Quickstart

The Python SDK lets you use evaluators in your own project:

Configure and run evaluators
Understand their outputs
Customize logging and handle errors

Contact us ↗ to request additional SDK language support. You can also sign up for a Platform account ↗ to receive updates on availability.

Install the SDK

	Latest release
GitHub ↗

Install the SDK from the package registry rather than cloning the evaluators repository ↗. The published package is versioned, so you can pick up fixes and new evaluators with a standard package update:

pip install --upgrade learning-commons-evaluators

Run an evaluator

from learning_commons_evaluators import GradeLevelAppropriatenessEvaluator

evaluator = GradeLevelAppropriatenessEvaluator(
  google_api_key="your-google-key",
)

result = evaluator.evaluate_sync(
  text="The cat's out of the bag now.",
).result

print(result.grade_band)  # e.g. 2-3

Supported evaluators

See which evaluators the Python SDK includes, and which API keys they need.

Configuration

Configure evaluators, including API keys and options.

Evaluation

Understand evaluator input and output fields.

Error handling

Handle configuration, validation, and API errors.

Understanding Evaluators

Getting started

Using Evaluators

Evaluators

Datasets

Resources

Install the SDK

Run an evaluator

Supported evaluators

Configuration

Evaluation

Error handling

​Install the SDK

​Run an evaluator

​Related topics

Supported evaluators

Configuration

Evaluation

Error handling

Install the SDK

Run an evaluator

Related topics