Skip to main content

​
Code

cookbook/11_models/meta/llama/async_basic_stream.py
import asyncio
from typing import Iterator  # noqa

from agno.agent import Agent, RunOutput  # noqa
from agno.models.meta import Llama

agent = Agent(model=Llama(id="Llama-4-Maverick-17B-128E-Instruct-FP8"), markdown=True)

# Get the response in a variable
# run_response: Iterator[RunOutputEvent] = asyncio.run(agent.arun("Share a 2 sentence horror story", stream=True))
# 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

1

Set up your virtual environment

uv venv --python 3.12
source .venv/bin/activate
2

Set your LLAMA API key

export LLAMA_API_KEY=YOUR_API_KEY
3

Install dependencies

uv pip install llama-api-client agno
4

Run Agent

python cookbook/11_models/meta/async_stream.py