Hi all,
I would like to follow this example and try to reproduce the same result but it's not possible.
https://github.com/microsoft/agent-framework/blob/main/python/samples/getting_started/workflows/_start-here/step2_agents_in_a_workflow.py
I try with the similar code but the Workflow hat final state of IDLE and therefore the outputs are blank.
import asyncio
from agent_framework import AgentRunEvent, ChatAgent, WorkflowBuilder
from agent_framework.openai import OpenAIChatClient
import os
from dotenv import load_dotenv
from agent_framework.azure import AzureOpenAIChatClient
load_dotenv()
async def main():
client = AzureOpenAIChatClient(
api_key=os.getenv("FOUNDRY_APIKEY"),
endpoint=os.getenv("FOUNDRY_ENDPOINT"),
api_version="2024-12-01-preview",
deployment_name="gpt-5-mini"
)
writer_agent = client.as_agent(
instructions="You are an excellent content writer. You create new content and edit contents based on the feedback.",
name="writer",
)
reviewer_agent = client.as_agent(
instructions=(
"You are an excellent content reviewer."
"Provide actionable feedback to the writer about the provided content."
"Provide the feedback in the most concise manner possible."
),
name="reviewer",
)
workflow = (
WorkflowBuilder()
.set_start_executor(writer_agent)
.add_edge(writer_agent, reviewer_agent)
.build()
)
events = await workflow.run(
"Create one (only one) slogan for a new electric SUV that is affordable and fun to drive."
)
for event in events:
if isinstance(event, AgentRunEvent):
print(f"{'='*60})")
print(f"{event.executor_id}:{event.data}")
print(f"{'='*60}\nWorkflow Outputs:{events.get_outputs()}")
print("Final State:", events.get_final_state())
if __name__ == "__main__":
asyncio.run(main())
I'm not sure if I do anything wrong or the framework has changed his behavior and therefore the sample is not updated anymore?
I use Microsoft Agent Framework version: 1.0.0b260116
Thank you.
Regards
Hi all,
I would like to follow this example and try to reproduce the same result but it's not possible.
https://github.com/microsoft/agent-framework/blob/main/python/samples/getting_started/workflows/_start-here/step2_agents_in_a_workflow.py
I try with the similar code but the Workflow hat final state of IDLE and therefore the outputs are blank.
I'm not sure if I do anything wrong or the framework has changed his behavior and therefore the sample is not updated anymore?
I use Microsoft Agent Framework version: 1.0.0b260116
Thank you.
Regards