Gathering Multiple Async Agents

This example demonstrates how to run multiple async agents concurrently using asyncio.gather() to generate research reports on different AI providers simultaneously.

Code

gather_agents.py

import asyncio

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.duckduckgo import DuckDuckGoTools
from rich.pretty import pprint

providers = ["openai", "anthropic", "ollama", "cohere", "google"]
instructions = [
    "Your task is to write a well researched report on AI providers.",
    "The report should be unbiased and factual.",
]


async def get_reports():
    tasks = []
    for provider in providers:
        agent = Agent(
            model=OpenAIChat(id="gpt-4"),
            instructions=instructions,
            tools=[DuckDuckGoTools()],
        )
        tasks.append(
            agent.arun(f"Write a report on the following AI provider: {provider}")
        )

    results = await asyncio.gather(*tasks)
    return results


async def main():
    results = await get_reports()
    for result in results:
        print("************")
        pprint(result.content)
        print("************")
        print("\n")


if __name__ == "__main__":
    asyncio.run(main())

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. Install libraries

   pip install -U agno openai ddgs rich
   
3. Export your OpenAI API key

   Mac/Linux

       export OPENAI_API_KEY="your_openai_api_key_here"
   
4. Create a Python file

   Create a Python file and add the above code.

   touch gather_agents.py
   
5. Run Agent

   Mac

   python gather_agents.py
   
6. Find All Cookbooks

   Explore all the available cookbooks in the Agno repository. Click the link below to view the code on GitHub:

   Agno Cookbooks on GitHub