Skip to main content

Documentation Index

Fetch the complete documentation index at: https://polos.dev/docs/llms.txt

Use this file to discover all available pages before exploring further.

A simple agent that uses a tool to look up weather information.

​
Define a tool

from pydantic import BaseModel
from polos import tool, WorkflowContext

class WeatherInput(BaseModel):
    city: str

class WeatherOutput(BaseModel):
    city: str
    temperature: int
    condition: str

@tool(description="Get weather for a city")
async def get_weather(ctx: WorkflowContext, input: WeatherInput) -> WeatherOutput:
    # In production, call a real weather API
    return WeatherOutput(city=input.city, temperature=72, condition="Sunny")

​
Create the agent

from polos import Agent, max_steps, MaxStepsConfig

weather_agent = Agent(
    id="weather_agent",
    provider="openai",
    model="gpt-4o-mini",
    system_prompt="You are a weather assistant. Use the get_weather tool to look up weather.",
    tools=[get_weather],
    stop_conditions=[max_steps(MaxStepsConfig(limit=10))],
)

​
Run it

git clone https://github.com/polos-dev/polos.git
cd polos/python-examples/01-weather-agent
cp .env.example .env  # Add your POLOS_PROJECT_ID and OPENAI_API_KEY
uv sync
python main.py
Open http://localhost:5173 to view your agents and workflows, run them from the UI, and see execution traces. Python example on GitHub | TypeScript example on GitHub