dataset = [
    {"input": "What is 2+2?", "expected": "4"},
    {"input": "Capital of France?", "expected": "Paris"},
    {"input": "What color is the sky?", "expected": "blue"},
]

def task(input_text):
    response = client.chat.completions.create(
        model="gpt-4o-mini",
        messages=[{"role": "user", "content": input_text}]
    )
    return response.choices[0].message.content

from lunar.evals import exactMatch, contains

# Built-in scorer
scorer = exactMatch  # Returns 1.0 if output == expected, else 0.0

from lunar import Lunar
from lunar.evals import exactMatch, contains

client = Lunar()

result = client.evals.run(
    name="QA Test",
    dataset=[
        {"input": "What is 2+2?", "expected": "4"},
        {"input": "Capital of France?", "expected": "Paris"},
    ],
    task=lambda x: client.chat.completions.create(
        model="gpt-4o-mini",
        messages=[{"role": "user", "content": x}]
    ).choices[0].message.content,
    scorers=[exactMatch, contains],
)

# View results
print(f"Success rate: {result.summary.success_rate:.1%}")
for scorer_name, summary in result.summary.scores.items():
    print(f"{scorer_name}: mean={summary.mean:.2f}, std={summary.std_dev:.2f}")