Evaluations 도입

# 의존성 설치 및 임포트
!pip install wandb weave openai -q

import os
from getpass import getpass

from openai import OpenAI
from pydantic import BaseModel

import weave

# 🔑 API 키 설정
# 이 셀을 실행하면 `getpass`를 통해 API 키 입력을 요청하며, 터미널에는 표시되지 않습니다.
#####
print("---")
print(
    "다음 링크에서 W&B API 키를 생성하세요: https://wandb.ai/settings#apikeys"
)
os.environ["WANDB_API_KEY"] = getpass("W&B API 키를 입력하세요: ")
print("---")
print("다음 링크에서 OpenAI API 키를 생성할 수 있습니다: https://platform.openai.com/api-keys")
os.environ["OPENAI_API_KEY"] = getpass("OpenAI API 키를 입력하세요: ")
print("---")
#####

# 🏠 W&B 프로젝트 이름을 입력하세요
weave_client = weave.init("MY_PROJECT_NAME")  # 🐝 사용자의 W&B 프로젝트 이름

# 1. Weave 모델 구성
class FruitExtract(BaseModel):
    fruit: str
    color: str
    flavor: str

class ExtractFruitsModel(weave.Model):
    model_name: str
    prompt_template: str

    @weave.op()
    def predict(self, sentence: str) -> dict:
        client = OpenAI()

        response = client.beta.chat.completions.parse(
            model=self.model_name,
            messages=[
                {
                    "role": "user",
                    "content": self.prompt_template.format(sentence=sentence),
                }
            ],
            response_format=FruitExtract,
        )
        result = response.choices[0].message.parsed
        return result

model = ExtractFruitsModel(
    name="gpt4o",
    model_name="gpt-4o",
    prompt_template='Extract fields ("fruit": <str>, "color": <str>, "flavor": <str>) as json, from the following text : {sentence}',
)

# 2. 샘플 수집
sentences = [
    "There are many fruits that were found on the recently discovered planet Goocrux. There are neoskizzles that grow there, which are purple and taste like candy.",
    "Pounits are a bright green color and are more savory than sweet.",
    "Finally, there are fruits called glowls, which have a very sour and bitter taste which is acidic and caustic, and a pale orange tinge to them.",
]
labels = [
    {"fruit": "neoskizzles", "color": "purple", "flavor": "candy"},
    {"fruit": "pounits", "color": "green", "flavor": "savory"},
    {"fruit": "glowls", "color": "orange", "flavor": "sour, bitter"},
]
examples = [
    {"id": "0", "sentence": sentences[0], "target": labels[0]},
    {"id": "1", "sentence": sentences[1], "target": labels[1]},
    {"id": "2", "sentence": sentences[2], "target": labels[2]},
]

# 3. 평가를 위한 스코어링 함수 정의
@weave.op()
def fruit_name_score(target: dict, output: FruitExtract) -> dict:
    target_flavors = [f.strip().lower() for f in target["flavor"].split(",")]
    output_flavors = [f.strip().lower() for f in output.flavor.split(",")]
    # 타겟 풍미가 출력 풍미에 포함되어 있는지 확인
    matches = any(tf in of for tf in target_flavors for of in output_flavors)
    return {"correct": matches}

# 4. 평가 실행
evaluation = weave.Evaluation(
    name="fruit_eval",
    dataset=examples,
    scorers=[fruit_name_score],
)
await evaluation.evaluate(model)