Usage
Basic Agent
Run a GPT model through the CometAPI gateway in sync, async, and streaming modes.
Code
import asyncio
from agno.agent import Agent, RunOutput # noqa
from agno.models.cometapi import CometAPI
agent = Agent(model=CometAPI(id="gpt-5.2"), markdown=True)
# Get the response in a variable
# run: RunOutput = agent.run("Explain quantum computing in simple terms")
# print(run.content)
if __name__ == "__main__":
# --- Sync ---
agent.print_response("Explain quantum computing in simple terms")
# --- Sync + Streaming ---
agent.print_response("Explain quantum computing in simple terms", stream=True)
# --- Async ---
asyncio.run(agent.aprint_response("Share a 2 sentence horror story"))
# --- Async + Streaming ---
asyncio.run(
agent.aprint_response(
"Write a short poem about artificial intelligence", stream=True
)
)Usage
Set up your virtual environment
uv venv --python 3.12
source .venv/bin/activateSet your API key
export COMETAPI_KEY=xxxInstall dependencies
uv pip install -U agno openaiRun Agent
Save the code above as basic.py, then run:
python basic.py