daft.functions.jev#

def jev(
    row: Expression,
    condition: str,
    threshold: float = 0.5,
    *,
    model: str | None = None,
    api_key: str | None = None,
    base_url: str | None = None,
    timeout: float = 60.0,
) -> Expression:
    """Whether each row satisfies a plain-English condition, i.e. `jev_prob(row, condition) >= threshold`.

    Args:
        row (Expression): The value to judge. Pass `to_struct(...)` to judge several columns; field names are visible to the model.
        condition (str): A plain-English condition, e.g. "the name is European".
        threshold (float): The minimum probability that counts as true. Defaults to 0.5.
        model (str | None): The Jev model. Defaults to `TYPESAFE_DEFAULT_MODEL`, else `jev-latest`.
        api_key (str | None): TypeSafe API key. Defaults to `TYPESAFE_API_KEY`.
        base_url (str | None): API root, e.g. to route through a proxy. Defaults to `TYPESAFE_BASE_URL`, else `https://api.typesafe.ai`.
        timeout (float): Seconds allowed for each request, which carries up to 25 rows. Defaults to 60.

    Returns:
        Expression: A Boolean, or null where `row` is null.

    Examples:
        >>> import daft
        >>> from daft.functions import jev, to_struct
        >>> df = daft.from_pydict({"first": ["Hans", "Mei"], "last": ["Müller", "Chen"]})
        >>> df.where(jev(to_struct(df["first"], df["last"]), "the name is European")).show()  # doctest: +SKIP
    """
    return jev_prob(row, condition, model=model, api_key=api_key, base_url=base_url, timeout=timeout) >= lit(threshold)