Merge pull request #7737 from TimShererWithAquent/us496641-10

Freshness Edit: AI Foundry: Develop applications with Semantic Kernel and Azure AI Foundry

Author: prmerger-automator[bot]

articles/ai-foundry/how-to/develop/semantic-kernel.md

@@ -1,11 +1,11 @@
 ---
-title: Develop applications with Semantic Kernel and Azure AI Foundry
+title: Develop Applications with Semantic Kernel and Azure AI Foundry
 titleSuffix: Azure AI Foundry
-description: Develop applications with Semantic Kernel and Azure AI Foundry.
+description: Learn how to Develop applications with Semantic Kernel and Azure AI Foundry with models deployed from the Azure AI model catalog.
 author: lgayhardt
 ms.author: lagayhar
 ms.reviewer: taochen
-ms.date: 02/27/2025
+ms.date: 10/20/2025
 ms.topic: how-to
 ms.service: azure-ai-foundry
 ---
@@ -17,27 +17,27 @@ In this article, you learn how to use [Semantic Kernel](/semantic-kernel/overvie
 ## Prerequisites
 
 - [!INCLUDE [azure-subscription](../../includes/azure-subscription.md)]
-- An Azure AI project as explained at [Create a project in Azure AI Foundry portal](../create-projects.md).
-- A model supporting the [Azure AI Model Inference API](../../../ai-foundry/model-inference/reference/reference-model-inference-api.md?tabs=python) deployed. In this example, we use a `Mistral-Large` deployment, but use any model of your preference. For using embeddings capabilities in LlamaIndex, you need an embedding model like `cohere-embed-v3-multilingual`.
+- An Azure AI project as explained at [Create a project for Azure AI Foundry](../create-projects.md).
+- A model that supports the [Azure AI Model Inference API](../../../ai-foundry/model-inference/reference/reference-model-inference-api.md?tabs=python) deployed. This article uses a `Mistral-Large` deployment. You can use any model. For using embeddings capabilities in LlamaIndex, you need an embedding model like `cohere-embed-v3-multilingual`.
 
   - You can follow the instructions at [Deploy models as serverless API deployments](../deploy-models-serverless.md).
 
 - Python **3.10** or later installed, including pip.
-- Semantic Kernel installed. You can do it with:
+- Semantic Kernel installed. You can use the following command:
 
     ```bash
     pip install semantic-kernel
     ```
 
-- In this example, we're working with the Model Inference API, so we need to install the relevant Azure dependencies. You can do it with:
+- This article uses the Model Inference API, so install the relevant Azure dependencies. You can use the following command:
 
     ```bash
     pip install semantic-kernel[azure]
     ```
 
 ## Configure the environment
 
-To use LLMs deployed in Azure AI Foundry portal, you need the endpoint and credentials to connect to it. Follow these steps to get the information you need from the model you want to use:
+To use language models deployed in Azure AI Foundry portal, you need the endpoint and credentials to connect to your project. Follow these steps to get the information you need from the model:
 
 [!INCLUDE [tip-left-pane](../../includes/tip-left-pane.md)]
 
@@ -49,14 +49,14 @@ To use LLMs deployed in Azure AI Foundry portal, you need the endpoint and crede
     > [!TIP]
     > If your model was deployed with Microsoft Entra ID support, you don't need a key.
 
-In this scenario, we placed both the endpoint URL and key in the following environment variables:
+This example uses environment variables for both the endpoint URL and key:
 
 ```bash
 export AZURE_AI_INFERENCE_ENDPOINT="<your-model-endpoint-goes-here>"
 export AZURE_AI_INFERENCE_API_KEY="<your-key-goes-here>"
 ```
 
-Once configured, create a client to connect to the endpoint:
+After you configure the endpoint and key, create a client to connect to the endpoint:
 
 ```python
 from semantic_kernel.connectors.ai.azure_ai_inference import AzureAIInferenceChatCompletion
@@ -65,7 +65,7 @@ chat_completion_service = AzureAIInferenceChatCompletion(ai_model_id="<deploymen
 ```
 
 > [!TIP]
-> The client automatically reads the environment variables `AZURE_AI_INFERENCE_ENDPOINT` and `AZURE_AI_INFERENCE_API_KEY` to connect to the model. However, you can also pass the endpoint and key directly to the client via the `endpoint` and `api_key` parameters on the constructor.
+> The client automatically reads the environment variables `AZURE_AI_INFERENCE_ENDPOINT` and `AZURE_AI_INFERENCE_API_KEY` to connect to the model. You could instead pass the endpoint and key directly to the client by using the `endpoint` and `api_key` parameters on the constructor.
 
 Alternatively, if your endpoint support Microsoft Entra ID, you can use the following code to create the client:
 
@@ -80,7 +80,7 @@ chat_completion_service = AzureAIInferenceChatCompletion(ai_model_id="<deploymen
 ```
 
 > [!NOTE]
-> When using Microsoft Entra ID, make sure that the endpoint was deployed with that authentication method and that you have the required permissions to invoke it.
+> If you use Microsoft Entra ID, make sure that the endpoint was deployed with that authentication method and that you have the required permissions to invoke it.
 
 ### Azure OpenAI models
 
@@ -104,7 +104,7 @@ chat_completion_service = AzureAIInferenceChatCompletion(
 
 ## Inference parameters
 
-You can configure how inference is performed by using the `AzureAIInferenceChatPromptExecutionSettings` class:
+You can configure how to perform inference by using the `AzureAIInferenceChatPromptExecutionSettings` class:
 
 ```python
 from semantic_kernel.connectors.ai.azure_ai_inference import AzureAIInferenceChatPromptExecutionSettings
@@ -119,7 +119,7 @@ execution_settings = AzureAIInferenceChatPromptExecutionSettings(
 
 ## Calling the service
 
-Let's first call the chat completion service with a simple chat history:
+First, call the chat completion service with a simple chat history:
 
 > [!TIP]
 > Semantic Kernel is an asynchronous library, so you need to use the asyncio library to run the code.