changes

Author: alexwolfmsft

docs/ai/quickstarts/quickstart-openai-summarize-text.md

@@ -28,86 +28,71 @@ In this quickstart, get started with AI by creating a .NET console chat app to c
 
 ---
 
-## Get the sample project
-
-[!INCLUDE [clone-sample-repo](includes/clone-sample-repo.md)]
-
-## Try the hiking benefits sample
+## Create the app
 
-The sample project includes completed apps you can run to connect to your AI model of choice:
-
-# [OpenAI](#tab/openai)
-
-1. From a terminal or command prompt, navigate to the `src\quickstarts\microsoft-extensions-ai\openai\01-HikeBenefitsSummary` directory.
-
-1. Run the following commands to configure your OpenAI API key as a secret for the sample app:
+1. In an empty directory on your computer, use the `dotnet new` command to create a new console app:
 
-    ```bash
-    dotnet user-secrets init
-    dotnet user-secrets set OpenAIKey <your-openai-key>
+    ```dotnetcli
+    dotnet new console -o ExtensionsAI
     ```
 
-1. Use the `dotnet run` command to run the app:
+1. Change directory into the app folder:
 
     ```dotnetcli
-    dotnet run
+    cd ExtensionsAI
     ```
 
-# [Azure OpenAI](#tab/azure-openai)
-
-1. From a terminal or command prompt, navigate to the `src\quickstarts\microsoft-extensions-ai\azure-openai\01-HikeBenefitsSummary` directory.
-
-    > [!NOTE]
-    > The Azure OpenAI scenario assumes the use of `azd` to provision an Azure OpenAI resource and configure essential permissions. Your can also [provision an Azure OpenAI resource](/azure/ai-services/openai/how-to/create-resource) using another tool such as the Azure portal or Azure CLI.
-
-1. Run the `azd up` command to provision the Azure OpenAI resource and configure the necessary permissions. The command may take a few minutes to finish.
+1. Install the required packages:
 
     ```bash
-    azd up
+    dotnet add package Azure.AI.OpenAI
+    dotnet add package Microsoft.Extensions.AI.OpenAI
+    dotnet add package Microsoft.Extensions.Configuration
+    dotnet add package Microsoft.Extensions.Configuration.UserSecrets
     ```
 
-1. Use the `dotnet run` command to run the app:
-
-    ```dotnetcli
-    dotnet run
-    ```
+1. Open the app in Visual Studio code or your editor of choice
 
----
+```bash
+code.
+```
 
-## Explore the code
+## Add the code
 
 The app uses the [`Microsoft.Extensions.AI`](https://www.nuget.org/packages/Microsoft.Extensions.AI) package to send and receive requests to the OpenAI service.
 
-The **Program.cs** file contains all of the app code. The first several lines of code set configuration values to connect and authenticate to the AI model.
+1. In the **Program.cs** file, add the following code to connect and authenticate to the AI model:
 
-# [OpenAI](#tab/openai)
+    # [OpenAI](#tab/openai)
 
-:::code language="csharp" source="./snippets/prompt-completion/extensions-ai/openai/program.cs" range="5-7":::
+    :::code language="csharp" source="./snippets/prompt-completion/extensions-ai/openai/program.cs" range="5-7":::
 
-# [Azure OpenAI](#tab/azure-openai)
+    # [Azure OpenAI](#tab/azure-openai)
 
-> [!NOTE]
-> `DefaultAzureCredential` searches for credentials from your local environment and tooling. If you are not using the `azd` template to provision the Azure OpenAI resource, assign the `Azure AI Developer` role manually to the account you used to sign-in to Visual Studio or the Azure CLI.
+    > [!NOTE]
+    > `DefaultAzureCredential` searches for credentials from your local environment and tooling. If you are not using the `azd` template to provision the Azure OpenAI resource, assign the `Azure AI Developer` role manually to the account you used to sign-in to Visual Studio or the Azure CLI.
 
-:::code language="csharp" source="./snippets/prompt-completion/extensions-ai/azure-openai/program.cs" range="6-8":::
+    :::code language="csharp" source="./snippets/prompt-completion/extensions-ai/azure-openai/program.cs" range="6-8":::
 
----
+    ---
 
-The following code obtains an `IChatClient` service configured to connect to the AI Model. The `OpenAI` and `Azure.AI.OpenAI` libraries implement types defined in the `Microsoft.Extensions.AI` library, which enables you to code using the `IChatClient` interface abstraction. This abstraction allows you to change the underlying AI provider to other services by updating only a few lines of code, such as Ollama or Azure Inference models.
+1. Add the following code to create an `IChatClient` service configured to connect to the AI Model:
 
-# [OpenAI](#tab/openai)
+    # [OpenAI](#tab/openai)
 
-:::code language="csharp" source="./snippets/prompt-completion/extensions-ai/openai/program.cs" range="10-11":::
+    :::code language="csharp" source="./snippets/prompt-completion/extensions-ai/openai/program.cs" range="10-11":::
 
-# [Azure OpenAI](#tab/azure-openai)
+    # [Azure OpenAI](#tab/azure-openai)
 
-:::code language="csharp" source="./snippets/prompt-completion/extensions-ai/azure-openai/program.cs" range="10-12":::
+    :::code language="csharp" source="./snippets/prompt-completion/extensions-ai/azure-openai/program.cs" range="10-12":::
 
----
+    ---
+
+     The `OpenAI` and `Azure.AI.OpenAI` libraries implement types defined in the `Microsoft.Extensions.AI` library, which enables you to code using the `IChatClient` interface abstraction. This abstraction allows you to change the underlying AI provider to other services by updating only a few lines of code, such as Ollama or Azure Inference models.
 
-The `CompleteAsync` function sends the `prompt` to the model to generate a response. The `Microsoft.Extensions.AI` library enables this code to be agnostic towards a specific AI service because it uses an `IChatClient` abstraction rather than a platform-specific SDK implementation.
+1. Use the `CompleteAsync` function to send a `prompt` to the model to generate a response.
 
-:::code language="csharp" source="./snippets/prompt-completion/extensions-ai/openai/program.cs" range="14-22":::
+    :::code language="csharp" source="./snippets/prompt-completion/extensions-ai/openai/program.cs" range="14-22":::
 
 Customize the text content of the `benefits.md` file or the length of the summary to see the differences in the responses.