rubric

from rubric.schemas import Dataset, DataQualityRule, Severity, Operator from rubric.engine import RubricEngine # Define your dataset schema rules = [ DataQualityRule( rule_id="length_check", description="Responses should be between 10 and 100 characters.", column="response", operator=Operator.LENGTH_BETWEEN, value=[10, 100], severity=Severity.HIGH, error_message="Response length out of range." ), DataQualityRule( rule_id="language_is_english", description="Responses should be in English.", column="response", operator=Operator.IS_LANGUAGE, value="en", severity=Severity.MEDIUM, error_message="Response is not in English." ) ] dataset_schema = Dataset(rules=rules) # Initialize RubricEngine with the schema rubric_engine = RubricEngine(dataset=dataset_schema) # Sample data to validate data = [ {"id": 1, "prompt": "Hello", "response": "This is a short test."}, # Valid {"id": 2, "prompt": "Another", "response": "Too short"}, # Invalid (length) {"id": 3, "prompt": "Translate", "response": "Ceci n'est pas anglais."}, # Invalid (language) {"id": 4, "prompt": "Long response", "response": "a" * 150} # Invalid (length) ] # Validate the data validation_results = rubric_engine.validate(data) for result in validation_results: print(f"ID: {result.id}, Valid: {result.is_valid}, Errors: {result.errors}") # Expected Output: # ID: 1, Valid: True, Errors: [] # ID: 2, Valid: False, Errors: ['Response length out of range.'] # ID: 3, Valid: False, Errors: ['Response is not in English.'] # ID: 4, Valid: False, Errors: ['Response length out of range.']