Merge pull request #5392 from MicrosoftDocs/main

6/5/2025 AM Publish

Author: Taojunshen

articles/ai-services/agents/how-to/tools/bing-grounding.md

@@ -37,6 +37,13 @@ Grounding with Bing returns relevant search results to the customer's model depl
 
 The authorization will happen between Grounding with Bing Search service and Azure AI Foundry Agent Service. Any Bing search query that is generated and sent to Bing for the purposes of grounding is transferred, along with the resource key, outside of the Azure compliance boundary to the Grounding with Bing Search service. Grounding with Bing Search is subject to Bing's terms and do not have the same compliance standards and certifications as the Azure AI Foundry Agent Service, as described in the [Grounding with Bing Search Terms of Use](https://www.microsoft.com/bing/apis/grounding-legal). It is your responsibility to assess whether the use of Grounding with Bing Search in your agent meets your needs and requirements.
 
+## Supported capabilities and known issues
+- Grounding with Bing Search tool is designed to retrieve real-time information from web, NOT specific web domains.
+- NOT Recommended to **summarize** an entire web page.
+- Within one run, the AI model will evaluate the tool outputs and may decide to invoke the tool again for more information and context. AI model may also decide which piece(s) of tool outputs are used to generate the response.
+- Azure AI Agent service will return **AI model generated response** as output so end-to-end latency will be impacted pre-/post-processing of LLMs.
+- Grounding with Bing Search tool does NOT return the tool output to developers and end users.
+
 ## Usage support
 
 |Azure AI foundry support  | Python SDK |	C# SDK | JavaScript SDK | REST API |Basic agent setup | Standard agent setup |

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

@@ -54,6 +54,7 @@ For customers without an existing virtual network, the Standard Setup with Priva
     * `Microsoft.Search`
     * `Microsoft.Network`
     * `Microsoft.App`
+    * `Microsoft.ContainerService`
     * To use Bing Search tool: `Microsoft.Bing`
 
     ```console
@@ -104,6 +105,36 @@ For customers without an existing virtual network, the Standard Setup with Priva
         ```console
         az deployment group create --resource-group {my_resource_group} --template-file main-create.bicep
         ```
+
+1. Run the CheckCapabilityHostReadiness.ps1 and edit the command to add your subscription ID, resource group name, and your newly deployed AI Services account resource name.
+   
+   ```
+   .\CheckCapabilityHostReadiness.ps1 -subscriptionId "<your-sub-id>" -resourcegroup "<new-rg-name>" -accountname "<your-aiservices-name>"
+   ```
+   
+   If you don't want to run the PowerShell script, you can run a bash script instead, from the file CheckCapabilityHostReadiness.sh. Run the following two commands:
+   
+      ```
+      chmod +x CheckCapabilityHostReadiness.sh
+      ./CheckCapabilityHostReadiness.sh "<your-sub-id>" "<new-rg-name>" "<your-aiservices-name>"
+      ```
+      
+1. Deploy the main-project-caphost-create.bicep
+   
+   ```
+   az deployment group create --resource-group <new-rg-name> --template-file main-project-caphost-create.bicep
+   ```
+   
+   After running this script, you're required to input the following values:
+   
+   ```
+   Please provide string value for 'accountName' (? for help): <your-account-name>
+   Please provide string value for 'projectName' (? for help): <your-project-name>
+   Please provide string value for 'aiSearchName' (? for help): <your-search-name>
+   Please provide string value for 'azureStorageName' (? for help): <your-storage-name>
+   Please provide string value for 'cosmosDBName' (? for help): <your-cosmosdb-name>
+   ```
+
 For more details, see the [README](https://github.com/azure-ai-foundry/foundry-samples/tree/main/samples/microsoft/infrastructure-setup/15-private-network-standard-agent-setup).
 
 ## Deep Dive Standard Setup with Private Networking Template

articles/ai-services/agents/includes/quickstart-python.md

@@ -79,32 +79,32 @@ with project_client:
     )
     print(f"Created agent, ID: {agent.id}")
 
-# Create a thread for communication
-thread = project_client.agents.threads.create()
-print(f"Created thread, ID: {thread.id}")
-
-# Add a message to the thread
-message = project_client.agents.messages.create(
-    thread_id=thread.id,
-    role="user",  # Role of the message sender
-    content="What is the weather in Seattle today?",  # Message content
-)
-print(f"Created message, ID: {message['id']}")
-
-# Create and process an agent run
-run = project_client.agents.runs.create_and_process(thread_id=thread.id, agent_id=agent.id)
-print(f"Run finished with status: {run.status}")
-
-# Check if the run failed
-if run.status == "failed":
-    print(f"Run failed: {run.last_error}")
-
-# Fetch and log all messages
-messages = project_client.agents.messages.list(thread_id=thread.id)
-for message in messages.data:
-    print(f"Role: {message.role}, Content: {message.content}")
-
-# Delete the agent when done
-project_client.agents.delete_agent(agent.id)
-print("Deleted agent")
+    # Create a thread for communication
+    thread = project_client.agents.threads.create()
+    print(f"Created thread, ID: {thread.id}")
+    
+    # Add a message to the thread
+    message = project_client.agents.messages.create(
+        thread_id=thread.id,
+        role="user",  # Role of the message sender
+        content="What is the weather in Seattle today?",  # Message content
+    )
+    print(f"Created message, ID: {message['id']}")
+    
+    # Create and process an agent run
+    run = project_client.agents.runs.create_and_process(thread_id=thread.id, agent_id=agent.id)
+    print(f"Run finished with status: {run.status}")
+    
+    # Check if the run failed
+    if run.status == "failed":
+        print(f"Run failed: {run.last_error}")
+    
+    # Fetch and log all messages
+    messages = project_client.agents.messages.list(thread_id=thread.id)
+    for message in messages:
+        print(f"Role: {message.role}, Content: {message.content}")
+    
+    # Delete the agent when done
+    project_client.agents.delete_agent(agent.id)
+    print("Deleted agent")
 ```

articles/ai-services/openai/how-to/provisioned-throughput-onboarding.md

@@ -77,14 +77,14 @@ The amount of throughput (measured in tokens per minute or TPM) a deployment get
 
 For example, for `gpt-4.1:2025-04-14`, 1 output token counts as 4 input tokens towards your utilization limit which matches the [pricing](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/). Older models use a different ratio and for a deeper understanding on how different ratios of input and output tokens impact the throughput your workload needs, see the [Azure AI Foundry PTU quota calculator](https://ai.azure.com/resource/calculator).
 
-|Topic| **o4-mini** | **gpt-4.1** | **gpt-4.1-mini** | **gpt-4.1-nano** | **o3** | **o3-mini** | **o1** | **gpt-4o** | **gpt-4o-mini** |  **DeepSeek-R1** | **DeepSeek-V3-0324** | **MAI-DS-R1** |
-| --- |  --- | --- |  --- |  --- | --- | --- | --- | --- | --- | --- | --- | --- |
-|Global & data zone provisioned minimum deployment| 15 | 15|15| 15 | 15 |15|15|15|15| 100|100|100|
-|Global & data zone provisioned scale increment| 5 | 5|5| 5 | 5 |5|5|5|5|  100|100|100|
-|Regional provisioned minimum deployment|25| 50|25| 25 |50 | 25|25|50|25| NA|NA|NA|
-|Regional provisioned scale increment|25| 50|25| 25 | 50 | 25|50|50|25|NA|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|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|50 Tokens Per Second|
+|Topic| **o4-mini** | **gpt-4.1** | **gpt-4.1-mini** | **gpt-4.1-nano** | **o3** | **o3-mini** | **o1** | **gpt-4o** | **gpt-4o-mini** |  **DeepSeek-R1** | **DeepSeek-V3-0324** |
+| --- |  --- | --- |  --- |  --- | --- | --- | --- | --- | --- | --- | --- |
+|Global & data zone provisioned minimum deployment| 15 | 15|15| 15 | 15 |15|15|15|15| 100|100|
+|Global & data zone provisioned scale increment| 5 | 5|5| 5 | 5 |5|5|5|5|  100|100|
+|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|
 
 
 For a full list, see the [Azure AI Foundry calculator](https://ai.azure.com/resource/calculator).

articles/machine-learning/feature-retrieval-concepts.md

@@ -96,7 +96,7 @@ serialization_version: 2
 The feature store point-in-time join can create training data in two ways:
 
 - The `get_offline_features()` API function in the feature store SDK in a Spark session/job
-- The Azure Machine Learning build-in feature retrieval (pipeline) component
+- The Azure Machine Learning built-in feature retrieval (pipeline) component
 
 In the first option, the feature retrieval specification itself is optional because the user can provide the list of features on that API. However, if a feature retrieval specification is provided, the `resolve_feature_retrieval_spec()` function in the feature store SDK can load the list of features that the specification defined. That function then passes that list to the `get_offline_features()` API function.
 

articles/machine-learning/troubleshooting-managed-feature-store.md

@@ -279,7 +279,7 @@ Once the `begin_create_or_update()` call returns successfully, the next `feature
 - [Observation Data isn't Joined with any feature values](#observation-data-isnt-joined-with-any-feature-values)
 - [User or Managed Identity doesn't have proper RBAC permission on the feature store](#user-or-managed-identity-doesnt-have-proper-rbac-permission-on-the-feature-store)
 - [User or Managed Identity doesn't have proper RBAC permission to Read from the Source Storage or Offline store](#user-or-managed-identity-doesnt-have-proper-rbac-permission-to-read-from-the-source-storage-or-offline-store)
-- [Training job fails to read data generated by the build-in Feature Retrieval Component](#training-job-fails-to-read-data-generated-by-the-build-in-feature-retrieval-component)
+- [Training job fails to read data generated by the built-in Feature Retrieval Component](#training-job-fails-to-read-data-generated-by-the-built-in-feature-retrieval-component)
 - [`generate_feature_retrieval_spec()` fails due to use of local feature set specification](#generate_feature_retrieval_spec-fails-due-to-use-of-local-feature-set-specification)
 - [The `get_offline_features()` query takes a long time](#the-get_offline_features-query-takes-a-long-time)
 
@@ -450,7 +450,7 @@ An error occurred while calling o1025.parquet.
 
 `Storage Blob Data Reader` is the minimum recommended access requirement. Users can also assign roles - for example, `Storage Blob Data Contributor` or `Storage Blob Data Owner` - with more privileges.
 
-### Training job fails to read data generated by the build-in Feature Retrieval Component
+### Training job fails to read data generated by the built-in Feature Retrieval Component
 
 #### Symptom
 

articles/machine-learning/v1/how-to-debug-visual-studio-code.md

@@ -369,7 +369,7 @@ Local web service deployments require a working Docker installation on your loca
 
 1. To configure VS Code to communicate with the Docker image, create a new debug configuration:
 
-    1. From VS Code, select the __Debug__ menu in the __Run__ extention and then select __Open configurations__. A file named __launch.json__ opens.
+    1. From VS Code, select the __Debug__ menu in the __Run__ extension and then select __Open configurations__. A file named __launch.json__ opens.
 
     1. In the __launch.json__ file, find the __"configurations"__ item (the line that contains `"configurations": [`), and insert the following text after it. 
 
@@ -509,7 +509,7 @@ Local web service deployments require a working Docker installation on your loca
 
     This command attaches your `score.py` locally to the one in the container. Therefore, any changes made in the editor are automatically reflected in the container
 
-2. For a better experience, you can go into the container with a new VS Code interface. Select the `Docker` extention from the VS Code side bar, find your local container created, in this documentation its `debug:1`. Right-click this container and select `"Attach Visual Studio Code"`, then a new VS Code interface will be opened automatically, and this interface shows the inside of your created container.
+2. For a better experience, you can go into the container with a new VS Code interface. Select the `Docker` extension from the VS Code side bar, find your local container created, in this documentation its `debug:1`. Right-click this container and select `"Attach Visual Studio Code"`, then a new VS Code interface will be opened automatically, and this interface shows the inside of your created container.
 
     ![The container VS Code interface](../media/how-to-troubleshoot-deployment/container-interface.png)
 
@@ -522,7 +522,7 @@ Local web service deployments require a working Docker installation on your loca
 
     ![The container run console output](../media/how-to-troubleshoot-deployment/container-run.png)
 
-4. To attach VS Code to debugpy inside the container, open VS Code, and use the F5 key or select __Debug__. When prompted, select the __Azure Machine Learning Deployment: Docker Debug__ configuration. You can also select the __Run__ extention icon from the side bar, the __Azure Machine Learning Deployment: Docker Debug__ entry from the Debug dropdown menu, and then use the green arrow to attach the debugger.
+4. To attach VS Code to debugpy inside the container, open VS Code, and use the F5 key or select __Debug__. When prompted, select the __Azure Machine Learning Deployment: Docker Debug__ configuration. You can also select the __Run__ extension icon from the side bar, the __Azure Machine Learning Deployment: Docker Debug__ entry from the Debug dropdown menu, and then use the green arrow to attach the debugger.
 
     ![The debug icon, start debugging button, and configuration selector](../media/how-to-troubleshoot-deployment/start-debugging.png)
     

articles/machine-learning/v1/how-to-monitor-datasets.md

@@ -194,7 +194,7 @@ As described later, a dataset monitor runs at a set frequency (daily, weekly, mo
 The **backfill** function runs a backfill job, for a specified start and end date range. A backfill job fills in expected missing data points in a data set, as a way to ensure data accuracy and completeness.
 
 > [!NOTE]
-> Azure Machine Learning model monitoring doesn't support manual **backfill** function, if you want to redo the model monitor for a specif time range, you can create another model monitor for that specific time range.
+> Azure Machine Learning model monitoring doesn't support manual **backfill** function, if you want to redo the model monitor for a specific time range, you can create another model monitor for that specific time range.
 
 # [Python SDK](#tab/python)
 <a name="sdk-monitor"></a>