Verdict

import weave
from verdict import Pipeline
from verdict.common.judge import JudgeUnit
from verdict.schema import Schema

# 프로젝트 이름으로 Weave 초기화
weave.init("verdict_demo")

# 단순한 평가 파이프라인 생성
pipeline = Pipeline()
pipeline = pipeline >> JudgeUnit().prompt("Rate the quality of this text: {source.text}")

# 샘플 데이터 생성
data = Schema.of(text="This is a sample text for evaluation.")

# 파이프라인 실행 - Weave가 자동으로 트레이스를 기록합니다
output = pipeline.run(data)

print(output)

import weave
from verdict import Pipeline
from verdict.common.judge import JudgeUnit
from verdict.schema import Schema

# 프로젝트 이름을 지정하여 Weave를 초기화합니다
weave.init("verdict_demo")

pipeline = pipeline >> JudgeUnit().prompt("Evaluate sentiment: {source.text}")

data = Schema.of(text="I love this product!")

with weave.attributes({"evaluation_type": "sentiment", "batch_id": "batch_001"}):
    output = pipeline.run(data)

print(output)

import weave
from verdict import Pipeline, Layer
from verdict.common.judge import JudgeUnit
from verdict.transform import MeanPoolUnit
from verdict.schema import Schema

# 프로젝트 이름으로 Weave 초기화
weave.init("verdict_demo")

# 여러 단계로 구성된 파이프라인 생성
pipeline = Pipeline()
pipeline = pipeline >> Layer([
    JudgeUnit().prompt("Rate coherence: {source.text}"),
    JudgeUnit().prompt("Rate relevance: {source.text}"),
    JudgeUnit().prompt("Rate accuracy: {source.text}")
], 3)
pipeline = pipeline >> MeanPoolUnit()

# 샘플 데이터
data = Schema.of(text="This is an evaluation of text quality across multiple dimensions.")

# 파이프라인 실행 - Weave가 모든 오퍼레이션을 자동으로 트레이스함
result = pipeline.run(data)

print(f"Average score: {result}")

import weave
from verdict import Pipeline
from verdict.common.judge import JudgeUnit
from verdict.util.tracing import ConsoleTracer
from verdict.schema import Schema

# 프로젝트 이름으로 Weave를 초기화합니다
weave.init("verdict_demo")

# Verdict의 기본 제공 트레이서도 그대로 사용할 수 있습니다
console_tracer = ConsoleTracer()

# Weave(자동) 트레이싱과 Console 트레이싱을 함께 사용하는 파이프라인을 생성합니다
pipeline = Pipeline(tracer=[console_tracer])  # Weave 트레이서는 자동으로 추가됩니다
pipeline = pipeline >> JudgeUnit().prompt("Evaluate: {source.text}")

data = Schema.of(text="Sample evaluation text")

# Weave와 콘솔 양쪽에 트레이스가 기록됩니다
result = pipeline.run(data)

import asyncio
import weave
from verdict import Pipeline
from verdict.common.judge import JudgeUnit
from verdict.schema import Schema

# 프로젝트 이름으로 Weave를 초기화합니다
weave.init("verdict_demo")

class TextQualityEvaluator(weave.Model):
    judge_prompt: str
    pipeline_name: str

    @weave.op()
    async def predict(self, text: str) -> dict:
        pipeline = Pipeline(name=self.pipeline_name)
        pipeline = pipeline >> JudgeUnit().prompt(self.judge_prompt)
        
        data = Schema.of(text=text)
        result = pipeline.run(data)
        
        return {
            "text": text,
            "quality_score": result.score if hasattr(result, 'score') else result,
            "evaluation_prompt": self.judge_prompt
        }

model = TextQualityEvaluator(
    judge_prompt="Rate the quality of this text on a scale of 1-10: {source.text}",
    pipeline_name="text_quality_evaluator"
)

text = "This is a well-written and informative piece of content that provides clear value to readers."

prediction = asyncio.run(model.predict(text))

# Jupyter Notebook에서는 다음을 실행하세요:
# prediction = await model.predict(text)

print(prediction)

import asyncio
import weave
from verdict import Pipeline
from verdict.common.judge import JudgeUnit
from verdict.schema import Schema

# Weave 초기화
weave.init("verdict_demo")

# 평가 모델 생성
class SentimentEvaluator(weave.Model):
    @weave.op()
    async def predict(self, text: str) -> dict:
        pipeline = Pipeline()
        pipeline = pipeline >> JudgeUnit().prompt(
            "Classify sentiment as positive, negative, or neutral: {source.text}"
        )
        
        data = Schema.of(text=text)
        result = pipeline.run(data)
        
        return {"sentiment": result}

# 테스트 데이터
texts = [
    "I love this product, it's amazing!",
    "This is terrible, worst purchase ever.",
    "The weather is okay today."
]
labels = ["positive", "negative", "neutral"]

examples = [
    {"id": str(i), "text": texts[i], "target": labels[i]}
    for i in range(len(texts))
]

# 점수화 함수
@weave.op()
def sentiment_accuracy(target: str, output: dict) -> dict:
    predicted = output.get("sentiment", "").lower()
    return {"correct": target.lower() in predicted}

model = SentimentEvaluator()

evaluation = weave.Evaluation(
    dataset=examples,
    scorers=[sentiment_accuracy],
)

scores = asyncio.run(evaluation.evaluate(model))
# Jupyter Notebook에서는 대신 다음을 실행하세요:
# scores = await evaluation.evaluate(model)

print(scores)

import weave
from verdict import Pipeline, Layer
from verdict.common.judge import JudgeUnit
from verdict.schema import Schema

weave.init("verdict_demo")

# 성능 편차가 발생할 수 있는 파이프라인 생성
pipeline = Pipeline()
pipeline = pipeline >> Layer([
    JudgeUnit().prompt("Quick evaluation: {source.text}"),
    JudgeUnit().prompt("Detailed analysis: {source.text}"),  # 더 느릴 수 있음
], 2)

data = Schema.of(text="Sample text for performance testing")

# 여러 번 실행하여 실행 시간 패턴 확인
for i in range(3):
    with weave.attributes({"run_number": i}):
        result = pipeline.run(data)

import weave
from verdict import Pipeline
from verdict.common.judge import JudgeUnit
from verdict.schema import Schema

weave.init("verdict_demo")

pipeline = Pipeline()
pipeline = pipeline >> JudgeUnit().prompt("Process: {source.invalid_field}")  # 이 부분에서 오류가 발생합니다

data = Schema.of(text="Sample text")

try:
    result = pipeline.run(data)
except Exception as e:
    print(f"Pipeline failed: {e}")
    # 오류 세부 정보는 Weave 트레이스에 캡처됩니다