Merge pull request #6558 from MicrosoftDocs/main

Auto Publish – main to live - 2025-08-13 17:11 UTC

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

articles/ai-foundry/agents/includes/quickstart-csharp.md

@@ -92,7 +92,7 @@ client.Messages.CreateMessage(
     MessageRole.User,
     "Hi, Agent! Draw a graph for a line with a slope of 4 and y-intercept of 9.");
 
-//Have Agent beging processing user's question with some additional instructions associated with the ThreadRun.
+//Have Agent begin processing user's question with some additional instructions associated with the ThreadRun.
 ThreadRun run = client.Runs.CreateRun(
     thread.Id,
     agent.Id,

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

@@ -51,15 +51,16 @@ Set this endpoint as an environment variable named `PROJECT_ENDPOINT`.
 
 [!INCLUDE [model-name-portal](model-name-portal.md)]
 
-Save the name of your model deployment name as an environment variable named `MODEL_DEPLOYMENT_NAME`. 
+Save the name of your model deployment name as an environment variable named `MODEL_DEPLOYMENT_NAME`.
 
 ```python
 import os
+from pathlib import Path
 from azure.ai.projects import AIProjectClient
 from azure.identity import DefaultAzureCredential
 from azure.ai.agents.models import CodeInterpreterTool
 
-# Create an Azure AI Client from an endpoint, copied from your Azure AI Foundry project.
+# Create an AIProjectClient from an endpoint, copied from your Azure AI Foundry project.
 # You need to login to Azure subscription via Azure CLI and set the environment variables
 project_endpoint = os.environ["PROJECT_ENDPOINT"]  # Ensure the PROJECT_ENDPOINT environment variable is set
 
@@ -71,40 +72,51 @@ project_client = AIProjectClient(
 
 code_interpreter = CodeInterpreterTool()
 with project_client:
-    # Create an agent with the Bing Grounding tool
+    # Create an agent with the Code Interpreter tool
     agent = project_client.agents.create_agent(
         model=os.environ["MODEL_DEPLOYMENT_NAME"],  # Model deployment name
         name="my-agent",  # Name of the agent
-        instructions="You are a helpful agent",  # Instructions for the agent
+        instructions="You politely help with math questions. Use the Code Interpreter tool when asked to visualize numbers.",  # Instructions for the agent
         tools=code_interpreter.definitions,  # Attach the tool
     )
     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
+        content="Hi, Agent! Draw a graph for a line with a slope of 4 and y-intercept of 9.",  # 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)
+    run = project_client.agents.runs.create_and_process(
+        thread_id=thread.id,
+        agent_id=agent.id,
+        additional_instructions="Please address the user as Jane Doe. The user has a premium account",
+    )
     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}")
-    
+
+        # Save every image file in the message
+        for img in message.image_contents:
+            file_id = img.image_file.file_id
+            file_name = f"{file_id}_image_file.png"
+            project_client.agents.files.save(file_id=file_id, file_name=file_name)
+            print(f"Saved image file to: {Path.cwd() / file_name}")
+
     # Delete the agent when done
     project_client.agents.delete_agent(agent.id)
     print("Deleted agent")

articles/ai-foundry/concepts/fine-tuning-overview.md

@@ -72,16 +72,18 @@ Follow this link to view and download [example datasets](https://github.com/Azur
 ## Model Comparison Table
 This table provides an overview of the models available 
 
-| Model                | Modalities     | Techniques   | Strengths                        | 
-|----------------------|---------------|--------------|--------------------------------------|
+| Model                | Modalities    | Techniques   | Strengths                                                          | 
+|----------------------|---------------|--------------|--------------------------------------------------------------------|
 | GPT 4.1              | Text, Vision  | SFT, DPO     | Superior performance on sophisticated tasks, nuanced understanding |
-| GPT 4.1-mini         | Text          | SFT, DPO     | Fast iteration, cost-effective, good for simple tasks  |
-| GPT 4.1-nano         | Text          | SFT, DPO     | Fast, cost-effective, and minimal resource usage        |
-| o4-mini              | Text          | RFT          | Reasoning model suited for complex logical tasks        |
-| Phi 4                | Text          | SFT          | Cost effective option for simpler tasks                |
-| Ministral 3B         | Text          | SFT          | Low-cost option for faster iteration                   |
-| Mistral Nemo         | Text          | SFT          | Balance between size and capability                    |
-| Mistral Large (2411) | Text          | SFT          | Most capable Mistral model, better for complex tasks   |
+| GPT 4.1-mini         | Text          | SFT, DPO     | Fast iteration, cost-effective, good for simple tasks              |
+| GPT 4.1-nano         | Text          | SFT, DPO     | Fast, cost-effective, and minimal resource usage                   |
+| GPT 4o               | Text, Vision  | SFT, DPO     | Previous generation flagship model for complex tasks               |
+| GPT 4o-mini          | Text          | SFT          | Previous generation small model for simple tasks                   |
+| o4-mini              | Text          | RFT          | Reasoning model suited for complex logical tasks                   |
+| Phi 4                | Text          | SFT          | Cost effective option for simpler tasks                            |
+| Ministral 3B         | Text          | SFT          | Low-cost option for faster iteration                               |
+| Mistral Nemo         | Text          | SFT          | Balance between size and capability                                |
+| Mistral Large (2411) | Text          | SFT          | Most capable Mistral model, better for complex tasks               |
 
 ## Get Started with Fine Tuning
 

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

@@ -46,11 +46,11 @@ Azure OpenAI in Azure AI Foundry Models offers a diverse set of models with diff
 | [`GPT-5 series`](../../openai/concepts/models.md#gpt-5) | **NEW** `gpt-5`, `gpt-5-mini`, `gpt-5-nano`, `gpt-5-chat` |
 | [gpt-oss](../../openai/concepts/models.md#gpt-oss) | Open-weight reasoning models |
 | [codex-mini](../../openai/concepts/models.md#o-series-models) | Fine-tuned version of o4-mini. |  
-| [GPT-4.1 series](../../openai/concepts/models.md#gpt-41-series) | The latest model release from Azure OpenAI. |
+| [GPT-4.1 series](../../openai/concepts/models.md#gpt-41-series) | `gpt-4.1`, `gpt-4.1-mini`, `gpt-4.1-nano` |
 | [model-router](../../openai/concepts/models.md#model-router) | A model that intelligently selects from a set of underlying chat models to respond to a given prompt. |
 | [computer-use-preview](../../openai/concepts/models.md#computer-use-preview) | An experimental model trained for use with the Responses API computer use tool. |
 | [o-series models](../../openai/concepts/models.md#o-series-models) |[Reasoning models](../../openai/how-to/reasoning.md) with advanced problem solving and increased focus and capability. |
-| [GPT-4o, GPT-4o mini, and GPT-4 Turbo](../../openai/concepts/models.md#gpt-4o-and-gpt-4-turbo) | The latest, most capable Azure OpenAI models with multimodal versions, which can accept both text and images as input. |
+| [GPT-4o, GPT-4o mini, and GPT-4 Turbo](../../openai/concepts/models.md#gpt-4o-and-gpt-4-turbo) | Capable Azure OpenAI models with multimodal versions, which can accept both text and images as input. |
 | [GPT-4](../../openai/concepts/models.md#gpt-4) | A set of models that improve on GPT-3.5 and can understand and generate natural language and code. |
 | [GPT-3.5](../../openai/concepts/models.md#gpt-35) | A set of models that improve on GPT-3 and can understand and generate natural language and code. |
 | [Embeddings](../../openai/concepts/models.md#embeddings) | A set of models that can convert text into numerical vector form to facilitate text similarity. |