Merge pull request #5303 from haileytap/hailey-newly-owned-content

[Azure Search] Update Azure AI Foundry portal steps for model deployment

Author: JamesJBarnett

articles/search/includes/quickstarts/agentic-retrieval-python.md

@@ -4,7 +4,7 @@ author: haileytap
 ms.author: haileytapia
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 05/29/2025
+ms.date: 05/30/2025
 ---
 
 [!INCLUDE [Feature preview](../previews/preview-generic.md)]
@@ -39,20 +39,19 @@ Agentic retrieval [supports several models](../../search-agentic-retrieval-how-t
 
 To deploy the Azure OpenAI models:
 
-1. Sign in to the [Azure AI Foundry portal](https://ai.azure.com/).
+1. Sign in to the [Azure AI Foundry portal](https://ai.azure.com/) and select your Azure OpenAI resource.
 
-1. On the home page, find the Azure OpenAI tile and select **Let's go**.
+1. From the left pane, select **Model catalog**.
 
-    :::image type="content" source="../../media/search-get-started-agentic-retrieval/azure-openai-lets-go-tile.png" alt-text="Screenshot of the Azure OpenAI tile in the Azure AI Foundry portal." border="true" lightbox="../../media/search-get-started-agentic-retrieval/azure-openai-lets-go-tile.png":::
+1. Select **gpt-4o-mini**, and then select **Use this model**.
 
-   Your most recently used Azure OpenAI resource appears. If you have multiple Azure OpenAI resources, select **All resources** to switch between them.
+1. Specify a deployment name. To simplify your code, we recommend **gpt-4o-mini**.
 
-1. From the left pane, select **Model catalog**.
+1. Accept the defaults.
 
-1. Deploy `gpt-4o-mini` and `text-embedding-3-large` to your Azure OpenAI resource.
+1. Select **Deploy**.
 
-   > [!NOTE]
-   > To simplify your code, don't use a custom deployment name for either model. This quickstart assumes the deployment and model names are the same.
+1. Repeat the previous steps for **text-embedding-3-large**.
 
 ## Configure role-based access
 

articles/search/includes/quickstarts/agentic-retrieval-rest.md

@@ -4,7 +4,7 @@ author: haileytap
 ms.author: haileytapia
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 05/29/2025
+ms.date: 05/30/2025
 ---
 
 [!INCLUDE [Feature preview](../previews/preview-generic.md)]
@@ -40,20 +40,19 @@ Agentic retrieval [supports several models](../../search-agentic-retrieval-how-t
 
 To deploy the Azure OpenAI models:
 
-1. Sign in to the [Azure AI Foundry portal](https://ai.azure.com/).
+1. Sign in to the [Azure AI Foundry portal](https://ai.azure.com/) and select your Azure OpenAI resource.
 
-1. On the home page, find the Azure OpenAI tile and select **Let's go**.
+1. From the left pane, select **Model catalog**.
 
-    :::image type="content" source="../../media/search-get-started-agentic-retrieval/azure-openai-lets-go-tile.png" alt-text="Screenshot of the Azure OpenAI tile in the Azure AI Foundry portal." border="true" lightbox="../../media/search-get-started-agentic-retrieval/azure-openai-lets-go-tile.png":::
+1. Select **gpt-4o-mini**, and then select **Use this model**.
 
-   Your most recently used Azure OpenAI resource appears. If you have multiple Azure OpenAI resources, select **All resources** to switch between them.
+1. Specify a deployment name. To simplify your code, we recommend **gpt-4o-mini**.
 
-1. From the left pane, select **Model catalog**.
+1. Accept the defaults.
 
-1. Deploy `gpt-4o-mini` and `text-embedding-3-large` to your Azure OpenAI resource.
+1. Select **Deploy**.
 
-   > [!NOTE]
-   > To simplify your code, don't use a custom deployment name for either model. This quickstart assumes the deployment and model names are the same.
+1. Repeat the previous steps for **text-embedding-3-large**.
 
 ## Configure role-based access
 

articles/search/media/vector-search-integrated-vectorization-ai-studio/use-this-model.png

@@ -8,7 +8,7 @@ ms.author: heidist
 ms.service: azure-ai-search
 ms.topic: tutorial
 ms.custom: references_regions
-ms.date: 05/29/2025
+ms.date: 05/30/2025
 
 ---
 
@@ -99,15 +99,13 @@ This tutorial series uses the following models and model providers:
 
 You must have [**Cognitive Services OpenAI Contributor**]( /azure/ai-services/openai/how-to/role-based-access-control#cognitive-services-openai-contributor) or higher to deploy models in Azure OpenAI.
 
-1. Go to [Azure AI Foundry](https://ai.azure.com/).
+1. Sign in to the [Azure AI Foundry portal](https://ai.azure.com/).
 
-1. Select **Deployments** on the left menu.
+1. From the left pane, select **Model catalog**.
 
-1. Select **Deploy model** > **Deploy base model**.
+1. Select **text-embedding-3-large**, and then select **Use this model**.
 
-1. Select **text-embedding-3-large** from the dropdown list and confirm the selection.
-
-1. Specify a deployment name. We recommend "text-embedding-3-large".
+1. Specify a deployment name. We recommend **text-embedding-3-large**.
 
 1. Accept the defaults.
 

articles/search/tutorial-rag-build-solution-models.md

@@ -8,7 +8,7 @@ ms.service: azure-ai-search
 ms.custom:
   - build-2024
 ms.topic: how-to
-ms.date: 05/08/2025
+ms.date: 05/30/2025
 ---
 
 # Use embedding models from Azure AI Foundry model catalog for integrated vectorization
@@ -49,15 +49,17 @@ For image embeddings:
 
 1. Open the [Azure AI Foundry model catalog](https://ai.azure.com/explore/models). Create a project if you don't have one already.
 
-1. Apply a filter to show just the embedding models. Under **Inference tasks**, select **Embeddings**:
+1. From the left pane, select **Model catalog**.
+
+1. Apply a filter to show just the embedding models. Under **Inference tasks**, select **Embeddings**.
 
    :::image type="content" source="media\vector-search-integrated-vectorization-ai-studio\ai-studio-catalog-embeddings-filter.png" lightbox="media\vector-search-integrated-vectorization-ai-studio\ai-studio-catalog-embeddings-filter.png" alt-text="Screenshot of the Azure AI Foundry model catalog page highlighting how to filter by embeddings models.":::
 
-1. Select a supported model, then select **Deploy**.
+1. Select a supported model, and then select **Use this model**.
 
-   :::image type="content" source="media\vector-search-integrated-vectorization-ai-studio\ai-studio-deploy-endpoint.png" lightbox="media\vector-search-integrated-vectorization-ai-studio\ai-studio-deploy-endpoint.png" alt-text="Screenshot of deploying an endpoint via the Azure AI Foundry model catalog.":::
+   :::image type="content" source="media\vector-search-integrated-vectorization-ai-studio\use-this-model.png" lightbox="media\vector-search-integrated-vectorization-ai-studio\use-this-model.png" alt-text="Screenshot of deploying a model via the Azure AI Foundry model catalog.":::
 
-1. Accept the defaults or modify as needed, and then select **Deploy**. The deployment details vary depending on which model you select. 
+1. Accept the defaults or modify as needed, and then select **Deploy**. The deployment details vary depending on which model you select.
 
 1. Wait for the model to finish deploying by monitoring the **Provisioning State**. It should change from "Provisioning" to "Updating" to "Succeeded". You might need to select **Refresh** every few minutes to see the status update.