt, run the following command and restart the command prompt to allow the change to take effect:
 
     ```cmd
-    setx AZURE_APPCONFIG_ENDPOINT "<endpoint-of-your-app-configuration-store>"
+    setx AZURE_APPCONFIGURATION_ENDPOINT "<endpoint-of-your-app-configuration-store>"
     ```
 
     If you use PowerShell, run the following command:
     ```pwsh
-    $Env:AZURE_APPCONFIG_ENDPOINT = "<endpoint-of-your-app-configuration-store>"
+    $Env:AZURE_APPCONFIGURATION_ENDPOINT = "<endpoint-of-your-app-configuration-store>"
     ```
 
     If you use macOS or Linux run the following command:
     ```
-    export AZURE_APPCONFIG_ENDPOINT='<endpoint-of-your-app-configuration-store>'
+    export AZURE_APPCONFIGURATION_ENDPOINT='<endpoint-of-your-app-configuration-store>'
     ```
     
 1. After the environment variable is properly set, run the following command to run the app locally: