Overview

This exercise demonstrates how to create an AI agent using Azure AI Foundry with custom function tools. The agent collects details of a technical issue and generates a support ticket.

Steps & Configuration Details

1. Create an Azure AI Foundry Project

  • Open Azure AI Foundry portal (https://ai.azure.com) and sign in.
  • Select Create an agent.
  • Configuration Items:
    • Azure AI Foundry Resource: A valid name.
    • Subscription: Your Azure subscription.
    • Resource Group: Select or create a resource group.
    • Region: Choose any AI Services-supported location.
    • Project Name: A unique name.

After creation, the Agents playground opens automatically, with a GPT-4o base model deployed.

2. Clone the Repository

  • Open Azure Portal (https://portal.azure.com).
  • Launch Azure Cloud Shell (PowerShell environment).
  • Clone the repository:
    rm -r ai-agents -f
git clone https://github.com/MicrosoftLearning/mslearn-ai-agents ai-agents
  • Navigate to the correct folder:
    cd ai-agents/Labfiles/03-ai-agent-functions/Python
  • Install dependencies:
    python -m venv labenv
./labenv/bin/Activate.ps1
pip install -r requirements.txt azure-ai-projects
  • Open the configuration file:
    code .env
  • Update Configuration Values:
    • Project Endpoint (copied from Azure AI Foundry portal).
  • Save the configuration file.

3. Define a Custom Function

  • Open the function code file:
    code user_functions.py
  • Add the function to generate a support ticket:
    # Create a function to submit a support ticket
def submit_support_ticket(email_address: str, description: str) -> str:
    script_dir = Path(__file__).parent
    ticket_number = str(uuid.uuid4()).replace('-', '')[:6]
    file_name = f"ticket-{ticket_number}.txt"
    file_path = script_dir / file_name
    text = f"Support ticket: {ticket_number}\nSubmitted by: {email_address}\nDescription:\n{description}"
    file_path.write_text(text)
    message_json = json.dumps({
        "message": f"Support ticket {ticket_number} submitted. The ticket file is saved as {file_name}"
    })
    return message_json
  • Define the callable function set:
    # Define a set of callable functions
user_functions: Set[Callable[..., Any]] = {submit_support_ticket}
  • Save the file.

4. Implement the AI Agent

  • Open the agent code file:
    code agent.py
  • Add references:
    from azure.identity import DefaultAzureCredential
from azure.ai.agents import AgentsClient
from azure.ai.agents.models import FunctionTool, ToolSet, ListSortOrder, MessageRole
from user_functions import user_functions
  • Connect to the Agent client:
    agent_client = AgentsClient(
    endpoint=project_endpoint,
    credential=DefaultAzureCredential(
        exclude_environment_credential=True,
        exclude_managed_identity_credential=True
    )
)
  • Define the agent with function tools:
    with agent_client:
    functions = FunctionTool(user_functions)
    toolset = ToolSet()
    toolset.add(functions)
    agent_client.enable_auto_function_calls(toolset)
    agent = agent_client.create_agent(
        model=model_deployment,
        name="support-agent",
        instructions="""You are a technical support agent. When a user has a technical issue, you get their email address and a description of the issue. Then you use those values to submit a support ticket using the function available to you. If a file is saved, tell the user the file name.""",
        toolset=toolset
    )
    thread = agent_client.threads.create()
    print(f"You're chatting with: {agent.name} ({agent.id})")
  • Send a prompt to the agent:
    message = agent_client.messages.create(
    thread_id=thread.id,
    role="user",
    content=user_prompt
)
run = agent_client.runs.create_and_process(thread_id=thread.id, agent_id=agent.id)
  • Check for errors:
    if run.status == "failed":
    print(f"Run failed: {run.last_error}")
  • Retrieve the latest response:
    last_msg = agent_client.messages.get_last_message_text_by_role(
    thread_id=thread.id,
    role=MessageRole.AGENT,
)
if last_msg:
    print(f"Last Message: {last_msg.text.value}")
  • Get conversation history:
    print("\nConversation Log:\n")
messages = agent_client.messages.list(thread_id=thread.id, order=ListSortOrder.ASCENDING)
for message in messages:
    if message.text_messages:
        last_msg = message.text_messages[-1]
        print(f"{message.role}: {last_msg.text.value}\n")
  • Clean up:
    agent_client.delete_agent(agent.id)
print("Deleted agent")

5. Run the AI Agent

  • Sign into Azure:
    az login
  • Run the application:
    python agent.py
  • Example prompt:
    I have a technical problem.
  • The agent should request an email address and issue description.
  • Provide an email (e.g., [email protected]).
  • Submit an issue description:
    My computer won't start.
  • The agent should generate a support ticket file.

6. Clean Up

  • Delete Azure resources to avoid unnecessary costs:

Related Posts