Merge pull request #5328 from aahill/agents-doc-fixes

Agents doc fixes

Author: prmerger-automator[bot]

articles/ai-services/agents/how-to/metrics.md

@@ -1,7 +1,7 @@
 ---
 title: Monitor Azure AI Foundry Agent Service
 description: Start here to learn how to use Azure Monitor to capture and analyze metrics for your Azure AI Foundry Agent Service.
-ms.date: 03/20/2025
+ms.date: 06/02/2025
 ms.custom: horz-monitor, subject-monitoring
 ms.topic: conceptual
 author: aahill
@@ -15,6 +15,9 @@ ms.service: azure-ai-agent-service
 
 Monitoring is available for agents in a [standard agent setup](../concepts/standard-agent-setup.md).
 
+> [!IMPORTANT]
+> Monitoring support is currently limited to Azure AI Foundry hubs. Azure AI Foundry projects are not supported.
+
 ## Dashboards
 
 Azure AI Foundry Agent Service provides out-of-box dashboards. There are two key dashboards to monitor your resource: 

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

@@ -22,6 +22,8 @@ Azure AI Agents supports function calling, which allows you to describe the stru
 
 * A prepared environment. See the [overview](./azure-functions.md) article for details.
 
+> [!NOTE] 
+> You must have a [A deployed agent with the standard setup](../../environment-setup.md#choose-your-setup). The basic agent setup is not supported.
 
 ::: zone pivot="python"
 
@@ -30,38 +32,30 @@ Azure AI Agents supports function calling, which allows you to describe the stru
 
 ## Define a function for your agent to call
 
-Start by defining an Azure Function queue trigger function that will process function calls from the queue. For example this sample in Python:
+Start by defining an Azure Function queue trigger function that will process function calls from the queue. For example:
 
 ```python
-# Function to get the weather from an Azure Storage queue where the AI Agent will send function call information
-# It returns the mock weather to an output queue with the correlation id for the Foundry Agent Service to pick up the result of the function call
-@app.function_name(name="GetWeather")
-@app.queue_trigger(arg_name="msg", queue_name="input", connection="STORAGE_CONNECTION")  
-def process_queue_message(msg: func.QueueMessage) -> None:
-    logging.info('Python queue trigger function processed a queue item')
-
-    # Queue to send message to
-    queue_client = QueueClient(
-        os.environ["STORAGE_CONNECTION__queueServiceUri"],
-        queue_name="output",
-        credential=DefaultAzureCredential(),
-        message_encode_policy=BinaryBase64EncodePolicy(),
-        message_decode_policy=BinaryBase64DecodePolicy()
-    )
-
-    # Get the content of the function call message
-    messagepayload = json.loads(msg.get_body().decode('utf-8'))
-    location = messagepayload['location']
-    correlation_id = messagepayload['CorrelationId']
+app = func.FunctionApp()
+
+@app.queue_trigger(arg_name="msg", queue_name="azure-function-foo-input", connection="STORAGE_CONNECTION")
+@app.queue_output(arg_name="outputQueue", queue_name="azure-function-foo-output", connection="STORAGE_CONNECTION")  
+
+def queue_trigger(inputQueue: func.QueueMessage, outputQueue: func.Out[str]):
+    try:
+        messagepayload = json.loads(inputQueue.get_body().decode("utf-8"))
+        logging.info(f'The function receives the following message: {json.dumps(messagepayload)}')
+        location = messagepayload["location"]
+        weather_result = f"Weather is {len(location)} degrees and sunny in {location}"
+        response_message = {
+            "Value": weather_result,
+            "CorrelationId": messagepayload["CorrelationId"]
+        }
+        logging.info(f'The function returns the following message through the {outputQueue} queue: {json.dumps(response_message)}')
 
-    # Send message to queue. Sends a mock message for the weather
-    result_message = {
-        'Value': 'Weather is 74 degrees and sunny in ' + location,
-        'CorrelationId': correlation_id
-    }
-    queue_client.send_message(json.dumps(result_message).encode('utf-8'))
+        outputQueue.set(json.dumps(response_message))
 
-    logging.info(f"Sent message to output queue with message {result_message}")
+    except Exception as e:
+        logging.error(f"Error processing message: {e}")
 ```
 
 ## Configure the Azure Function tool
@@ -93,7 +87,7 @@ azure_function_tool = AzureFunctionTool(
         storage_service_endpoint=storage_service_endpoint,
     ),
     output_queue=AzureFunctionStorageQueue(  # Output queue configuration
-        queue_name="azure-function-tool-output",
+        queue_name="azure-function-foo-output",
         storage_service_endpoint=storage_service_endpoint,
     ),
 )

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

@@ -27,8 +27,9 @@ To use all features of function calling including parallel functions, you need t
 ## Prerequisites
 
 * [Azure Functions Core Tools v4.x](/azure/azure-functions/functions-run-local)
-* [A deployed agent with the standard setup](../../quickstart.md)
-    * The basic agent setup is not supported.
+* [A deployed agent with the standard setup](../../environment-setup.md#choose-your-setup)
+    > [!NOTE] 
+    > The basic agent setup is not supported.
 * [Azurite](https://github.com/Azure/Azurite)
 
 ## Prepare your local environment

articles/ai-services/agents/how-to/tools/function-calling.md

@@ -31,6 +31,7 @@ Azure AI Agents supports function calling, which allows you to describe the stru
 
 ## Define a function for your agent to call
 Start by defining a function for your agent to call. When you create a function for an agent to call, you describe its structure with any required parameters in a docstring.
+
 ```python
 import json
 import datetime
@@ -54,9 +55,15 @@ user_functions = {fetch_weather}
 
 ## Create a client and agent
 
+<!--
 In the sample below we create a client and define a `toolset` which will be used to process the functions defined in `user_functions`.
 
 `toolset`: When using the toolset parameter, you provide not only the function definitions and descriptions but also their implementations. The SDK will execute these functions within `create_and_run_process` or streaming. These functions will be invoked based on their definitions.
+-->
+
+> [!NOTE]
+> You can find a streaming example on [GitHub](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/ai/azure-ai-agents/samples/agents_streaming/sample_agents_stream_eventhandler_with_functions.py).
+
 
 ```python
 import os, time
@@ -104,7 +111,7 @@ print(f"Created message, ID: {message['id']}")
 ## Create a run and check the output
 ```python
 # Create and process a run for the agent to handle the message
-run = project_client.agents.runs.create_and_process(thread_id=thread.id, agent_id=agent.id)
+run = project_client.agents.runs.create(thread_id=thread.id, agent_id=agent.id)
 print(f"Created run, ID: {run.id}")
 
 # Poll the run status until it is completed or requires action
@@ -137,6 +144,9 @@ print("Deleted agent")
 
 ::: zone pivot="csharp"
 
+> [!NOTE]
+> You can find a streaming example on [GitHub](https://github.com/Azure/azure-sdk-for-net/blob/main/sdk/ai/Azure.AI.Agents.Persistent/samples/Sample8_PersistentAgents_FunctionsWithStreaming.md).
+
 ## Configure client and define functions
 
 First, set up the configuration using `appsettings.json` and create a `PersistentAgentsClient`. 

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

@@ -47,7 +47,7 @@ project_client = AIProjectClient(
 
 ## Register the Logic App
 
-Register the Logic App by providing its name and trigger details.
+Register the Logic App by providing its name and trigger details. You can find code for `AzureLogicAppTool` on[GitHub](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/ai/azure-ai-agents/samples/utils/user_functions.py).
 
 ```python
 from user_logic_apps import AzureLogicAppTool