Files
agent-framework/python/samples/02-agents/declarative/microsoft_learn_agent.py
T
Copilot fd253c0b0e Python: Move workflow-samples and agent-samples under declarative-agents directory (#5011)
* Move workflow-samples and agent-samples under declarative-agents and update all references

Agent-Logs-Url: https://github.com/microsoft/agent-framework/sessions/f70f7d19-9256-4eec-b7db-28007d74440c

Co-authored-by: sphenry <6749825+sphenry@users.noreply.github.com>

* Fix relative paths in README files inside moved directories

Agent-Logs-Url: https://github.com/microsoft/agent-framework/sessions/f70f7d19-9256-4eec-b7db-28007d74440c

Co-authored-by: sphenry <6749825+sphenry@users.noreply.github.com>

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: sphenry <6749825+sphenry@users.noreply.github.com>
Co-authored-by: Shawn Henry <shahen@microsoft.com>
2026-04-02 09:34:33 +00:00

45 lines
1.6 KiB
Python

# Copyright (c) Microsoft. All rights reserved.
import asyncio
from pathlib import Path
from agent_framework.declarative import AgentFactory
from azure.identity.aio import AzureCliCredential
from dotenv import load_dotenv
# Load environment variables from .env file
load_dotenv()
"""
This sample demonstrates creating an agent from a declarative YAML file specification.
It uses a MCP server to connect to the Microsoft Learn content and a FoundryChatClient.
The yaml also has some chat options set, such as temperature and topP.
These options do not work with newer OpenAI models, so ensure to use a compatible model such as gpt-4o-mini.
Environment variables:
- FOUNDRY_PROJECT_ENDPOINT: The endpoint URL for the Foundry project.
- FOUNDRY_MODEL: The model ID to use for the agent, make sure it is compatible with the chat options specified in
the yaml, or remove the options.
"""
async def main():
"""Create an agent from a declarative yaml specification and run it."""
# get the path
current_path = Path(__file__).parent
yaml_path = current_path.parent.parent.parent.parent / "declarative-agents" / "agent-samples" / "foundry" / "MicrosoftLearnAgent.yaml"
# create the agent from the yaml
async with (
AzureCliCredential() as credential,
AgentFactory(client_kwargs={"credential": credential}, safe_mode=False).create_agent_from_yaml_path(
yaml_path
) as agent,
):
response = await agent.run("How do I create a storage account with private endpoint using bicep?")
print("Agent response:", response.text)
if __name__ == "__main__":
asyncio.run(main())