Merge pull request #5536 from MicrosoftDocs/main

6/13/2025 PM Publish

Author: Taojunshen

articles/ai-foundry/concepts/ai-resources.md

@@ -37,7 +37,7 @@ Hubs group one or more projects together with common settings including data acc
 
 ## Create a hub-based project
 
-To start developing, [create a project](../how-to/create-projects.md). Hub-projects can be accessed in [AI Foundry Portal](https://ai.azure.com/?cid=learnDocs) to build with generative AI tools, and [ML Studio](https://ml.azure.com) to build with tools designed for custom machine learning model training.
+To start developing, [create a [!INCLUDE [hub-project-name](../includes/hub-project-name.md)]](../how-to/create-projects.md?pivots=hub-project). Hub-projects can be accessed in [AI Foundry Portal](https://ai.azure.com/?cid=learnDocs) to build with generative AI tools, and [ML Studio](https://ml.azure.com) to build with tools designed for custom machine learning model training.
 
 ## Project concepts
 
@@ -89,6 +89,7 @@ If not provided by you, the following dependent resources are automatically crea
 
 ## Next steps
 
+- [Create a [!INCLUDE [hub-project-name](../includes/hub-project-name.md)]](../how-to/create-projects.md?pivots=hub-project)
 - [Quickstart: Analyze images and video in the chat playground](/azure/ai-services/openai/gpt-v-quickstart)
 - [Learn more about Azure AI Foundry](../what-is-azure-ai-foundry.md)
 - [Learn more about projects](../how-to/create-projects.md?pivots=hub-project)

articles/ai-services/agents/how-to/tools/azure-ai-search-samples.md

@@ -58,9 +58,12 @@ Using the connection ID of your Azure AI Search resource, configure the Azure AI
 
 ```python
 from azure.ai.agents.models import AzureAISearchTool, AzureAISearchQueryType
+from azure.ai.projects.models import ConnectionType
 
 # Define the Azure AI Search connection ID and index name
-azure_ai_conn_id = os.environ["AZURE_AI_CONNECTION_ID"]
+azure_ai_conn_id = project_client.connections.get_default(ConnectionType.AZURE_AI_SEARCH).id
+
+# find the index name in your AI Search Azure resource page under Search Management -> Indexes
 index_name = "sample_index"
 
 # Initialize the Azure AI Search tool

articles/ai-services/agents/how-to/tools/logic-apps.md

@@ -28,10 +28,38 @@ This article demonstrates how to integrate Logic Apps with Azure AI Agents to ex
    - `SUBSCRIPTION_ID`: Your Azure subscription ID.
    - `resource_group_name`: The name of your resource group.
 
+:::zone pivot="portal"
+
+
+## Add a Logic Apps workflow to an agent using the Azure AI Foundry portal
+
+1. Go to the [Azure AI Foundry portal](https://ai.azure.com/?cid=learnDocs). In the **Agents** screen for your agent, scroll down the **Setup** pane on the right to **Actions**. Then select **Add**.
+
+    :::image type="content" source="../../media/tools/action-tools.png" alt-text="A screenshot showing the available tool categories in the Azure AI Foundry portal." lightbox="../../media/tools/action-tools.png":::
+
+1. Select **Azure Logic Apps** and follow the prompts to add the tool. 
+
+    :::image type="content" source="../../media/tools/action-tools-list.png" alt-text="A screenshot showing the available action tools in the Azure AI Foundry portal." lightbox="../../media/tools/action-tools-list.png":::
+
+    You can choose to add Microsoft authored workflows, or add your own.
+    
+    > [!NOTE]
+    > For your logic apps to appear in the Azure AI Foundry portal, they must:
+    > * Be in the same subscription and resource group.
+    > * Follow a request trigger with a description, and end with a response action. 
+
+    :::image type="content" source="../../media/tools/add-logic-apps.png" alt-text="A screenshot showing the screen to add Logic Apps." lightbox="../../media/tools/add-logic-apps.png":::
+
+
+:::zone-end
+
+:::zone pivot="python"
+
 ## Create a project client
 
 Create a client object to connect to your AI project and other resources.
 
+
 ```python
 import os
 from azure.ai.projects import AIProjectClient
@@ -141,6 +169,8 @@ project_client.agents.delete_agent(agent.id)
 print("Deleted agent")
 ```
 
+:::zone-end
+
 ## Next steps
 
 [See the full sample for Logic Apps integration.](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/ai/azure-ai-agents/samples/agents_tools/sample_agents_logic_apps.py)

articles/ai-services/agents/how-to/tools/sharepoint.md

@@ -48,4 +48,7 @@ Integrate your agents with the **Microsoft SharePoint** to chat with your privat
 
 ## Next steps
 
-[See the full sample for SharePoint.](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/ai/azure-ai-projects/samples/agents/sample_agents_sharepoint.py)
+* [How to use the SharePoint tool](./sharepoint-samples.md)
+* Reference articles for content retrieval used by the tool:
+    * [Overview of the Microsoft 365 Copilot Retrieval API](/microsoft-365-copilot/extensibility/api-reference/retrieval-api-overview).
+    * [Semantic indexing for Microsoft 365 Copilot](/microsoftsearch/semantic-index-for-copilot)

articles/ai-services/agents/how-to/virtual-networks.md

@@ -78,7 +78,10 @@ For customers without an existing virtual network, the Standard Setup with Priva
 * A Microsoft-managed key vault is used by default. 
 
 
-### Option 1: manually deploy the bicep template
+### Manually deploy the bicep template
+
+> [!NOTE]
+> Using the Bicep template is the only way to deploy a network secured environment for Azure AI Foundry Agent Service.
 
 1. To deploy and customize the bicep templates, [download the template from GitHub](https://github.com/azure-ai-foundry/foundry-samples/tree/main/samples/microsoft/infrastructure-setup/15-private-network-standard-agent-setup). Download the following from the `private-network-standard-agent-setup` folder:
     1. `main-create.bicep`

articles/ai-services/agents/media/agent-service-the-glue.png

@@ -3,7 +3,7 @@ title:  Understanding costs associated with provisioned throughput units (PTU)
 description: Learn about provisioned throughput costs and billing in Azure AI Foundry. 
 ms.service: azure-ai-openai
 ms.topic: conceptual 
-ms.date: 05/28/2025
+ms.date: 06/13/2025
 manager: nitinme
 author: aahill 
 ms.author: aahi 
@@ -84,8 +84,9 @@ For example, for `gpt-4.1:2025-04-14`, 1 output token counts as 4 input tokens t
 |Regional provisioned minimum deployment|25| 50|25| 25 |50 | 25|25|50|25| NA|NA|
 |Regional provisioned scale increment|25| 50|25| 25 | 50 | 25|50|50|25|NA|NA|
 |Input TPM per PTU|5,400 | 3,000|14,900| 59,400 | 600 | 2,500|230|2,500|37,000|4,000|4,000|
-|Latency Target Value| 66 Tokens Per Second | 40 Tokens Per Second|50 Tokens Per Second| 60 Tokens Per Second | 40 Tokens Per Second | 66 Tokens Per Second |25 Tokens Per Second|25 Tokens Per Second|33 Tokens Per Second|50 Tokens Per Second|50 Tokens Per Second|
+|Latency Target Value| 99% > 66 Tokens Per Second\* | 99% > 40 Tokens Per Second\* | 99% > 50 Tokens Per Second\*| 99% > 60 Tokens Per Second\* | 99% > 40 Tokens Per Second\* | 99% > 66 Tokens Per Second\* | 99% > 25 Tokens Per Second\* | 99% > 25 Tokens Per Second\* | 99% > 33 Tokens Per Second\* | 99% > 50 Tokens Per Second\*| 99% > 50 Tokens Per Second\*|
 
+\* Calculated as the average request latency on a per-minute basis across the month.
 
 For a full list, see the [Azure AI Foundry calculator](https://ai.azure.com/resource/calculator).
 

articles/ai-services/agents/media/tools/action-tools-list.png

@@ -289,6 +289,10 @@ The following table is a summary of Azure Machine Learning activities and the pe
 
 3. These scenarios don't include the permissions needed to create workspace dependent resources. For more information, see the write permissions for [Storage](https://learn.microsoft.com/azure/role-based-access-control/permissions/storage#microsoftstorage), [OperationalInsights](https://learn.microsoft.com/azure/role-based-access-control/permissions/monitor#microsoftoperationalinsights), [Key Vault](https://learn.microsoft.com/azure/role-based-access-control/permissions/security#microsoftkeyvault) and [Container Registry](https://learn.microsoft.com/azure/role-based-access-control/permissions/containers#microsoftcontainerregistry).
 
+4. When attaching user-managed identities, you also need to have `Microsoft.ManagedIdentity/userAssignedIdentities/assign/action` permission on the identities. For more information, see [Azure built-in roles for Identity](/azure/role-based-access-control/built-in-roles/identity).
+
+5. When specifying a serverless compute custom subnet, you also need to have `Microsoft.Network/virtualNetworks/subnets/join/action` on the virtual network. For more information, see [Azure permissions for Networking](/azure/role-based-access-control/permissions/networking).
+
 ###  Deploy into a virtual network or subnet
 
 [!INCLUDE [network-rbac](includes/network-rbac.md)]