Async Basic Streaming Agent
Stream a LiteLLM-backed agent's response asynchronously with aprint_response().
Code
import asyncio
from agno.agent import Agent
from agno.models.litellm import LiteLLM
openai_agent = Agent(
model=LiteLLM(
id="huggingface/mistralai/Mistral-7B-Instruct-v0.2",
top_p=0.95,
),
markdown=True,
)
# Print the response in the terminal
asyncio.run(
openai_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/activateSet your API key
export LITELLM_API_KEY=xxxInstall dependencies
uv pip install -U litellm agnoRun Agent
Save the code above as basic.py, then run:
python basic.py