Merge pull request #6004 from MicrosoftDocs/main

Auto Publish – main to live - 2025-07-11 22:03 UTC

Author: learn-build-service-prod[bot]

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

@@ -1222,6 +1222,11 @@
           "source_path_from_root": "/articles/ai-foundry/openai/context/context.json",
           "redirect_url": "/azure/ai-foundry/context/context",
           "redirect_document_id": false
+        },
+        {
+          "source_path_from_root": "/articles/ai-foundry/agents/concepts/agent-catalog.md",
+          "redirect_url": "/azure/ai-foundry/agents/overview",
+          "redirect_document_id": false
         }
     ]
 }

articles/ai-foundry/agents/concepts/agent-catalog.md

@@ -6,7 +6,7 @@ services: cognitive-services
 manager: nitinme
 ms.service: azure
 ms.topic: how-to
-ms.date: 06/04/2025
+ms.date: 07/11/2025
 author: aahill
 ms.author: aahi
 recommendations: false
@@ -237,7 +237,6 @@ To create a multi-agent setup, follow these steps:
     project_client = AIProjectClient(
     endpoint=os.environ["PROJECT_ENDPOINT"],
     credential=DefaultAzureCredential(),
-    api_version="latest",
     )
     ```
 

articles/ai-foundry/agents/how-to/connected-agents.md

@@ -6,7 +6,7 @@ services: cognitive-services
 manager: nitinme
 ms.service: azure-ai-agent-service
 ms.topic: how-to
-ms.date: 06/30/2025
+ms.date: 07/11/2025
 author: aahill
 ms.author: aahi
 ms.custom: azure-ai-agents
@@ -48,8 +48,7 @@ project_endpoint = os.environ["PROJECT_ENDPOINT"]
 # Initialize the AIProjectClient
 project_client = AIProjectClient(
     endpoint=project_endpoint,
-    credential=DefaultAzureCredential(exclude_interactive_browser_credential=False),
-    api_version="latest",
+    credential=DefaultAzureCredential(exclude_interactive_browser_credential=False)
 )
 ```
 

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

@@ -6,7 +6,7 @@ services: azure-ai-agent-service
 manager: nitinme
 ms.service: azure-ai-agent-service
 ms.topic: how-to
-ms.date: 05/20/2025
+ms.date: 07/11/2025
 author: aahill
 ms.author: aahi
 ms.custom: azure-ai-agents
@@ -101,8 +101,7 @@ Next, create an AI project client and then create an agent, attaching the Azure
 # Initialize the AIProjectClient
 project_client = AIProjectClient(
     endpoint=os.environ["PROJECT_ENDPOINT"],
-    credential=DefaultAzureCredential(),
-    api_version="latest",
+    credential=DefaultAzureCredential()
 )
 # Create an agent with the Azure Function tool
 agent = project_client.agents.create_agent(

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

@@ -6,7 +6,7 @@ services: cognitive-services
 manager: nitinme
 ms.service: azure-ai-agent-service
 ms.topic: how-to
-ms.date: 06/17/2025
+ms.date: 07/11/2025
 author: aahill
 ms.author: aahi
 zone_pivot_groups: selection-bing-grounding-code
@@ -64,8 +64,7 @@ project_endpoint = os.environ["PROJECT_ENDPOINT"]  # Ensure the PROJECT_ENDPOINT
 # Create an AIProjectClient instance
 project_client = AIProjectClient(
     endpoint=project_endpoint,
-    credential=DefaultAzureCredential(),  # Use Azure Default Credential for authentication
-    api_version="latest",
+    credential=DefaultAzureCredential()  # Use Azure Default Credential for authentication
 )
 ```
 

articles/ai-foundry/agents/how-to/tools/bing-code-samples.md

@@ -6,7 +6,7 @@ services: cognitive-services
 manager: nitinme
 ms.service: azure-ai-agent-service
 ms.topic: how-to
-ms.date: 07/02/2025
+ms.date: 07/11/2025
 author: aahill
 ms.author: aahi
 zone_pivot_groups: selection-bing-grounding-code
@@ -58,8 +58,7 @@ project_endpoint = os.environ["PROJECT_ENDPOINT"]  # Ensure the PROJECT_ENDPOINT
 # Initialize the AIProjectClient
 project_client = AIProjectClient(
     endpoint=project_endpoint,
-    credential=DefaultAzureCredential(exclude_interactive_browser_credential=False),  # Use Azure Default Credential for authentication
-    api_version="latest",
+    credential=DefaultAzureCredential(exclude_interactive_browser_credential=False)  # Use Azure Default Credential for authentication
 )
 ```
 

articles/ai-foundry/agents/how-to/tools/file-search-upload-files.md

@@ -6,7 +6,7 @@ services: cognitive-services
 manager: nitinme
 ms.service: azure-ai-agent-service
 ms.topic: how-to
-ms.date: 06/30/2025
+ms.date: 07/11/2025
 author: aahill
 ms.author: aahi
 zone_pivot_groups: selection-function-calling
@@ -18,7 +18,8 @@ ms.custom: azure-ai-agents
 Azure AI Agents supports function calling, which allows you to describe the structure of functions to an agent and then return the functions that need to be called along with their arguments.
 
 > [!NOTE]
-> Runs expire 10 minutes after creation. Be sure to submit your tool outputs before the expiration.
+> * Runs expire 10 minutes after creation. Be sure to submit your tool outputs before the expiration.
+> * Although function calling isn't supported in the Azure AI Foundry portal, agents will appear in the portal after creation. Agents run in the portal won't perform function calling.
 
 ### Usage support
 
@@ -77,8 +78,7 @@ project_endpoint = os.environ["PROJECT_ENDPOINT"]
 # Initialize the AIProjectClient
 project_client = AIProjectClient(
     endpoint=project_endpoint,
-    credential=DefaultAzureCredential(),
-    api_version="latest",
+    credential=DefaultAzureCredential()
 )
 
 # Initialize the FunctionTool with user-defined functions

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

@@ -6,7 +6,7 @@ services: cognitive-services
 manager: nitinme
 ms.service: azure-ai-agent-service
 ms.topic: how-to
-ms.date: 05/07/2025
+ms.date: 07/11/2025
 author: aahill
 ms.author: aahi
 ms.reviewer: umangsehgal
@@ -68,8 +68,7 @@ from azure.identity import DefaultAzureCredential
 # Initialize the AIProjectClient
 project_client = AIProjectClient(
     endpoint=os.environ["PROJECT_ENDPOINT"],
-    credential=DefaultAzureCredential(),
-    api_version="latest",
+    credential=DefaultAzureCredential()
 )
 ```
 

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

@@ -4,7 +4,7 @@ author: aahill
 ms.author: aahi
 ms.service: azure-ai-agent-service
 ms.topic: include
-ms.date: 01/21/2025
+ms.date: 07/11/2025
 ---
 
 ## Prerequisites
@@ -38,7 +38,7 @@ To create an account and project in Azure AI Foundry, follow these steps:
     1. The gpt-4o model will automatically be deployed
     1. A default agent will be created
 
-1. Once complete, you will land directly in the agent playground and you can start creating agents.
+1. Once complete, you will land directly in the agent playground and you can start creating agents. You can give your agent instructions on what to do and how to do it. For example: *"You are a helpful agent that can answer questions about geography."* Then you can start chatting with your agent.
 
     :::image type="content" source="../media\quickstart\agent-playground.png" alt-text="Screenshot of the agent playground." lightbox="../media\quickstart\agent-playground.png":::