Create a manual dataset

from scale_gp import SGPClient

client = SGPClient(api_key=api_key)

manual_evaluation_dataset = client.evaluation_datasets.create(
    account_id=account_id,
    name="manual_evaluation_dataset",
    schema_type="GENERATION",
    type="manual",
)

DATASET: List[TestCaseData]= [
    {
        "input": "What is the capital of France?",
        "expected_output": "The capital of France is Paris.",
        "expected_extra_info": {
            "info": "Paris, located in the northern part of France along the Seine River, is not only the country’s capital but also its largest city. Known for its art, fashion, gastronomy, and culture, Paris has a significant influence both in France and globally.",
            "schema_type": "STRING",
        },
    },
    {
        "input": "What color is an apple?",
        "expected_output": "An apple is typically red when ripe, though green and yellow varieties also exist depending on the species and maturity.",
        "expected_extra_info": {
            "info": "Apples come in various colors including red, green, and yellow. Red apples are one of the most common, with varieties like Red Delicious being very popular. Green apples, like Granny Smith, are tart and used often in baking. Yellow apples such as Golden Delicious are sweet and softer.",
            "schema_type": "STRING",
        },
    },
    {
        "input": "Who is the first president of the USA?",
        "expected_output": "The first president of the USA is George Washington.",
        "expected_extra_info": {
            "info": "George Washington served as the first president of the United States from 1789 to 1797. He is a pivotal figure in American history, recognized for his leadership during the Revolutionary War and setting many precedents for the national government.",
            "schema_type": "STRING",
        },
    },
]

items: List[Item] = [Item({"account_id": account_id, "test_case_data": item}) for item in DATASET]
test_cases: List[TestCase] = []
uploaded_test_cases = client.evaluation_datasets.test_cases.batch(
    evaluation_dataset_id=manual_evaluation_dataset.id,
    items=items,
)
test_cases.extend(uploaded_test_cases)

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