Merge pull request #278299 from eric-urban/eur/sdk-qs-leah-update

sdk qs update

Author: prmerger-automator[bot]

articles/ai-studio/quickstarts/get-started-code.md

@@ -13,7 +13,6 @@ author: eric-urban
 ---
 
 # Build a custom chat app in Python using the prompt flow SDK
-
 [!INCLUDE [Feature preview](~/reusable-content/ce-skilling/azure/includes/ai-studio/includes/feature-preview.md)]
 
 In this quickstart, we walk you through setting up your local development environment with the prompt flow SDK. We write a prompt, run it as part of your app code, trace the LLM calls being made, and run a basic evaluation on the outputs of the LLM.
@@ -139,7 +138,7 @@ Activating the Python environment means that when you run ```python``` or ```pip
 
 ## Install the prompt flow SDK
 
-In this section, we use prompt flow to build our application. [Prompt flow](https://microsoft.github.io/promptflow/) is a suite of development tools designed to streamline the end-to-end development cycle of LLM-based AI applications, from ideation, prototyping, testing, evaluation to production deployment and monitoring.
+In this section, we use prompt flow to build our application. [Prompt flow](https://microsoft.github.io/promptflow) is a suite of development tools designed to streamline the end-to-end development cycle of LLM-based AI applications, from ideation, prototyping, testing, evaluation to production deployment and monitoring.
 
 Use pip to install the prompt flow SDK into the virtual environment that you created.
 ```
@@ -161,24 +160,24 @@ Your AI services endpoint and deployment name are required to call the Azure Ope
 1. Create a ```.env``` file, and paste the following code:
     ```
     AZURE_OPENAI_ENDPOINT=endpoint_value
-    AZURE_OPENAI_DEPLOYMENT_NAME=deployment_name
-    AZURE_OPENAI_API_VERSION=2024-02-15-preview
+    AZURE_OPENAI_CHAT_DEPLOYMENT=chat_deployment_name
+    AZURE_OPENAI_API_VERSION=api_version
     ```
 
 1. Navigate to the [chat playground inside of your AI Studio project](./get-started-playground.md#chat-in-the-playground-without-your-data). First validate that chat is working with your model by sending a message to the LLM.
 1. Find the Azure OpenAI deployment name in the chat playground. Select the deployment in the dropdown and hover over the deployment name to view it. In this example, the deployment name is **gpt-35-turbo-16k**.
 
     :::image type="content" source="../media/quickstarts/promptflow-sdk/playground-deployment-view-code.png" alt-text="Screenshot of the AI Studio chat playground opened, highlighting the deployment name and the view code button." lightbox="../media/quickstarts/promptflow-sdk/playground-deployment-view-code.png":::
 
-1. In the ```.env``` file, replace ```deployment_name``` with the name of the deployment from the previous step. In this example, we're using the deployment name ```gpt-35-turbo-16k```. 
-1. Select the **<\> View Code** button and copy the endpoint value.
+1. In the ```.env``` file, replace ```chat_deployment_name``` with the name of the deployment from the previous step. In this example, we're using the deployment name ```gpt-35-turbo-16k```. 
+1. Select the **<\> View Code** button and copy the endpoint value and API version value.
 
     :::image type="content" source="../media/quickstarts/promptflow-sdk/playground-copy-endpoint.png" alt-text="Screenshot of the view code popup highlighting the button to copy the endpoint value." lightbox="../media/quickstarts/promptflow-sdk/playground-copy-endpoint.png":::
 
-1. In the ```.env``` file, replace ```endpoint_value``` with the endpoint value copied from the dialog in the previous step. 
+1. In the ```.env``` file, replace ```endpoint_value``` with the endpoint value and replace ```api_version``` with the API version copied from the dialog in the previous step (such as "2024-02-15-preview"). 
 
 > [!WARNING]
-> Key based authentication is supported but isn't recommended by Microsoft. If you want to use keys you can add your key to the ```.env```, but please ensure that your ```.env``` is in your ```.gitignore``` file so that you don't accidentally checked into your git repository.
+> Key based authentication is supported but isn't recommended by Microsoft. If you want to use keys you can add your key to the ```.env```, but please ensure that your ```.env``` is in your ```.gitignore``` file so that you don't accidentally check it into your git repository.
 
 ## Create a basic chat prompt and app
 
@@ -231,7 +230,7 @@ load_dotenv()
 from promptflow.core import Prompty, AzureOpenAIModelConfiguration
 
 model_config = AzureOpenAIModelConfiguration(
-    azure_deployment=os.getenv("AZURE_OPENAI_DEPLOYMENT_NAME"),
+    azure_deployment=os.getenv("AZURE_OPENAI_CHAT_DEPLOYMENT"),
     api_version=os.getenv("AZURE_OPENAI_API_VERSION"),
     azure_endpoint=os.getenv("AZURE_OPENAI_ENDPOINT")
 )
@@ -307,7 +306,7 @@ from promptflow.core import Prompty, AzureOpenAIModelConfiguration
 from promptflow.evals.evaluators import ChatEvaluator
 
 model_config = AzureOpenAIModelConfiguration(
-    azure_deployment=os.getenv("AZURE_OPENAI_DEPLOYMENT_NAME"),
+    azure_deployment=os.getenv("AZURE_OPENAI_CHAT_DEPLOYMENT"),
     api_version=os.getenv("AZURE_OPENAI_API_VERSION"),
     azure_endpoint=os.getenv("AZURE_OPENAI_ENDPOINT")
 )
@@ -352,4 +351,4 @@ For more information on how to use prompt flow evaluators, including how to make
 
 - [Quickstart: Create a project and use the chat playground in Azure AI Studio](./get-started-playground.md)
 - [Work with projects in VS Code](../how-to/develop/vscode.md)
-- [Overview of the Azure AI SDKs](../how-to/develop/sdk-overview.md)
+- [Overview of the Azure AI SDKs](../how-to/develop/sdk-overview.md)