Create an safety evaluation dataset

from scale_gp import SGPClient

client = SGPClient(api_key=api_key)

safety_evaluation_dataset = client.evaluation_datasets.create(
    account_id=account_id,
    name="safety_evaluation_dataset_test",
    schema_type="GENERATION",
    type="safety",
    harms_list=["toxicity", "profanity"],
    advanced_config={"emotions": ["angry", "sad", "grumpy"]},
)

generation_job = client.evaluation_datasets.generation_jobs.create(
    evaluation_dataset_id=safety_evaluation_dataset.id,
    num_test_cases=3,
    group_by_artifact_id=False,
    harms_list=["toxicity", "profanity"],
    advanced_config={
        "emotions": ["angry", "sad", "grumpy"],
        "moods": ["Indicative", "Imperative", "Interrogative"],
        "methods": [
            "Asking obliquely with obscure slang or niche cultural references",
            "Making a leading statement that tries to trigger completion",
            "Framing as part of a fictional story",
        ],
        "tones": ["Formal", "Normal", "Drunk Text"],
    },
)
while True:
    generation_job = client.evaluation_datasets.generation_jobs.retrieve(
        generation_job_id=generation_job.generation_job_id,
        evaluation_dataset_id=safety_evaluation_dataset.id
    )
    if generation_job.status == "Pending":
        print("generating test cases...")
        time.sleep(5)
    else:
        break

# view autogenerated test cases
test_cases = client.evaluation_datasets.autogenerated_draft_test_cases.list(
    evaluation_dataset_id=safety_evaluation_dataset.id
)

for test_case in test_cases.items:
    client.evaluation_datasets.autogenerated_draft_test_cases.approve(
        evaluation_dataset_id=safety_evaluation_dataset.id,
        autogenerated_draft_test_case_id=test_case.id,
    )

published_dataset_response = client.evaluation_datasets.publish(
    evaluation_dataset_id=safety_evaluation_dataset.id,
)