Team with Exponential Backoff

This example demonstrates how to configure a team with exponential backoff retry logic. When agents encounter errors or rate limits, the team will automatically retry with increasing delays between attempts.

Code

cookbook/examples/teams/basic/team_exponential_backoff.py

from agno.agent import Agent
from agno.team import Team
from agno.tools.duckduckgo import DuckDuckGoTools

# Create a research team
team = Team(
    members=[
        Agent(
            name="Sarah",
            role="Data Researcher",
            tools=[DuckDuckGoTools()],
            instructions="Focus on gathering and analyzing data",
        ),
        Agent(
            name="Mike",
            role="Technical Writer",
            instructions="Create clear, concise summaries",
        ),
    ],
    retries=3,
    exponential_backoff=True,
)

team.print_response(
    "Search for latest news about the latest AI models",
    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. Install required libraries

   pip install agno ddgs
   
3. Set environment variables

   export OPENAI_API_KEY=****
   
4. Run the agent

   python cookbook/examples/teams/basic/team_exponential_backoff.py