Outputs

Constructor options and outputs for evaluators using the Python SDK.

Once you’ve configured your evaluator, you can start evaluating text inputs for grade level appropriateness:

example.py

from learning_commons_evaluators import (
  GradeLevelAppropriatenessEvaluator,
  GradeLevelAppropriatenessEvaluationInput,
  GooglePromptProviderConfig,
  create_config,
)

# Create evaluator config
# NOTE: Telemetry is not yet implemented in v0.2.0
config = create_config(
  google_llm_provider_config=GooglePromptProviderConfig(api_key="your-google-key"),
  telemetry_partner_id="your-learning-commons-api-key",
)

# Instantiate evaluator
evaluator = GradeLevelAppropriatenessEvaluator(config)

# Evaluate text for grade level appropriateness
result = evaluator.evaluate(
  GradeLevelAppropriatenessEvaluationInput(text="The cat's out of the bag now.")
)

Literacy evaluators

The literacy evaluators have the following output fields.

Field	Type	Description
answer	EvaluationAnswer ↗	Complexity score returned by the evaluation
explanation	EvaluationExplanation ↗	Reasoning for the complexity score and evaluator-specific fields (explanation.details – see table below)
metadata	EvaluationMetadata ↗	Evaluation run metadata like timing, status, token usage, and per-step details

The explanation.details field includes detailed internal analysis data specific to that evaluator.

Evaluator	explanation.details description	explanation.details type
Grade Level Appropriateness  v0.2.0	Output fields	GradeLevelAppropriatenessInternal ↗
Vocabulary	Output fields	VocabularyComplexityOutput
Conventionality	Output fields	ConventionalityOutput