Agent v2 samples

samples/microsoft/python/getting-started-agents/agent-client/v2/computer_use.py

@@ -0,0 +1,134 @@
+import os
+from dotenv import load_dotenv
+from azure.identity import DefaultAzureCredential
+from azure.ai.projects import AIProjectClient
+from azure.ai.projects.models import AgentReference, PromptAgentDefinition, ComputerUsePreviewTool
+
+# Import shared helper functions
+from computer_use_util import (
+    SearchState,
+    load_screenshot_assets,
+    handle_computer_action_and_take_screenshot,
+    print_final_output,
+)
+
+load_dotenv()
+
+"""Main function to demonstrate Computer Use Agent functionality."""
+# Initialize state machine
+current_state = SearchState.INITIAL
+
+# Load screenshot assets
+try:
+    screenshots = load_screenshot_assets()
+    print("Successfully loaded screenshot assets")
+except FileNotFoundError:
+    print("Failed to load required screenshot assets. Please ensure the asset files exist in ../assets/")
+    exit(1)
+
+project_client = AIProjectClient(
+    endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
+    credential=DefaultAzureCredential(),
+)
+
+with project_client:
+    # <create_agent_with_computer_use_tool>
+    computer_use_tool = ComputerUsePreviewTool(display_width=1026, display_height=769, environment="windows")
+    agent = project_client.agents.create_version(
+        agent_name="ComputerUseAgent",
+        definition=PromptAgentDefinition(
+            model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
+            instructions="""
+            You are a computer automation assistant. 
+
+            Be direct and efficient. When you reach the search results page, read and describe the actual search result titles and descriptions you can see.
+            """,
+            tools=[computer_use_tool],
+        ),
+        description="Computer automation agent with screen interaction capabilities.",
+    )
+    # </create_agent_with_computer_use_tool>
+    print(f"Agent created (id: {agent.id}, name: {agent.name}, version: {agent.version})")
+
+    openai_client = project_client.get_openai_client()
+
+    # Initial request with screenshot - start with Bing search page
+    print("Starting computer automation session (initial screenshot: cua_browser_search.png)...")
+    # <computer_use_initial_request>
+    response = openai_client.responses.create(
+        input=[
+            {
+                "role": "user",
+                "content": [
+                    {
+                        "type": "input_text",
+                        "text": "I need you to help me search for 'OpenAI news'. Please type 'OpenAI news' and submit the search. Once you see search results, the task is complete.",
+                    },
+                    {
+                        "type": "input_image",
+                        "image_url": screenshots["browser_search"]["url"],
+                        "detail": "high",
+                    },  # Start with Bing search page
+                ],
+            }
+        ],
+        extra_body={"agent": AgentReference(name=agent.name).as_dict()},
+        truncation="auto",
+    )
+    # </computer_use_initial_request>
+
+    print(f"Initial response received (ID: {response.id})")
+
+# <computer_use_interaction_loop>
+max_iterations = 10  # Allow enough iterations for completion
+iteration = 0
+
+while True:
+    if iteration >= max_iterations:
+        print(f"\nReached maximum iterations ({max_iterations}). Stopping.")
+        break
+
+    iteration += 1
+    print(f"\n--- Iteration {iteration} ---")
+
+    # Check for computer calls in the response
+    computer_calls = [item for item in response.output if item.type == "computer_call"]
+
+    if not computer_calls:
+        print_final_output(response)
+        break
+
+    # Process the first computer call
+    computer_call = computer_calls[0]
+    action = computer_call.action
+    call_id = computer_call.call_id
+
+    print(f"Processing computer call (ID: {call_id})")
+
+    # Handle the action and get the screenshot info
+    screenshot_info, current_state = handle_computer_action_and_take_screenshot(action, current_state, screenshots)
+
+    print(f"Sending action result back to agent (using {screenshot_info['filename']})...")
+
+    # Regular response with just the screenshot
+    response = openai_client.responses.create(
+        previous_response_id=response.id,
+        input=[
+            {
+                "call_id": call_id,
+                "type": "computer_call_output",
+                "output": {
+                    "type": "computer_screenshot",
+                    "image_url": screenshot_info["url"],
+                },
+            }
+        ],
+        extra_body={"agent": AgentReference(name=agent.name).as_dict()},
+        truncation="auto",
+    )
+
+    print(f"Follow-up response received (ID: {response.id})")
+# </computer_use_interaction_loop>
+
+# uncomment the following line to clean up the created agent after running the sample
+# project_client.agents.delete_version(agent_name=agent.name, agent_version=agent.version)

samples/microsoft/python/getting-started-agents/agent-client/v2/file_search.py

@@ -0,0 +1,75 @@
+from azure.identity import DefaultAzureCredential
+from azure.ai.projects import AIProjectClient
+from azure.ai.projects.models import PromptAgentDefinition, FileSearchTool
+from dotenv import load_dotenv
+import os
+
+load_dotenv()
+# Load the file to be indexed for search
+file_1 = os.path.abspath(os.path.join(os.path.dirname(__file__), "../assets/product_info.md"))
+
+project_client = AIProjectClient(
+    endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
+    credential=DefaultAzureCredential(),
+)
+
+openai_client = project_client.get_openai_client()
+
+# Create vector store for file search
+
+# <create_vector_store_basic>
+vector_store = openai_client.vector_stores.create(name="ProductInfoStore")
+print(f"Vector store created (id: {vector_store.id})")
+# </create_vector_store_basic>
+
+# Create vector store with expiration
+
+# <create_vector_store_with_expiration>
+vector_store_with_expiration = openai_client.vector_stores.create_and_poll(
+  name="Product Documentation",
+  file_ids=[file_1.id],
+  expires_after={
+      "anchor": "last_active_at",
+      "days": 7
+  }
+)
+# </create_vector_store_with_expiration>
+
+with project_client:
+    # Create agent with file search tool
+    # <create_agent_with_file_search_tool>
+    agent = project_client.agents.create_version(
+        agent_name="MyAgent",
+        definition=PromptAgentDefinition(
+            model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
+            instructions="You are a helpful assistant that can search through product information.",
+            tools=[FileSearchTool(vector_store_ids=[vector_store.id])],
+        ),
+        description="File search agent for product information queries.",
+    )
+    # </create_agent_with_file_search_tool>
+    print(f"Agent created (id: {agent.id}, name: {agent.name}, version: {agent.version})")
+
+    # Create a conversation for the agent interaction
+    conversation = openai_client.conversations.create()
+    print(f"Created conversation (id: {conversation.id})")
+
+    # Send a query to search through the uploaded file
+    response = openai_client.responses.create(
+        conversation=conversation.id,
+        input="Tell me about Contoso products",
+        extra_body={"agent": {"name": agent.name, "type": "agent_reference"}},
+    )
+    print(f"Response: {response.output_text}")
+
+    print("\nCleaning up...")
+    # <delete_vector_store>
+    openai_client.vector_stores.delete(vector_store.id)
+    print("Deleted vector store")
+    # </delete_vector_store>
+
+    # Uncomment the following lines to delete the agent after testing
+    #project_client.agents.delete_version(agent_name=agent.name, agent_version=agent.version)
+    #print("Agent deleted")
+
+

samples/microsoft/python/getting-started-agents/agent-client/v2/function_calling.py

@@ -0,0 +1,90 @@
+import os
+import json
+from dotenv import load_dotenv
+from azure.ai.projects import AIProjectClient
+from azure.ai.projects.models import PromptAgentDefinition, Tool, FunctionTool
+from azure.identity import DefaultAzureCredential
+from openai.types.responses.response_input_param import FunctionCallOutput, ResponseInputParam
+
+load_dotenv()
+
+# Define a function tool for the model to use
+# <define_function_tool>
+func_tool = FunctionTool(
+    name="get_horoscope",
+    parameters={
+        "type": "object",
+        "properties": {
+            "sign": {
+                "type": "string",
+                "description": "An astrological sign like Taurus or Aquarius",
+            },
+        },
+        "required": ["sign"],
+        "additionalProperties": False,
+    },
+    description="Get today's horoscope for an astrological sign.",
+    strict=True,
+)
+
+# Create tools list with proper typing for the agent definition
+tools: list[Tool] = [mcp_tool]
+# </define_function_tool>
+
+with project_client:
+    # Create a prompt agent with MCP tool capabilities
+    # The agent will be able to access external GitHub repositories through the MCP protocol
+    # <create_agent_with_mcp_tool>
+    agent = project_client.agents.create_version(
+        agent_name="MyAgent",
+        definition=PromptAgentDefinition(
+            model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
+            instructions="You are a helpful agent that can use MCP tools to assist users. Use the available MCP tools to answer questions and perform tasks.",
+            tools=tools,
+        ),
+    )
+    # </create_agent_with_mcp_tool>
+    print(f"Agent created (id: {agent.id}, name: {agent.name}, version: {agent.version})")
+    openai_client = project_client.get_openai_client()
+
+    # Prompt the model with tools defined
+    response = openai_client.responses.create(
+        input="What is my horoscope? I am an Aquarius.",
+        extra_body={"agent": {"name": agent.name, "type": "agent_reference"}},
+    )
+    print(f"Response output: {response.output_text}")
+
+    input_list: ResponseInputParam = []
+    # Process function calls
+    # <process_function_calls>
+    for item in response.output:
+        if item.type == "function_call":
+            if item.name == "get_horoscope":
+                # Execute the function logic for get_horoscope
+                horoscope = get_horoscope(**json.loads(item.arguments))
+
+                # Provide function call results to the model
+                input_list.append(
+                    FunctionCallOutput(
+                        type="function_call_output",
+                        call_id=item.call_id,
+                        output=json.dumps({"horoscope": horoscope}),
+                    )
+                )
+    # </process_function_calls>
+    print("Final input:")
+    print(input_list)
+    response = openai_client.responses.create(
+        input=input_list,
+        previous_response_id=response.id,
+        extra_body={"agent": {"name": agent.name, "type": "agent_reference"}},
+    )
+
+    # The model should be able to give a response!
+    print("Final output:")
+    print("\n" + response.output_text)
+
+    # Uncomment these lines to clean up resources by deleting the agent version
+    # This prevents accumulation of unused agent versions in your project
+    # project_client.agents.delete_version(agent_name=agent.name, agent_version=agent.version)
+    # print("Agent deleted")

samples/microsoft/python/getting-started-agents/agent-client/v2/image_generation.py

@@ -0,0 +1,55 @@
+import base64
+import os
+from dotenv import load_dotenv
+
+from azure.identity import DefaultAzureCredential
+from azure.ai.projects import AIProjectClient
+from azure.ai.projects.models import PromptAgentDefinition, ImageGenTool
+
+load_dotenv()
+
+project_client = AIProjectClient(
+    endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
+    credential=DefaultAzureCredential(),
+)
+
+openai_client = project_client.get_openai_client()
+
+with project_client:
+    # <create_agent_with_image_gen_tool>
+    agent = project_client.agents.create_version(
+        agent_name="MyAgent",
+        definition=PromptAgentDefinition(
+            model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
+            instructions="Generate images based on user prompts",
+            tools=[ImageGenTool(quality="low", size="1024x1024")],
+        ),
+        description="Agent for image generation.",
+    )
+    # </create_agent_with_image_gen_tool>
+    print(f"Agent created (id: {agent.id}, name: {agent.name}, version: {agent.version})")
+    response = openai_client.responses.create(
+        input="Generate an image of Microsoft logo.",
+        extra_headers={
+            "x-ms-oai-image-generation-deployment": "gpt-image-1"
+        },  # this is required at the moment for image generation
+        extra_body={"agent": {"name": agent.name, "type": "agent_reference"}},
+    )
+    print(f"Response created: {response.id}")
+    # Save the image to a file
+    # <download_generated_image>
+    image_data = [output.result for output in response.output if output.type == "image_generation_call"]
+
+    if image_data and image_data[0]:
+        print("Downloading generated image...")
+        filename = "microsoft.png"
+        file_path = os.path.abspath(filename)
+
+        with open(file_path, "wb") as f:
+            f.write(base64.b64decode(image_data[0]))
+    # </download_generated_image>
+        print(f"Image downloaded and saved to: {file_path}")
+    # uncomment the following lines to clean up the created agent after running the sample
+    #print("\nCleaning up...")
+    #project_client.agents.delete_version(agent_name=agent.name, agent_version=agent.version)
+    #print("Agent deleted")