pip install praisonaiagents

from praisonaiagents.eval import AccuracyEvaluator, EvalResult

evaluator = AccuracyEvaluator()
result = evaluator.evaluate(
    expected="Paris",
    actual="The capital of France is Paris."
)
print(result.score)  # 1.0

from praisonaiagents.eval import AccuracyEvaluator

evaluator = AccuracyEvaluator(
    match_type="contains",  # or "exact", "semantic"
    case_sensitive=False
)

from praisonaiagents.eval import PerformanceEvaluator

evaluator = PerformanceEvaluator()
result = evaluator.evaluate(
    latency_ms=150,
    tokens_used=500,
    cost=0.001
)

from praisonaiagents.eval import ReliabilityEvaluator

evaluator = ReliabilityEvaluator()
result = evaluator.evaluate(
    results=[result1, result2, result3],
    expected_consistency=0.9
)

from praisonaiagents.eval import CriteriaEvaluator

evaluator = CriteriaEvaluator(
    criteria=[
        "Response is professional",
        "Response is factually accurate",
        "Response is concise"
    ],
    llm="gpt-4o-mini"
)

from praisonaiagents.eval import EvalResult

result.score        # 0.0 to 1.0
result.passed       # True/False
result.details      # Detailed breakdown
result.metadata     # Additional info

from praisonaiagents.eval import AccuracyEvaluator

evaluator = AccuracyEvaluator()

# Test agent response
result = evaluator.evaluate(
    expected="42",
    actual="The answer is 42."
)

print(f"Score: {result.score}")
print(f"Passed: {result.passed}")

from praisonaiagents.eval import AccuracyEvaluator, EvalResults

evaluator = AccuracyEvaluator()

test_cases = [
    {"expected": "Paris", "actual": "Paris is the capital"},
    {"expected": "Tokyo", "actual": "The answer is Tokyo"},
]

results = evaluator.evaluate_batch(test_cases)
print(f"Average score: {results.average_score}")

from praisonaiagents.eval import CriteriaEvaluator

evaluator = CriteriaEvaluator(
    criteria=[
        "Response answers the question",
        "Response is helpful",
        "Response is accurate"
    ]
)

result = evaluator.evaluate(
    question="What is machine learning?",
    response="Machine learning is a subset of AI..."
)