Skip to main content
此示例展示了一个评估,它运行提供的 agent 并使用提供的输入,然后评估 agent 提供的答案。

代码

from typing import Optional

from agno.agent import Agent
from agno.eval.accuracy import AccuracyEval, AccuracyResult
from agno.models.openai import OpenAIChat
from agno.tools.calculator import CalculatorTools

evaluation = AccuracyEval(
    model=OpenAIChat(id="o4-mini"),
    agent=Agent(
        model=OpenAIChat(id="gpt-4o-mini"),
        tools=[CalculatorTools(factorial=True)],
    ),
    input="What is 10!?",
    expected_output="3628800",
)

result: Optional[AccuracyResult] = evaluation.run(print_results=True)
assert result is not None and result.avg_score >= 8