Async Basic Streaming Agent

Code

cookbook/models/litellm/async_basic_stream.py

import asyncio

from agno.agent import Agent
from agno.models.litellm import LiteLLM

openai_agent = Agent(
    model=LiteLLM(
        id="gpt-5-mini",
        name="LiteLLM",
    ),
    markdown=True,
)

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

Usage

1. Create a virtual environment

   Open the Terminal and create a python virtual environment.

   Mac

   python3 -m venv .venv
   source .venv/bin/activate
   
2. Set your API key

   export LITELLM_API_KEY=xxx
   
3. Install libraries

   pip install -U litellm agno
   
4. Run Agent

   Mac

   python cookbook/models/litellm/async_basic_stream.py