如何定义代码评估器 - 以编程方式使用文档

代码评估器是接收数据集示例和生成的应用输出，并返回一个或多个指标的函数。这些函数可以直接传入 evaluate() 或 aevaluate() 函数。

基本示例

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]
)

const correct = async ({ outputs, referenceOutputs }: {
  outputs: Record<string, any>;
  referenceOutputs?: Record<string, any>;
}): Promise => {
  const score = outputs?.answer === referenceOutputs?.answer;
  return { key: "correct", score };
}

评估器参数

代码评估器函数必须具有特定的参数名称。它们可以接受以下任意参数的子集：

* run: Run：完整的运行对象，该对象由应用程序根据给定示例生成。
* example: Example：完整的数据集示例，包括示例输入、输出（如果有）和元数据（如果有）。
* inputs: dict：对应数据集中单个示例的输入字典。
* outputs: dict：由应用程序根据给定 inputs.
* reference_outputs/referenceOutputs: dict：与示例关联的参考输出字典（如果有）。

对于大多数用例，你只需要 inputs, outputs，和 reference_outputs. run 和 example 仅在你需要应用程序实际输入和输出之外的额外跟踪或示例元数据时有用。

When using JS/TS these should all be passed in as part of a single object argument.

评估器输出

代码评估器应返回以下类型之一：

Python and JS/TS

* dict：以下形式的字典 {"score" | "value": ..., "key": ...} 允许你自定义指标类型（"score"表示数值，"value"表示分类）和指标名称。例如，如果你想将整数记录为分类指标，这将很有用。

仅 Python

* int | float | bool：这被解释为连续指标，可以进行平均、排序等。函数名用作指标名称。
* str：这被解释为分类指标。函数名用作指标名称。
* list[dict]：使用单个函数返回多个指标。

更多示例

要求 langsmith>=0.2.0

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-5.4-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]
)

// Type definitions
interface AppInputs {
    question: string;
}

interface AppOutputs {
    answer: string;
    reasoning: string;
}

interface Response {
    reasoning_is_valid: boolean;
}

// Old signature evaluator
function correctOldSignature(run: Run, example: Example) {
    return {
        key: "correct",
        score: run.outputs?.["answer"] === example.outputs?.["answer"],
    };
}

// Output-only evaluator
function concision({ outputs }: { outputs: AppOutputs }) {
    return {
        key: "concision",
        score: Math.min(Math.floor(outputs.answer.length / 1000), 4) + 1,
    };
}

// LLM-as-judge evaluator
const openai = new OpenAI();

async function validReasoning({
    inputs,
    outputs
}: {
    inputs: AppInputs;
    outputs: AppOutputs;
}) {
    const 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.`;

    const msg = `Question: ${inputs.question}
Answer: ${outputs.answer}
Reasoning: ${outputs.reasoning}`;

    const response = await openai.chat.completions.create({
        model: "gpt-4",
        messages: [
            { role: "system", content: instructions },
            { role: "user", content: msg }
        ],
        response_format: { type: "json_object" },
        functions: [{
            name: "parse_response",
            parameters: {
                type: "object",
                properties: {
                    reasoning_is_valid: {
                        type: "boolean",
                        description: "Whether the reasoning is valid"
                    }
                },
                required: ["reasoning_is_valid"]
            }
        }]
    });

    const parsed = JSON.parse(response.choices[0].message.content ?? "{}") as Response;
    return {
        key: "valid_reasoning",
        score: parsed.reasoning_is_valid ? 1 : 0
    };
}

// Example application
function dummyApp(inputs: AppInputs): AppOutputs {
    return {
        answer: "hmm i'm not sure",
        reasoning: "i didn't understand the question"
    };
}

const results = await evaluate(dummyApp, {
    data: "dataset_name",
    evaluators: [correctOldSignature, concision, validReasoning],
    client: new Client()
});

基本示例

评估器参数

评估器输出

更多示例

相关