评估聊天机器人

export LANGSMITH_TRACING="true"
export LANGSMITH_API_KEY="<Your LangSmith API key>"
export OPENAI_API_KEY="<Your OpenAI API key>"

from langsmith import Client

client = Client()

# 定义数据集：这些是您的测试用例
dataset_name = "QA Example Dataset"
dataset = client.create_dataset(dataset_name)

client.create_examples(
    dataset_id=dataset.id,
    examples=[
        {
            "inputs": {"question": "What is LangChain?"},
            "outputs": {"answer": "A framework for building LLM applications"},
        },
        {
            "inputs": {"question": "What is LangSmith?"},
            "outputs": {"answer": "A platform for observing and evaluating LLM applications"},
        },
        {
            "inputs": {"question": "What is OpenAI?"},
            "outputs": {"answer": "A company that creates Large Language Models"},
        },
        {
            "inputs": {"question": "What is Google?"},
            "outputs": {"answer": "A technology company known for search"},
        },
        {
            "inputs": {"question": "What is Mistral?"},
            "outputs": {"answer": "A company that creates Large Language Models"},
        }
    ]
)

import openai
from langsmith import wrappers

openai_client = wrappers.wrap_openai(openai.OpenAI())

eval_instructions = "You are an expert professor specialized in grading students' answers to questions."

def correctness(inputs: dict, outputs: dict, reference_outputs: dict) -> bool:
    user_content = f"""You are grading the following question:
{inputs['question']}
Here is the real answer:
{reference_outputs['answer']}
You are grading the following predicted answer:
{outputs['response']}
Respond with CORRECT or INCORRECT:
Grade:"""
    response = openai_client.chat.completions.create(
        model="gpt-5.4-mini",
        temperature=0,
        messages=[
            {"role": "system", "content": eval_instructions},
            {"role": "user", "content": user_content},
        ],
    ).choices[0].message.content
    return response == "CORRECT"

def concision(outputs: dict, reference_outputs: dict) -> bool:
    return int(len(outputs["response"]) < 2 * len(reference_outputs["answer"]))

default_instructions = "Respond to the users question in a short, concise manner (one short sentence)."

def my_app(question: str, model: str = "gpt-5.4-mini", instructions: str = default_instructions) -> str:
    return openai_client.chat.completions.create(
        model=model,
        temperature=0,
        messages=[
            {"role": "system", "content": instructions},
            {"role": "user", "content": question},
        ],
    ).choices[0].message.content

def ls_target(inputs: str) -> dict:
    return {"response": my_app(inputs["question"])}

experiment_results = client.evaluate(
    ls_target, # 您的 AI 系统
    data=dataset_name, # 要预测和评分的数据
    evaluators=[concision, correctness], # 用于对结果评分的评估器
    experiment_prefix="openai-4o-mini", # 实验名称的前缀，以便轻松识别
)

def ls_target_v2(inputs: str) -> dict:
    return {"response": my_app(inputs["question"], model="gpt-4-turbo")}

experiment_results = client.evaluate(
    ls_target_v2,
    data=dataset_name,
    evaluators=[concision, correctness],
    experiment_prefix="openai-4-turbo",
)

instructions_v3 = "Respond to the users question in a short, concise manner (one short sentence). Do NOT use more than ten words."

def ls_target_v3(inputs: str) -> dict:
    response = my_app(
        inputs["question"],
        model="gpt-4-turbo",
        instructions=instructions_v3
    )
    return {"response": response}

experiment_results = client.evaluate(
    ls_target_v3,
    data=dataset_name,
    evaluators=[concision, correctness],
    experiment_prefix="strict-openai-4-turbo",
)

def test_length_score() -> None:
    """测试长度分数至少为 80%。"""
    experiment_results = evaluate(
        ls_target, # 您的 AI 系统
        data=dataset_name, # 要预测和评分的数据
        evaluators=[concision, correctness], # 用于对结果评分的评估器
    )
    # 这将在下一个版本中清理：
    feedback = client.list_feedback(
        run_ids=[r.id for r in client.list_runs(project_name=experiment_results.experiment_name)],
        feedback_key="concision"
    )
    scores = [f.score for f in feedback]
    assert sum(scores) / len(scores) >= 0.8, "聚合分数应至少为 .8"