如何定义代码评估器

from langsmith import evaluate

def correct(outputs: dict, reference_outputs: dict) -> bool:
    """Check if the answer exactly matches the expected answer."""
    return outputs["answer"] == reference_outputs["answer"]

def dummy_app(inputs: dict) -> dict:
    return {"answer": "hmm i'm not sure", "reasoning": "i didn't understand the question"}

results = evaluate(
    dummy_app,
    data="dataset_name",
    evaluators=[correct]
)

from langsmith import evaluate, wrappers
from langsmith.schemas import Run, Example
from openai import AsyncOpenAI
# Assumes you've installed pydantic.
from pydantic import BaseModel

# We can still pass in Run and Example objects if we'd like
def correct_old_signature(run: Run, example: Example) -> dict:
    """Check if the answer exactly matches the expected answer."""
    return {"key": "correct", "score": run.outputs["answer"] == example.outputs["answer"]}

# Just evaluate actual outputs
def concision(outputs: dict) -> int:
    """Score how concise the answer is. 1 is the most concise, 5 is the least concise."""
    return min(len(outputs["answer"]) // 1000, 4) + 1

# Use an LLM-as-a-judge
oai_client = wrappers.wrap_openai(AsyncOpenAI())

async def valid_reasoning(inputs: dict, outputs: dict) -> bool:
    """Use an LLM to judge if the reasoning and the answer are consistent."""
    instructions = """
Given the following question, answer, and reasoning, determine if the reasoning for the
answer is logically valid and consistent with question and the answer."""

    class Response(BaseModel):
        reasoning_is_valid: bool

    msg = f"Question: {inputs['question']}\nAnswer: {outputs['answer']}\nReasoning: {outputs['reasoning']}"
    response = await oai_client.beta.chat.completions.parse(
        model="gpt-4o-mini",
        messages=[{"role": "system", "content": instructions,}, {"role": "user", "content": msg}],
        response_format=Response
    )
    return response.choices[0].message.parsed.reasoning_is_valid

def dummy_app(inputs: dict) -> dict:
    return {"answer": "hmm i'm not sure", "reasoning": "i didn't understand the question"}

results = evaluate(
    dummy_app,
    data="dataset_name",
    evaluators=[correct_old_signature, concision, valid_reasoning]
)