Async Streaming Agent

Stream a WatsonX agent's response asynchronously with aprint_response.

Code

import asyncio
from typing import AsyncIterator  # noqa

from agno.agent import Agent, RunOutputEvent  # noqa
from agno.models.ibm import WatsonX

agent = Agent(
    model=WatsonX(id="mistralai/mistral-small-3-1-24b-instruct-2503"), markdown=True
)

# Get the response in a variable
# run_response: AsyncIterator[RunOutputEvent] = agent.arun("Share a 2 sentence horror story", stream=True)
# async for chunk in run_response:
#     print(chunk.content)

# Print the response in the terminal
asyncio.run(agent.aprint_response("Share a 2 sentence horror story", stream=True))

Usage

Set up your virtual environment

uv venv --python 3.12
source .venv/bin/activate

Set your API key

export IBM_WATSONX_API_KEY=xxx
export IBM_WATSONX_PROJECT_ID=xxx

Install dependencies

uv pip install -U ibm-watsonx-ai agno

Run Agent

Save the code above as basic.py, then run:

python basic.py

The agent runs asynchronously and streams the response as it's generated.