使用 openevals 包运行评估

pip install -U openevals

import pytest
from langsmith import testing as t
from openevals.llm import create_llm_as_judge
from openevals.prompts import CORRECTNESS_PROMPT

correctness_evaluator = create_llm_as_judge(
    prompt=CORRECTNESS_PROMPT,
    feedback_key="correctness",
    model="openai:o3-mini",
)

# 你的应用程序的模拟替代品
def my_llm_app(inputs: dict) -> str:
    return "Doodads have increased in price by 10% in the past year."

@pytest.mark.langsmith
def test_correctness():
    inputs = "How much has the price of doodads changed in the past year?"
    reference_outputs = "The price of doodads has decreased by 50% in the past year."
    outputs = my_llm_app(inputs)

    t.log_inputs({"question": inputs})
    t.log_outputs({"answer": outputs})
    t.log_reference_outputs({"answer": reference_outputs})

    correctness_evaluator(
        inputs=inputs,
        outputs=outputs,
        reference_outputs=reference_outputs
    )

from langsmith import Client
from openevals.llm import create_llm_as_judge
from openevals.prompts import CONCISENESS_PROMPT

client = Client()
conciseness_evaluator = create_llm_as_judge(
    prompt=CONCISENESS_PROMPT,
    feedback_key="conciseness",
    model="openai:o3-mini",
)

experiment_results = client.evaluate(
    # 这是一个虚拟的目标函数，请替换为你实际的基于 LLM 的系统
    lambda inputs: "What color is the sky?",
    data="Sample dataset",
    evaluators=[
        conciseness_evaluator
    ]
)