以编程方式使用文档

运行评估需要三个主要部分：

  1. A 数据集 测试输入和预期输出。
  2. 目标函数，这是你要评估的内容。
  3. 评估器 对目标函数的输出进行评分。

本指南向你展示如何根据你要评估的应用程序部分定义目标函数。参见此处了解 如何创建数据集 和 如何定义评估器，此处查看 运行评估的端到端示例.

目标函数签名

为了在代码中评估应用程序，我们需要一种运行应用程序的方式。当使用 evaluate() (Python / JavaScript时，我们将通过传入一个 *目标函数* 参数来实现这一点。这是一个接收数据集 示例的 输入并以字典形式返回应用程序输出的函数。在这个函数中，我们可以按自己喜欢的方式调用应用程序。也可以按自己喜欢的方式格式化输出。关键是，我们定义的所有评估器函数都应该能处理目标函数中返回的输出格式。

from langsmith import Client

# 'inputs' will come from your dataset.
def dummy_target(inputs: dict) -> dict:
    return {"foo": 1, "bar": "two"}

# 'inputs' will come from your dataset.
# 'outputs' will come from your target function.
def evaluator_one(inputs: dict, outputs: dict) -> bool:
    return outputs["foo"] == 2

def evaluator_two(inputs: dict, outputs: dict) -> bool:
    return len(outputs["bar"]) < 3

client = Client()
results = client.evaluate(
    dummy_target,  # <-- target function
    data="your-dataset-name",
    evaluators=[evaluator_one, evaluator_two],
    ...
)

示例：单个 LLM 调用

from langsmith import wrappers
from openai import OpenAI

# Optionally wrap the OpenAI client to automatically
# trace all model calls.
oai_client = wrappers.wrap_openai(OpenAI())

def target(inputs: dict) -> dict:
  # This assumes your dataset has inputs with a 'messages' key.
  # You can update to match your dataset schema.
  messages = inputs["messages"]
  response = oai_client.chat.completions.create(
      messages=messages,
      model="gpt-5.4-mini",
  )
  return {"answer": response.choices[0].message.content}
const client = wrapOpenAI(new OpenAI());

// This is the function you will evaluate.
const target = async(inputs) => {
  // This assumes your dataset has inputs with a `messages` key
  const messages = inputs.messages;
  const response = await client.chat.completions.create({
      messages: messages,
      model: 'gpt-5.4-mini',
  });
  return { answer: response.choices[0].message.content };
}
from langchain.chat_models import init_chat_model

model = init_chat_model("gpt-5.4-mini")

def target(inputs: dict) -> dict:
  # This assumes your dataset has inputs with a `messages` key
  messages = inputs["messages"]
  response = model.invoke(messages)
  return {"answer": response.content}
// This is the function you will evaluate.
const target = async(inputs) => {
  // This assumes your dataset has inputs with a `messages` key
  const messages = inputs.messages;
  const model = new ChatOpenAI({ model: "gpt-5.4-mini" });
  const response = await model.invoke(messages);
  return {"answer": response.content};
}

示例：非 LLM 组件

from langsmith import traceable

# Optionally decorate with '@traceable' to trace all invocations of this function.
@traceable
def calculator_tool(operation: str, number1: float, number2: float) -> str:
  if operation == "add":
      return str(number1 + number2)
  elif operation == "subtract":
      return str(number1 - number2)
  elif operation == "multiply":
      return str(number1 * number2)
  elif operation == "divide":
      return str(number1 / number2)
  else:
      raise ValueError(f"Unrecognized operation: {operation}.")

# This is the function you will evaluate.
def target(inputs: dict) -> dict:
  # This assumes your dataset has inputs with `operation`, `num1`, and `num2` keys.
  operation = inputs["operation"]
  number1 = inputs["num1"]
  number2 = inputs["num2"]
  result = calculator_tool(operation, number1, number2)
  return {"result": result}
// Optionally wrap in 'traceable' to trace all invocations of this function.
const calculatorTool = traceable(async ({ operation, number1, number2 }) => {
// Functions must return strings
if (operation === "add") {
  return (number1 + number2).toString();
} else if (operation === "subtract") {
  return (number1 - number2).toString();
} else if (operation === "multiply") {
  return (number1 * number2).toString();
} else if (operation === "divide") {
  return (number1 / number2).toString();
} else {
  throw new Error("Invalid operation.");
}
});

// This is the function you will evaluate.
const target = async (inputs) => {
// This assumes your dataset has inputs with `operation`, `num1`, and `num2` keys
const result = await calculatorTool.invoke({
  operation: inputs.operation,
  number1: inputs.num1,
  number2: inputs.num2,
});
return { result };
}

示例：应用程序或智能体

from my_agent import agent

      # This is the function you will evaluate.
def target(inputs: dict) -> dict:
  # This assumes your dataset has inputs with a `messages` key
  messages = inputs["messages"]
  # Replace `invoke` with whatever you use to call your agent
  response = agent.invoke({"messages": messages})
  # This assumes your agent output is in the right format
  return response
// This is the function you will evaluate.
const target = async(inputs) => {
// This assumes your dataset has inputs with a `messages` key
const messages = inputs.messages;
// Replace `invoke` with whatever you use to call your agent
const response = await agent.invoke({ messages });
// This assumes your agent output is in the right format
return response;
}