Merge pull request #7339 from msakande/freshness-create-model-deployments

freshness - deploy foundry models

Author: v-shils

articles/ai-foundry/.openpublishing.redirection.ai-studio.json

@@ -25,6 +25,11 @@
           "redirect_url": "/azure/ai-foundry/whats-new-azure-ai-foundry",
           "redirect_document_id": false
         },
+        {
+          "source_path_from_root": "/articles/ai-foundry/foundry-models/how-to/github/create-model-deployments.md",
+          "redirect_url": "/azure/ai-foundry/foundry-models/how-to/create-model-deployments",
+          "redirect_document_id": false
+        },
         {
           "source_path_from_root": "/articles/ai-foundry/concepts/rbac-ai-foundry.md",
           "redirect_url": "/azure/ai-foundry/concepts/rbac-azure-ai-foundry",

articles/ai-foundry/foundry-models/how-to/create-model-deployments.md

@@ -1,18 +1,21 @@
 ---
 title: Add and configure models to Azure AI Foundry
 titleSuffix: Azure AI Foundry
-description: Learn how to add and configure new models to the Azure AI Foundry's inference endpoint.
+description: Learn how to add and configure AI models to Azure AI Foundry Models inference endpoint for deployment and inference in your applications.
 ms.service: azure-ai-foundry
 ms.subservice: azure-ai-foundry-model-inference
 ms.topic: how-to
-ms.date: 05/19/2025
+ms.date: 09/29/2025
 ms.custom: ignite-2024, github-universe-2024
 author: msakande   
 ms.author: mopeakande
 recommendations: false
 zone_pivot_groups: azure-ai-models-deployment
 ms.reviewer: fasantia
 reviewer: santiagxf
+ai.usage: ai-assisted
+
+#CustomerIntent: As a developer or AI practitioner, I want to deploy and configure AI models to Azure AI Foundry Models endpoint so that I can integrate these models into my applications and generate predictions through inference requests.
 ---
 
 # Add and configure models to Azure AI Foundry Models
@@ -29,6 +32,6 @@ reviewer: santiagxf
 [!INCLUDE [bicep](../../foundry-models/includes/create-model-deployments/bicep.md)]
 ::: zone-end
 
-## Next steps
+## Next step
 
 * [Develop applications using Azure AI Foundry Models](../../model-inference/supported-languages.md)

articles/ai-foundry/foundry-models/how-to/github/create-model-deployments.md

@@ -4,7 +4,7 @@ author: santiagxf
 ms.author: fasantia 
 ms.service: azure-ai-foundry
 ms.subservice: azure-ai-foundry-model-inference
-ms.date: 1/21/2025
+ms.date: 09/29/2025
 ms.topic: include
 zone_pivot_groups: azure-ai-models-deployment
 ---
@@ -17,11 +17,11 @@ zone_pivot_groups: azure-ai-models-deployment
 
   * Your Azure subscription ID.
 
-  * Your Azure AI Foundry (formerly known Azure AI Services) resource name.
+  * Your Azure AI Foundry resource (formerly known as Azure AI Services resource) name.
 
   * The resource group where the Azure AI Foundry resource is deployed.
 
-  * The model name, provider, version, and SKU you would like to deploy. You can use the Azure AI Foundry portal or the Azure CLI to identify it. In this example we deploy the following model:
+  * The model name, provider, version, and SKU you want to deploy. You can use the Azure AI Foundry portal or the Azure CLI to find this information. In this example, you deploy the following model:
 
     * **Model name:**: `Phi-3.5-vision-instruct`
     * **Provider**: `Microsoft`
@@ -52,7 +52,7 @@ cd azureai-model-inference-bicep/infra
 
     :::code language="bicep" source="~/azureai-model-inference-bicep/infra/modules/ai-services-deployment-template.bicep":::
 
-2. Run the deployment:
+1. Run the deployment:
 
     ```azurecli
     RESOURCE_GROUP="<resource-group-name>"
@@ -70,4 +70,18 @@ cd azureai-model-inference-bicep/infra
 
 ## Use the model
 
-Deployed models can be consumed using the [Azure AI model's inference endpoint](../../concepts/endpoints.md) for the resource. When constructing your request, indicate the parameter `model` and insert the model deployment name you have created.
+Deployed models in can be consumed using the [Azure AI model's inference endpoint](../../concepts/endpoints.md) for the resource. When constructing your request, indicate the parameter `model` and insert the model deployment name you have created. You can programmatically get the URI for the inference endpoint using the following code:
+
+__Inference endpoint__
+
+```azurecli
+az cognitiveservices account show  -n $accountName -g $resourceGroupName | jq '.properties.endpoints["Azure AI Model Inference API"]'
+```
+
+To make requests to the Azure AI Foundry Models endpoint, append the route `models`, for example `https://<resource>.services.ai.azure.com/models`. You can see the API reference for the endpoint at [Azure AI Model Inference API reference page](https://aka.ms/azureai/modelinference).
+
+__Inference keys__
+
+```azurecli
+az cognitiveservices account keys list  -n $accountName -g $resourceGroupName
+```

articles/ai-foundry/foundry-models/includes/create-model-deployments/bicep.md

@@ -4,61 +4,61 @@ author: santiagxf
 ms.author: fasantia 
 ms.service: azure-ai-foundry
 ms.subservice: azure-ai-foundry-model-inference
-ms.date: 1/21/2025
+ms.date: 09/29/2025
 ms.topic: include
 zone_pivot_groups: azure-ai-models-deployment
 ---
 
 [!INCLUDE [Header](intro.md)]
 
-* Install the [Azure CLI](/cli/azure/) and the `cognitiveservices` extension for Azure AI Services:
+* Install the [Azure CLI](/cli/azure/) and the `cognitiveservices` extension for Azure AI Services.
 
     ```azurecli
     az extension add -n cognitiveservices
     ```
 
-* Some of the commands in this tutorial use the `jq` tool, which might not be installed in your system. For installation instructions, see [Download `jq`](https://stedolan.github.io/jq/download/).
+* Some of the commands in this tutorial use the `jq` tool, which might not be installed on your system. For installation instructions, see [Download `jq`](https://stedolan.github.io/jq/download/).
 
 * Identify the following information:
 
   * Your Azure subscription ID.
 
   * Your Azure AI Services resource name.
 
-  * The resource group where the Azure AI Services resource is deployed.
+  * The resource group where you deployed the Azure AI Services resource.
     
     
 ## Add models
 
-To add a model, you first need to identify the model that you want to deploy. You can query the available models as follows:
+To add a model, first identify the model that you want to deploy. You can query the available models as follows:
 
-1. Log in into your Azure subscription:
+1. Sign in to your Azure subscription.
 
     ```azurecli
     az login
     ```
 
-2. If you have more than 1 subscription, select the subscription where your resource is located:
+1. If you have more than one subscription, select the subscription where your resource is located.
 
     ```azurecli
     az account set --subscription $subscriptionId
     ```
 
-3. Set the following environment variables with the name of the Azure AI Services resource you plan to use and resource group.
+1. Set the following environment variables with the name of the Azure AI Services resource you plan to use and resource group.
 
     ```azurecli
     accountName="<ai-services-resource-name>"
     resourceGroupName="<resource-group>"
     location="eastus2"
     ```
 
-3. If you don't have an Azure AI Services account create yet, you can create one as follows:
+1. If you didn't create an Azure AI Services account yet, create one.
 
     ```azurecli
     az cognitiveservices account create -n $accountName -g $resourceGroupName --custom-domain $accountName --location $location --kind AIServices --sku S0
     ```
 
-4. Let's see first which models are available to you and under which SKU. SKUs, also known as [deployment types](../../concepts/deployment-types.md), define how Azure infrastructure is used to process requests. Models may offer different deployment types. The following command list all the model definitions available:
+1. Check which models are available to you and under which SKU. SKUs, also known as [deployment types](../../concepts/deployment-types.md), define how Azure infrastructure is used to process requests. Models might offer different deployment types. The following command lists all the model definitions available:
     
     ```azurecli
     az cognitiveservices account list-models \
@@ -67,7 +67,7 @@ To add a model, you first need to identify the model that you want to deploy. Yo
     | jq '.[] | { name: .name, format: .format, version: .version, sku: .skus[0].name, capacity: .skus[0].capacity.default }'
     ```
 
-5. Outputs look as follows:
+1. Outputs look as follows:
 
     ```output
     {
@@ -79,9 +79,9 @@ To add a model, you first need to identify the model that you want to deploy. Yo
     }
     ```
 
-6. Identify the model you want to deploy. You need the properties `name`, `format`, `version`, and `sku`. The property `format` indicates the provider offering the model. Capacity might also be needed depending on the type of deployment.
+1. Identify the model you want to deploy. You need the properties `name`, `format`, `version`, and `sku`. The property `format` indicates the provider offering the model. You might also need capacity depending on the type of deployment.
 
-7. Add the model deployment to the resource. The following example adds `Phi-3.5-vision-instruct`:
+1. Add the model deployment to the resource. The following example adds `Phi-3.5-vision-instruct`:
 
     ```azurecli
     az cognitiveservices account deployment create \
@@ -95,9 +95,9 @@ To add a model, you first need to identify the model that you want to deploy. Yo
         --sku-name GlobalStandard
     ```
 
-8. The model is ready to be consumed.
+1. The model is ready to use.
 
-You can deploy the same model multiple times if needed as long as it's under a different deployment name. This capability might be useful in case you want to test different configurations for a given model, including content filters.
+You can deploy the same model multiple times if needed as long as it's under a different deployment name. This capability might be useful if you want to test different configurations for a given model, including content filters.
 
 ## Use the model
 

articles/ai-foundry/foundry-models/includes/create-model-deployments/cli.md

@@ -4,20 +4,21 @@ author: santiagxf
 ms.author: fasantia 
 ms.service: azure-ai-foundry
 ms.subservice: azure-ai-foundry-model-inference
-ms.date: 1/21/2025
+ms.date: 09/29/2025
 ms.topic: include
 ---
 
-You can decide and configure which models are available for inference in your Azure AI Foundry resource. When a given model is configured, you can then generate predictions from it by indicating its model name or deployment name on your requests. No further changes are required in your code to use it.
+You can decide and configure which models are available for inference in your Azure AI Foundry resource. When you configure a model, you can generate predictions from it by specifying its model name or deployment name in your requests. You don't need to make any other changes in your code to use the model.
 
-In this article, you'll learn how to add a new model to Azure AI Foundry.
+In this article, you learn how to add a new model to an Azure AI Foundry Models endpoint.
 
 ## Prerequisites
 
 To complete this article, you need:
 
 * An Azure subscription. If you're using [GitHub Models](https://docs.github.com/en/github-models/), you can upgrade your experience and create an Azure subscription in the process. Read [Upgrade from GitHub Models to Azure AI Foundry Models](../../how-to/quickstart-github-models.md) if that's your case.
 
-* An Azure AI Foundry resource (formerly known as Azure AI Services). For more information, see [Create and configure all the resources for Azure AI Foundry Models](../../how-to/quickstart-create-resources.md).
+* An Azure AI Foundry project. This kind of project is managed under an Azure AI Foundry resource (formerly known as Azure AI Services resource). If you don't have a Foundry project, see [Create a project for Azure AI Foundry (Foundry projects)](../../../how-to/create-projects.md).
+
 
 * [Models from Partners and Community](../../concepts/models.md#models-from-partners-and-community) require access to **Azure Marketplace**. Ensure you have the [permissions required to subscribe to model offerings](../../how-to/configure-marketplace.md). [Models Sold Directly by Azure](../../concepts/models.md#models-sold-directly-by-azure) don't have this requirement.