hud-python

import os from hud import Environment from hud.agents import create_agent # Ensure your HUD_API_KEY is set as an environment variable # Example: export HUD_API_KEY="your_api_key_here" hud_api_key = os.environ.get('HUD_API_KEY', '') # Define an environment env = Environment("my-first-env") # Define a scenario using a tool @env.tool() def add(a: int, b: int) -> int: """Adds two numbers.""" return a + b @env.scenario("sum-check") async def sum_check(num1: int, num2: int): # Prompt the agent to use the 'add' tool answer = yield f"What is the sum of {num1} and {num2}? Use the 'add' tool." correct = num1 + num2 # Score the agent's answer yield 1.0 if str(correct) in str(answer) else 0.0 async def run_evaluation(): # Create a task for the scenario task = env("sum-check", num1=5, num2=7) # Create an agent (e.g., using a model via HUD's gateway) agent = create_agent("gpt-4o") # or "claude-sonnet-4-5", etc. print(f"Running task: {task.scenario_slug} with {agent.model}") async with hud.eval(task) as ctx: result = await agent.run(ctx) print(f"Agent response: {result.response}") print(f"Reward: {result.reward}") if __name__ == "__main__": import asyncio if not hud_api_key: print("Error: HUD_API_KEY environment variable not set. Please set it to run the quickstart.") else: asyncio.run(run_evaluation())