pydantic_evals.dataset

Dataset management for pydantic evals.

This module provides functionality for creating, loading, saving, and evaluating datasets of test cases. Each case must have inputs, and can optionally have a name, expected output, metadata, and case-specific evaluators.

Datasets can be loaded from and saved to YAML or JSON files, and can be evaluated against a task function to produce an evaluation report.

Case dataclass

Bases: Generic[InputsT, OutputT, MetadataT]

A single row of a Dataset.

Each case represents a single test scenario with inputs to test. A case may optionally specify a name, expected outputs to compare against, and arbitrary metadata.

Cases can also have their own specific evaluators which are run in addition to dataset-level evaluators.

Example:

from pydantic_evals import Case

case = Case(
    name='Simple addition',
    inputs={'a': 1, 'b': 2},
    expected_output=3,
    metadata={'description': 'Tests basic addition'},
)

Source code in pydantic_evals/pydantic_evals/dataset.py

@dataclass(init=False)
class Case(Generic[InputsT, OutputT, MetadataT]):
    """A single row of a [`Dataset`][pydantic_evals.Dataset].

    Each case represents a single test scenario with inputs to test. A case may optionally specify a name, expected
    outputs to compare against, and arbitrary metadata.

    Cases can also have their own specific evaluators which are run in addition to dataset-level evaluators.

    Example:
    ```python
    from pydantic_evals import Case

    case = Case(
        name='Simple addition',
        inputs={'a': 1, 'b': 2},
        expected_output=3,
        metadata={'description': 'Tests basic addition'},
    )
    ```
    """

    name: str | None
    """Name of the case. This is used to identify the case in the report and can be used to filter cases."""
    inputs: InputsT
    """Inputs to the task. This is the input to the task that will be evaluated."""
    metadata: MetadataT | None = None
    """Metadata to be used in the evaluation.

    This can be used to provide additional information about the case to the evaluators.
    """
    expected_output: OutputT | None = None
    """Expected output of the task. This is the expected output of the task that will be evaluated."""
    evaluators: list[Evaluator[InputsT, OutputT, MetadataT]] = field(default_factory=list)
    """Evaluators to be used just on this case."""

    def __init__(
        self,
        *,
        name: str | None = None,
        inputs: InputsT,
        metadata: MetadataT | None = None,
        expected_output: OutputT | None = None,
        evaluators: tuple[Evaluator[InputsT, OutputT, MetadataT], ...] = (),
    ):
        """Initialize a new test case.

        Args:
            name: Optional name for the case. If not provided, a generic name will be assigned when added to a dataset.
            inputs: The inputs to the task being evaluated.
            metadata: Optional metadata for the case, which can be used by evaluators.
            expected_output: Optional expected output of the task, used for comparison in evaluators.
            evaluators: Tuple of evaluators specific to this case. These are in addition to any
                dataset-level evaluators.

        """
        # Note: `evaluators` must be a tuple instead of Sequence due to misbehavior with pyright's generic parameter
        # inference if it has type `Sequence`
        self.name = name
        self.inputs = inputs
        self.metadata = metadata
        self.expected_output = expected_output
        self.evaluators = list(evaluators)

__init__

__init__(
    *,
    name: str | None = None,
    inputs: InputsT,
    metadata: MetadataT | None = None,
    expected_output: OutputT | None = None,
    evaluators: tuple[
        Evaluator[InputsT, OutputT, MetadataT], ...
    ] = ()
)

Initialize a new test case.

Parameters:

Name	Type	Description	Default
name	str | None	Optional name for the case. If not provided, a generic name will be assigned when added to a dataset.	None
inputs	InputsT	The inputs to the task being evaluated.	required
metadata	MetadataT | None	Optional metadata for the case, which can be used by evaluators.	None
expected_output	OutputT | None	Optional expected output of the task, used for comparison in evaluators.	None
evaluators	tuple[Evaluator[InputsT, OutputT, MetadataT], ...]	Tuple of evaluators specific to this case. These are in addition to any dataset-level evaluators.	()

Source code in pydantic_evals/pydantic_evals/dataset.py

def __init__(
    self,
    *,
    name: str | None = None,
    inputs: InputsT,
    metadata: MetadataT | None = None,
    expected_output: OutputT | None = None,
    evaluators: tuple[Evaluator[InputsT, OutputT, MetadataT], ...] = (),
):
    """Initialize a new test case.

    Args:
        name: Optional name for the case. If not provided, a generic name will be assigned when added to a dataset.
        inputs: The inputs to the task being evaluated.
        metadata: Optional metadata for the case, which can be used by evaluators.
        expected_output: Optional expected output of the task, used for comparison in evaluators.
        evaluators: Tuple of evaluators specific to this case. These are in addition to any
            dataset-level evaluators.

    """
    # Note: `evaluators` must be a tuple instead of Sequence due to misbehavior with pyright's generic parameter
    # inference if it has type `Sequence`
    self.name = name
    self.inputs = inputs
    self.metadata = metadata
    self.expected_output = expected_output
    self.evaluators = list(evaluators)

name instance-attribute

name: str | None = name

Name of the case. This is used to identify the case in the report and can be used to filter cases.

inputs instance-attribute

inputs: InputsT = inputs

Inputs to the task. This is the input to the task that will be evaluated.

metadata class-attribute instance-attribute

metadata: MetadataT | None = metadata

Metadata to be used in the evaluation.

This can be used to provide additional information about the case to the evaluators.

expected_output class-attribute instance-attribute

expected_output: OutputT | None = expected_output

Expected output of the task. This is the expected output of the task that will be evaluated.

evaluators class-attribute instance-attribute

evaluators: list[Evaluator[InputsT, OutputT, MetadataT]] = (
    list(evaluators)
)

Evaluators to be used just on this case.

Dataset

Bases: BaseModel, Generic[InputsT, OutputT, MetadataT]

A dataset of test cases.

Datasets allow you to organize a collection of test cases and evaluate them against a task function. They can be loaded from and saved to YAML or JSON files, and can have dataset-level evaluators that apply to all cases.

Example:

# Create a dataset with two test cases
from dataclasses import dataclass

from pydantic_evals import Case, Dataset
from pydantic_evals.evaluators import Evaluator, EvaluatorContext


@dataclass
class ExactMatch(Evaluator):
    def evaluate(self, ctx: EvaluatorContext) -> bool:
        return ctx.output == ctx.expected_output

dataset = Dataset(
    cases=[
        Case(name='test1', inputs={'text': 'Hello'}, expected_output='HELLO'),
        Case(name='test2', inputs={'text': 'World'}, expected_output='WORLD'),
    ],
    evaluators=[ExactMatch()],
)

# Evaluate the dataset against a task function
async def uppercase(inputs: dict) -> str:
    return inputs['text'].upper()

async def main():
    report = await dataset.evaluate(uppercase)
    report.print()
'''
   Evaluation Summary: uppercase
┏━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━━┓
┃ Case ID  ┃ Assertions ┃ Duration ┃
┡━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━┩
│ test1    │ ✔          │     10ms │
├──────────┼────────────┼──────────┤
│ test2    │ ✔          │     10ms │
├──────────┼────────────┼──────────┤
│ Averages │ 100.0% ✔   │     10ms │
└──────────┴────────────┴──────────┘
'''

Source code in pydantic_evals/pydantic_evals/dataset.py

class Dataset(BaseModel, Generic[InputsT, OutputT, MetadataT], extra='forbid', arbitrary_types_allowed=True):
    """A dataset of test [cases][pydantic_evals.Case].

    Datasets allow you to organize a collection of test cases and evaluate them against a task function.
    They can be loaded from and saved to YAML or JSON files, and can have dataset-level evaluators that
    apply to all cases.

    Example:
    ```python
    # Create a dataset with two test cases
    from dataclasses import dataclass

    from pydantic_evals import Case, Dataset
    from pydantic_evals.evaluators import Evaluator, EvaluatorContext


    @dataclass
    class ExactMatch(Evaluator):
        def evaluate(self, ctx: EvaluatorContext) -> bool:
            return ctx.output == ctx.expected_output

    dataset = Dataset(
        cases=[
            Case(name='test1', inputs={'text': 'Hello'}, expected_output='HELLO'),
            Case(name='test2', inputs={'text': 'World'}, expected_output='WORLD'),
        ],
        evaluators=[ExactMatch()],
    )

    # Evaluate the dataset against a task function
    async def uppercase(inputs: dict) -> str:
        return inputs['text'].upper()

    async def main():
        report = await dataset.evaluate(uppercase)
        report.print()
    '''
       Evaluation Summary: uppercase
    ┏━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━━┓
    ┃ Case ID  ┃ Assertions ┃ Duration ┃
    ┡━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━┩
    │ test1    │ ✔          │     10ms │
    ├──────────┼────────────┼──────────┤
    │ test2    │ ✔          │     10ms │
    ├──────────┼────────────┼──────────┤
    │ Averages │ 100.0% ✔   │     10ms │
    └──────────┴────────────┴──────────┘
    '''
    ```
    """

    cases: list[Case[InputsT, OutputT, MetadataT]]
    """List of test cases in the dataset."""
    evaluators: list[Evaluator[InputsT, OutputT, MetadataT]] = []
    """List of evaluators to be used on all cases in the dataset."""

    def __init__(
        self,
        *,
        cases: Sequence[Case[InputsT, OutputT, MetadataT]],
        evaluators: Sequence[Evaluator[InputsT, OutputT, MetadataT]] = (),
    ):
        """Initialize a new dataset with test cases and optional evaluators.

        Args:
            cases: Sequence of test cases to include in the dataset.
            evaluators: Optional sequence of evaluators to apply to all cases in the dataset.
        """
        case_names = set[str]()
        for case in cases:
            if case.name is None:
                continue
            if case.name in case_names:
                raise ValueError(f'Duplicate case name: {case.name!r}')
            case_names.add(case.name)

        super().__init__(
            cases=cases,
            evaluators=list(evaluators),
        )

    async def evaluate(
        self, task: Callable[[InputsT], Awaitable[OutputT]], name: str | None = None, max_concurrency: int | None = None
    ) -> EvaluationReport:
        """Evaluates the test cases in the dataset using the given task.

        This method runs the task on each case in the dataset, applies evaluators,
        and collects results into a report. Cases are run concurrently, limited by `max_concurrency` if specified.

        Args:
            task: The task to evaluate. This should be a callable that takes the inputs of the case
                and returns the output.
            name: The name of the task being evaluated, this is used to identify the task in the report.
                If omitted, the name of the task function will be used.
            max_concurrency: The maximum number of concurrent evaluations of the task to allow.
                If None, all cases will be evaluated concurrently.

        Returns:
            A report containing the results of the evaluation.
        """
        name = name or get_unwrapped_function_name(task)

        limiter = anyio.Semaphore(max_concurrency) if max_concurrency is not None else AsyncExitStack()
        with _logfire.span('evaluate {name}', name=name) as eval_span:

            async def _handle_case(case: Case[InputsT, OutputT, MetadataT], report_case_name: str):
                async with limiter:
                    return await _run_task_and_evaluators(task, case, report_case_name, self.evaluators)

            report = EvaluationReport(
                name=name,
                cases=await task_group_gather(
                    [
                        lambda case=case, i=i: _handle_case(case, case.name or f'Case {i}')
                        for i, case in enumerate(self.cases, 1)
                    ]
                ),
            )
            # TODO(DavidM): This attribute will be too big in general; remove it once we can use child spans in details panel:
            eval_span.set_attribute('cases', report.cases)
            # TODO(DavidM): Remove this 'averages' attribute once we compute it in the details panel
            eval_span.set_attribute('averages', report.averages())

        return report

    def evaluate_sync(
        self, task: Callable[[InputsT], Awaitable[OutputT]], name: str | None = None, max_concurrency: int | None = None
    ) -> EvaluationReport:  # pragma: no cover
        """Evaluates the test cases in the dataset using the given task.

        This is a synchronous wrapper around [`evaluate`][pydantic_evals.Dataset.evaluate] provided for convenience.

        Args:
            task: The task to evaluate. This should be a callable that takes the inputs of the case
                and returns the output.
            name: The name of the task being evaluated, this is used to identify the task in the report.
                If omitted, the name of the task function will be used.
            max_concurrency: The maximum number of concurrent evaluations of the task to allow.
                If None, all cases will be evaluated concurrently.

        Returns:
            A report containing the results of the evaluation.
        """
        return get_event_loop().run_until_complete(self.evaluate(task, name=name, max_concurrency=max_concurrency))

    def add_case(
        self,
        *,
        name: str | None = None,
        inputs: InputsT,
        metadata: MetadataT | None = None,
        expected_output: OutputT | None = None,
        evaluators: tuple[Evaluator[InputsT, OutputT, MetadataT], ...] = (),
    ) -> None:
        """Adds a case to the dataset.

        This is a convenience method for creating a [`Case`][pydantic_evals.Case] and adding it to the dataset.

        Args:
            name: Optional name for the case. If not provided, a generic name will be assigned.
            inputs: The inputs to the task being evaluated.
            metadata: Optional metadata for the case, which can be used by evaluators.
            expected_output: The expected output of the task, used for comparison in evaluators.
            evaluators: Tuple of evaluators specific to this case, in addition to dataset-level evaluators.
        """
        if name in {case.name for case in self.cases}:
            raise ValueError(f'Duplicate case name: {name!r}')

        case = Case[InputsT, OutputT, MetadataT](
            name=name,
            inputs=inputs,
            metadata=metadata,
            expected_output=expected_output,
            evaluators=evaluators,
        )
        self.cases.append(case)

    def add_evaluator(
        self,
        evaluator: Evaluator[InputsT, OutputT, MetadataT],
        specific_case: str | None = None,
    ) -> None:
        """Adds an evaluator to the dataset or a specific case.

        Args:
            evaluator: The evaluator to add.
            specific_case: If provided, the evaluator will only be added to the case with this name.
                If None, the evaluator will be added to all cases in the dataset.

        Raises:
            ValueError: If `specific_case` is provided but no case with that name exists in the dataset.
        """
        if specific_case is None:
            self.evaluators.append(evaluator)
        else:
            # If this is too slow, we could try to add a case lookup dict.
            # Note that if we do that, we'd need to make the cases list private to prevent modification.
            added = False
            for case in self.cases:
                if case.name == specific_case:
                    case.evaluators.append(evaluator)
                    added = True
            if not added:
                raise ValueError(f'Case {specific_case!r} not found in the dataset')

    @classmethod
    @functools.cache
    def _params(cls) -> tuple[type[InputsT], type[OutputT], type[MetadataT]]:
        """Get the type parameters for the Dataset class.

        Returns:
            A tuple of (InputsT, OutputT, MetadataT) types.
        """
        for c in cls.__mro__:
            metadata = getattr(c, '__pydantic_generic_metadata__', {})
            if len(args := (metadata.get('args', ()) or getattr(c, '__args__', ()))) == 3:
                return args
        else:  # pragma: no cover
            warnings.warn(
                f'Could not determine the generic parameters for {cls}; using `Any` for each.'
                f' You should explicitly set the generic parameters via `Dataset[MyInputs, MyOutput, MyMetadata]`'
                f' when serializing or deserializing.',
                UserWarning,
            )
            return Any, Any, Any  # type: ignore

    @classmethod
    def from_file(
        cls,
        path: Path | str,
        fmt: Literal['yaml', 'json'] | None = None,
        custom_evaluator_types: Sequence[type[Evaluator[InputsT, OutputT, MetadataT]]] = (),
    ) -> Self:
        """Load a dataset from a file.

        Args:
            path: Path to the file to load.
            fmt: Format of the file. If None, the format will be inferred from the file extension.
                Must be either 'yaml' or 'json'.
            custom_evaluator_types: Custom evaluator classes to use when deserializing the dataset.
                These are additional evaluators beyond the default ones.

        Returns:
            A new Dataset instance loaded from the file.

        Raises:
            ValidationError: If the file cannot be parsed as a valid dataset.
            ValueError: If the format cannot be inferred from the file extension.
        """
        path = Path(path)
        fmt = cls._infer_fmt(path, fmt)

        raw = Path(path).read_text()
        try:
            return cls.from_text(raw, fmt=fmt, custom_evaluator_types=custom_evaluator_types)
        except ValidationError as e:  # pragma: no cover
            raise ValueError(f'{path} contains data that does not match the schema for {cls.__name__}:\n{e}.') from e

    @classmethod
    def from_text(
        cls,
        contents: str,
        fmt: Literal['yaml', 'json'] = 'yaml',
        custom_evaluator_types: Sequence[type[Evaluator[InputsT, OutputT, MetadataT]]] = (),
    ) -> Self:
        """Load a dataset from a string.

        Args:
            contents: The string content to parse.
            fmt: Format of the content. Must be either 'yaml' or 'json'.
            custom_evaluator_types: Custom evaluator classes to use when deserializing the dataset.
                These are additional evaluators beyond the default ones.

        Returns:
            A new Dataset instance parsed from the string.

        Raises:
            ValidationError: If the content cannot be parsed as a valid dataset.
        """
        if fmt == 'yaml':
            loaded = yaml.safe_load(contents)
            return cls.from_dict(loaded, custom_evaluator_types)
        else:
            dataset_model_type = cls._serialization_type()
            dataset_model = dataset_model_type.model_validate_json(contents)
            return cls._from_dataset_model(dataset_model, custom_evaluator_types)

    @classmethod
    def from_dict(
        cls,
        data: dict[str, Any],
        custom_evaluator_types: Sequence[type[Evaluator[InputsT, OutputT, MetadataT]]] = (),
    ) -> Self:
        """Load a dataset from a dictionary.

        Args:
            data: Dictionary representation of the dataset.
            custom_evaluator_types: Custom evaluator classes to use when deserializing the dataset.
                These are additional evaluators beyond the default ones.

        Returns:
            A new Dataset instance created from the dictionary.

        Raises:
            ValidationError: If the dictionary cannot be converted to a valid dataset.
        """
        dataset_model_type = cls._serialization_type()
        dataset_model = dataset_model_type.model_validate(data)
        return cls._from_dataset_model(dataset_model, custom_evaluator_types)

    @classmethod
    def _from_dataset_model(
        cls,
        dataset_model: _DatasetModel[InputsT, OutputT, MetadataT],
        custom_evaluator_types: Sequence[type[Evaluator[InputsT, OutputT, MetadataT]]] = (),
    ) -> Self:
        """Create a Dataset from a _DatasetModel.

        Args:
            dataset_model: The _DatasetModel to convert.
            custom_evaluator_types: Custom evaluator classes to register for deserialization.

        Returns:
            A new Dataset instance created from the _DatasetModel.
        """
        registry = _get_registry(custom_evaluator_types)

        cases: list[Case[InputsT, OutputT, MetadataT]] = []
        errors: list[ValueError] = []
        dataset_evaluators: list[Evaluator] = []
        for spec in dataset_model.evaluators:
            try:
                dataset_evaluator = _load_evaluator_from_registry(registry, None, spec)
            except ValueError as e:
                errors.append(e)
                continue
            dataset_evaluators.append(dataset_evaluator)

        for row in dataset_model.cases:
            evaluators: list[Evaluator] = []
            for spec in row.evaluators:
                try:
                    evaluator = _load_evaluator_from_registry(registry, row.name, spec)
                except ValueError as e:
                    errors.append(e)
                    continue
                evaluators.append(evaluator)
            row = Case[InputsT, OutputT, MetadataT](
                name=row.name,
                inputs=row.inputs,
                metadata=row.metadata,
                expected_output=row.expected_output,
            )
            row.evaluators = evaluators
            cases.append(row)
        if errors:
            raise ExceptionGroup(f'{len(errors)} error(s) loading evaluators from registry', errors[:3])
        result = cls(cases=cases)
        result.evaluators = dataset_evaluators
        return result

    def to_file(
        self,
        path: Path | str,
        fmt: Literal['yaml', 'json'] | None = None,
        schema_path: Path | str | None = DEFAULT_SCHEMA_PATH_TEMPLATE,
        custom_evaluator_types: Sequence[type[Evaluator[InputsT, OutputT, MetadataT]]] = (),
    ):
        """Save the dataset to a file.

        Args:
            path: Path to save the dataset to.
            fmt: Format to use. If None, the format will be inferred from the file extension.
                Must be either 'yaml' or 'json'.
            schema_path: Path to save the JSON schema to. If None, no schema will be saved.
                Can be a string template with {stem} which will be replaced with the dataset filename stem.
            custom_evaluator_types: Custom evaluator classes to include in the schema.
        """
        path = Path(path)
        fmt = self._infer_fmt(path, fmt)

        schema_ref: str | None = None
        if schema_path is not None:
            if isinstance(schema_path, str):
                schema_path = Path(schema_path.format(stem=path.stem))

            if not schema_path.is_absolute():
                schema_ref = str(schema_path)
                schema_path = path.parent / schema_path
            elif schema_path.is_relative_to(path):  # pragma: no cover
                schema_ref = str(_get_relative_path_reference(schema_path, path))
            else:  # pragma: no cover
                schema_ref = str(schema_path)
            self._save_schema(schema_path, custom_evaluator_types)

        context: dict[str, Any] = {'use_short_form': True}
        if fmt == 'yaml':
            dumped_data = self.model_dump(mode='json', by_alias=True, exclude_defaults=True, context=context)
            content = yaml.dump(dumped_data, sort_keys=False)
            if schema_ref:
                yaml_language_server_line = f'{_YAML_SCHEMA_LINE_PREFIX}{schema_ref}'
                content = f'{yaml_language_server_line}\n{content}'
            path.write_text(content)
        else:
            context['$schema'] = schema_ref
            json_data = self.model_dump_json(indent=2, by_alias=True, exclude_defaults=True, context=context)
            path.write_text(json_data + '\n')

    @classmethod
    def model_json_schema_with_evaluators(
        cls,
        custom_evaluator_types: Sequence[type[Evaluator[InputsT, OutputT, MetadataT]]] = (),
    ) -> dict[str, Any]:
        """Generate a JSON schema for this dataset type, including evaluator details.

        This is useful for generating a schema that can be used to validate YAML-format dataset files.

        Args:
            custom_evaluator_types: Custom evaluator classes to include in the schema.

        Returns:
            A dictionary representing the JSON schema.
        """
        # Note: this function could maybe be simplified now that Evaluators are always dataclasses
        registry = _get_registry(custom_evaluator_types)

        evaluator_schema_types: list[Any] = []
        for name, evaluator_class in registry.items():
            type_hints = _typing_extra.get_function_type_hints(evaluator_class)
            type_hints.pop('return', None)
            required_type_hints: dict[str, Any] = {}

            for p in inspect.signature(evaluator_class).parameters.values():
                type_hints.setdefault(p.name, Any)
                if p.default is not p.empty:
                    type_hints[p.name] = NotRequired[type_hints[p.name]]
                else:
                    required_type_hints[p.name] = type_hints[p.name]

            def _make_typed_dict(cls_name_prefix: str, fields: dict[str, Any]) -> Any:
                td = TypedDict(f'{cls_name_prefix}_{name}', fields)  # pyright: ignore[reportArgumentType]
                config = ConfigDict(extra='forbid', arbitrary_types_allowed=True)
                # TODO: Replace with pydantic.with_config after pydantic 2.11 is released
                td.__pydantic_config__ = config  # pyright: ignore[reportAttributeAccessIssue]
                return td

            # Shortest form: just the call name
            if len(type_hints) == 0 or not required_type_hints:
                evaluator_schema_types.append(Literal[name])

            # Short form: can be called with only one parameter
            if len(type_hints) == 1:
                [type_hint_type] = type_hints.values()
                evaluator_schema_types.append(_make_typed_dict('short_evaluator', {name: type_hint_type}))
            elif len(required_type_hints) == 1:
                [type_hint_type] = required_type_hints.values()
                evaluator_schema_types.append(_make_typed_dict('short_evaluator', {name: type_hint_type}))

            # Long form: multiple parameters, possibly required
            if len(type_hints) > 1:
                params_td = _make_typed_dict('evaluator_params', type_hints)
                evaluator_schema_types.append(_make_typed_dict('evaluator', {name: params_td}))

        in_type, out_type, meta_type = cls._params()

        # Note: we shadow the `Case` and `Dataset` class names here to generate a clean JSON schema
        class Case(BaseModel, extra='forbid'):  # pyright: ignore[reportUnusedClass]  # this _is_ used below, but pyright doesn't seem to notice..
            name: str | None = None
            inputs: in_type  # pyright: ignore[reportInvalidTypeForm]
            metadata: meta_type | None = None  # pyright: ignore[reportInvalidTypeForm,reportUnknownVariableType]
            expected_output: out_type | None = None  # pyright: ignore[reportInvalidTypeForm,reportUnknownVariableType]
            if evaluator_schema_types:
                evaluators: list[Union[tuple(evaluator_schema_types)]] = []  # pyright: ignore  # noqa UP007

        class Dataset(BaseModel, extra='forbid'):
            cases: list[Case]
            if evaluator_schema_types:
                evaluators: list[Union[tuple(evaluator_schema_types)]] = []  # pyright: ignore  # noqa UP007

        json_schema = Dataset.model_json_schema()
        # See `_add_json_schema` below, since `$schema` is added to the JSON, it has to be supported in the JSON
        json_schema['properties']['$schema'] = {'type': 'string'}
        return json_schema

    @classmethod
    def _save_schema(
        cls, path: Path | str, custom_evaluator_types: Sequence[type[Evaluator[InputsT, OutputT, MetadataT]]] = ()
    ):
        """Save the JSON schema for this dataset type to a file.

        Args:
            path: Path to save the schema to.
            custom_evaluator_types: Custom evaluator classes to include in the schema.
        """
        path = Path(path)
        json_schema = cls.model_json_schema_with_evaluators(custom_evaluator_types)
        schema_content = to_json(json_schema, indent=2).decode() + '\n'
        if not path.exists() or path.read_text() != schema_content:
            path.write_text(schema_content)

    @classmethod
    @functools.cache
    def _serialization_type(cls) -> type[_DatasetModel[InputsT, OutputT, MetadataT]]:
        """Get the serialization type for this dataset class.

        Returns:
            A _DatasetModel type with the same generic parameters as this Dataset class.
        """
        input_type, output_type, metadata_type = cls._params()
        return _DatasetModel[input_type, output_type, metadata_type]

    @classmethod
    def _infer_fmt(cls, path: Path, fmt: Literal['yaml', 'json'] | None) -> Literal['yaml', 'json']:
        """Infer the format to use for a file based on its extension.

        Args:
            path: The path to infer the format for.
            fmt: The explicitly provided format, if any.

        Returns:
            The inferred format ('yaml' or 'json').

        Raises:
            ValueError: If the format cannot be inferred from the file extension.
        """
        if fmt is not None:
            return fmt
        suffix = path.suffix.lower()
        if suffix in {'.yaml', '.yml'}:
            return 'yaml'
        elif suffix == '.json':
            return 'json'
        raise ValueError(
            f'Could not infer format for filename {path.name!r}. Use the `fmt` argument to specify the format.'
        )

    @model_serializer(mode='wrap')
    def _add_json_schema(self, nxt: SerializerFunctionWrapHandler, info: SerializationInfo) -> dict[str, Any]:
        """Add the JSON schema path to the serialized output.

        See <https://github.com/json-schema-org/json-schema-spec/issues/828> for context, that seems to be the nearest
        there is to a spec for this.
        """
        context = cast(Union[dict[str, Any], None], info.context)
        if isinstance(context, dict) and (schema := context.get('$schema')):
            return {'$schema': schema} | nxt(self)
        else:
            return nxt(self)

cases instance-attribute

cases: list[Case[InputsT, OutputT, MetadataT]]

List of test cases in the dataset.

evaluators class-attribute instance-attribute

evaluators: list[Evaluator[InputsT, OutputT, MetadataT]] = (
    []
)

List of evaluators to be used on all cases in the dataset.

__init__

__init__(
    *,
    cases: Sequence[Case[InputsT, OutputT, MetadataT]],
    evaluators: Sequence[
        Evaluator[InputsT, OutputT, MetadataT]
    ] = ()
)

Initialize a new dataset with test cases and optional evaluators.

Parameters:

Name	Type	Description	Default
cases	Sequence[Case[InputsT, OutputT, MetadataT]]	Sequence of test cases to include in the dataset.	required
evaluators	Sequence[Evaluator[InputsT, OutputT, MetadataT]]	Optional sequence of evaluators to apply to all cases in the dataset.	()

Source code in pydantic_evals/pydantic_evals/dataset.py

def __init__(
    self,
    *,
    cases: Sequence[Case[InputsT, OutputT, MetadataT]],
    evaluators: Sequence[Evaluator[InputsT, OutputT, MetadataT]] = (),
):
    """Initialize a new dataset with test cases and optional evaluators.

    Args:
        cases: Sequence of test cases to include in the dataset.
        evaluators: Optional sequence of evaluators to apply to all cases in the dataset.
    """
    case_names = set[str]()
    for case in cases:
        if case.name is None:
            continue
        if case.name in case_names:
            raise ValueError(f'Duplicate case name: {case.name!r}')
        case_names.add(case.name)

    super().__init__(
        cases=cases,
        evaluators=list(evaluators),
    )

evaluate async

evaluate(
    task: Callable[[InputsT], Awaitable[OutputT]],
    name: str | None = None,
    max_concurrency: int | None = None,
) -> EvaluationReport

Evaluates the test cases in the dataset using the given task.

This method runs the task on each case in the dataset, applies evaluators, and collects results into a report. Cases are run concurrently, limited by max_concurrency if specified.

Parameters:

Name	Type	Description	Default
task	Callable[[InputsT], Awaitable[OutputT]]	The task to evaluate. This should be a callable that takes the inputs of the case and returns the output.	required
name	str | None	The name of the task being evaluated, this is used to identify the task in the report. If omitted, the name of the task function will be used.	None
max_concurrency	int | None	The maximum number of concurrent evaluations of the task to allow. If None, all cases will be evaluated concurrently.	None

Returns:

Type	Description
EvaluationReport	A report containing the results of the evaluation.

Source code in pydantic_evals/pydantic_evals/dataset.py

async def evaluate(
    self, task: Callable[[InputsT], Awaitable[OutputT]], name: str | None = None, max_concurrency: int | None = None
) -> EvaluationReport:
    """Evaluates the test cases in the dataset using the given task.

    This method runs the task on each case in the dataset, applies evaluators,
    and collects results into a report. Cases are run concurrently, limited by `max_concurrency` if specified.

    Args:
        task: The task to evaluate. This should be a callable that takes the inputs of the case
            and returns the output.
        name: The name of the task being evaluated, this is used to identify the task in the report.
            If omitted, the name of the task function will be used.
        max_concurrency: The maximum number of concurrent evaluations of the task to allow.
            If None, all cases will be evaluated concurrently.

    Returns:
        A report containing the results of the evaluation.
    """
    name = name or get_unwrapped_function_name(task)

    limiter = anyio.Semaphore(max_concurrency) if max_concurrency is not None else AsyncExitStack()
    with _logfire.span('evaluate {name}', name=name) as eval_span:

        async def _handle_case(case: Case[InputsT, OutputT, MetadataT], report_case_name: str):
            async with limiter:
                return await _run_task_and_evaluators(task, case, report_case_name, self.evaluators)

        report = EvaluationReport(
            name=name,
            cases=await task_group_gather(
                [
                    lambda case=case, i=i: _handle_case(case, case.name or f'Case {i}')
                    for i, case in enumerate(self.cases, 1)
                ]
            ),
        )
        # TODO(DavidM): This attribute will be too big in general; remove it once we can use child spans in details panel:
        eval_span.set_attribute('cases', report.cases)
        # TODO(DavidM): Remove this 'averages' attribute once we compute it in the details panel
        eval_span.set_attribute('averages', report.averages())

    return report

evaluate_sync

evaluate_sync(
    task: Callable[[InputsT], Awaitable[OutputT]],
    name: str | None = None,
    max_concurrency: int | None = None,
) -> EvaluationReport

Evaluates the test cases in the dataset using the given task.

This is a synchronous wrapper around evaluate provided for convenience.

Parameters:

Name	Type	Description	Default
task	Callable[[InputsT], Awaitable[OutputT]]	The task to evaluate. This should be a callable that takes the inputs of the case and returns the output.	required
name	str | None	The name of the task being evaluated, this is used to identify the task in the report. If omitted, the name of the task function will be used.	None
max_concurrency	int | None	The maximum number of concurrent evaluations of the task to allow. If None, all cases will be evaluated concurrently.	None

Returns:

Type	Description
EvaluationReport	A report containing the results of the evaluation.

Source code in pydantic_evals/pydantic_evals/dataset.py

def evaluate_sync(
    self, task: Callable[[InputsT], Awaitable[OutputT]], name: str | None = None, max_concurrency: int | None = None
) -> EvaluationReport:  # pragma: no cover
    """Evaluates the test cases in the dataset using the given task.

    This is a synchronous wrapper around [`evaluate`][pydantic_evals.Dataset.evaluate] provided for convenience.

    Args:
        task: The task to evaluate. This should be a callable that takes the inputs of the case
            and returns the output.
        name: The name of the task being evaluated, this is used to identify the task in the report.
            If omitted, the name of the task function will be used.
        max_concurrency: The maximum number of concurrent evaluations of the task to allow.
            If None, all cases will be evaluated concurrently.

    Returns:
        A report containing the results of the evaluation.
    """
    return get_event_loop().run_until_complete(self.evaluate(task, name=name, max_concurrency=max_concurrency))

add_case

add_case(
    *,
    name: str | None = None,
    inputs: InputsT,
    metadata: MetadataT | None = None,
    expected_output: OutputT | None = None,
    evaluators: tuple[
        Evaluator[InputsT, OutputT, MetadataT], ...
    ] = ()
) -> None

Adds a case to the dataset.

This is a convenience method for creating a Case and adding it to the dataset.

Parameters:

Name	Type	Description	Default
name	str | None	Optional name for the case. If not provided, a generic name will be assigned.	None
inputs	InputsT	The inputs to the task being evaluated.	required
metadata	MetadataT | None	Optional metadata for the case, which can be used by evaluators.	None
expected_output	OutputT | None	The expected output of the task, used for comparison in evaluators.	None
evaluators	tuple[Evaluator[InputsT, OutputT, MetadataT], ...]	Tuple of evaluators specific to this case, in addition to dataset-level evaluators.	()

Source code in pydantic_evals/pydantic_evals/dataset.py

def add_case(
    self,
    *,
    name: str | None = None,
    inputs: InputsT,
    metadata: MetadataT | None = None,
    expected_output: OutputT | None = None,
    evaluators: tuple[Evaluator[InputsT, OutputT, MetadataT], ...] = (),
) -> None:
    """Adds a case to the dataset.

    This is a convenience method for creating a [`Case`][pydantic_evals.Case] and adding it to the dataset.

    Args:
        name: Optional name for the case. If not provided, a generic name will be assigned.
        inputs: The inputs to the task being evaluated.
        metadata: Optional metadata for the case, which can be used by evaluators.
        expected_output: The expected output of the task, used for comparison in evaluators.
        evaluators: Tuple of evaluators specific to this case, in addition to dataset-level evaluators.
    """
    if name in {case.name for case in self.cases}:
        raise ValueError(f'Duplicate case name: {name!r}')

    case = Case[InputsT, OutputT, MetadataT](
        name=name,
        inputs=inputs,
        metadata=metadata,
        expected_output=expected_output,
        evaluators=evaluators,
    )
    self.cases.append(case)

add_evaluator

add_evaluator(
    evaluator: Evaluator[InputsT, OutputT, MetadataT],
    specific_case: str | None = None,
) -> None

Adds an evaluator to the dataset or a specific case.

Parameters:

Name	Type	Description	Default
evaluator	Evaluator[InputsT, OutputT, MetadataT]	The evaluator to add.	required
specific_case	str | None	If provided, the evaluator will only be added to the case with this name. If None, the evaluator will be added to all cases in the dataset.	None

Raises:

Type	Description
ValueError	If specific_case is provided but no case with that name exists in the dataset.

Source code in pydantic_evals/pydantic_evals/dataset.py

def add_evaluator(
    self,
    evaluator: Evaluator[InputsT, OutputT, MetadataT],
    specific_case: str | None = None,
) -> None:
    """Adds an evaluator to the dataset or a specific case.

    Args:
        evaluator: The evaluator to add.
        specific_case: If provided, the evaluator will only be added to the case with this name.
            If None, the evaluator will be added to all cases in the dataset.

    Raises:
        ValueError: If `specific_case` is provided but no case with that name exists in the dataset.
    """
    if specific_case is None:
        self.evaluators.append(evaluator)
    else:
        # If this is too slow, we could try to add a case lookup dict.
        # Note that if we do that, we'd need to make the cases list private to prevent modification.
        added = False
        for case in self.cases:
            if case.name == specific_case:
                case.evaluators.append(evaluator)
                added = True
        if not added:
            raise ValueError(f'Case {specific_case!r} not found in the dataset')

from_file classmethod

from_file(
    path: Path | str,
    fmt: Literal["yaml", "json"] | None = None,
    custom_evaluator_types: Sequence[
        type[Evaluator[InputsT, OutputT, MetadataT]]
    ] = (),
) -> Self

Load a dataset from a file.

Parameters:

Name	Type	Description	Default
path	Path | str	Path to the file to load.	required
fmt	Literal['yaml', 'json'] | None	Format of the file. If None, the format will be inferred from the file extension. Must be either 'yaml' or 'json'.	None
custom_evaluator_types	Sequence[type[Evaluator[InputsT, OutputT, MetadataT]]]	Custom evaluator classes to use when deserializing the dataset. These are additional evaluators beyond the default ones.	()

Returns:

Type	Description
Self	A new Dataset instance loaded from the file.

Raises:

Type	Description
ValidationError	If the file cannot be parsed as a valid dataset.
ValueError	If the format cannot be inferred from the file extension.

Source code in pydantic_evals/pydantic_evals/dataset.py

@classmethod
def from_file(
    cls,
    path: Path | str,
    fmt: Literal['yaml', 'json'] | None = None,
    custom_evaluator_types: Sequence[type[Evaluator[InputsT, OutputT, MetadataT]]] = (),
) -> Self:
    """Load a dataset from a file.

    Args:
        path: Path to the file to load.
        fmt: Format of the file. If None, the format will be inferred from the file extension.
            Must be either 'yaml' or 'json'.
        custom_evaluator_types: Custom evaluator classes to use when deserializing the dataset.
            These are additional evaluators beyond the default ones.

    Returns:
        A new Dataset instance loaded from the file.

    Raises:
        ValidationError: If the file cannot be parsed as a valid dataset.
        ValueError: If the format cannot be inferred from the file extension.
    """
    path = Path(path)
    fmt = cls._infer_fmt(path, fmt)

    raw = Path(path).read_text()
    try:
        return cls.from_text(raw, fmt=fmt, custom_evaluator_types=custom_evaluator_types)
    except ValidationError as e:  # pragma: no cover
        raise ValueError(f'{path} contains data that does not match the schema for {cls.__name__}:\n{e}.') from e

from_text classmethod

from_text(
    contents: str,
    fmt: Literal["yaml", "json"] = "yaml",
    custom_evaluator_types: Sequence[
        type[Evaluator[InputsT, OutputT, MetadataT]]
    ] = (),
) -> Self

Load a dataset from a string.

Parameters:

Name	Type	Description	Default
contents	str	The string content to parse.	required
fmt	Literal['yaml', 'json']	Format of the content. Must be either 'yaml' or 'json'.	'yaml'
custom_evaluator_types	Sequence[type[Evaluator[InputsT, OutputT, MetadataT]]]	Custom evaluator classes to use when deserializing the dataset. These are additional evaluators beyond the default ones.	()

Returns:

Type	Description
Self	A new Dataset instance parsed from the string.

Raises:

Type	Description
ValidationError	If the content cannot be parsed as a valid dataset.

Source code in pydantic_evals/pydantic_evals/dataset.py

@classmethod
def from_text(
    cls,
    contents: str,
    fmt: Literal['yaml', 'json'] = 'yaml',
    custom_evaluator_types: Sequence[type[Evaluator[InputsT, OutputT, MetadataT]]] = (),
) -> Self:
    """Load a dataset from a string.

    Args:
        contents: The string content to parse.
        fmt: Format of the content. Must be either 'yaml' or 'json'.
        custom_evaluator_types: Custom evaluator classes to use when deserializing the dataset.
            These are additional evaluators beyond the default ones.

    Returns:
        A new Dataset instance parsed from the string.

    Raises:
        ValidationError: If the content cannot be parsed as a valid dataset.
    """
    if fmt == 'yaml':
        loaded = yaml.safe_load(contents)
        return cls.from_dict(loaded, custom_evaluator_types)
    else:
        dataset_model_type = cls._serialization_type()
        dataset_model = dataset_model_type.model_validate_json(contents)
        return cls._from_dataset_model(dataset_model, custom_evaluator_types)

from_dict classmethod

from_dict(
    data: dict[str, Any],
    custom_evaluator_types: Sequence[
        type[Evaluator[InputsT, OutputT, MetadataT]]
    ] = (),
) -> Self

Load a dataset from a dictionary.

Parameters:

Name	Type	Description	Default
data	dict[str, Any]	Dictionary representation of the dataset.	required
custom_evaluator_types	Sequence[type[Evaluator[InputsT, OutputT, MetadataT]]]	Custom evaluator classes to use when deserializing the dataset. These are additional evaluators beyond the default ones.	()

Returns:

Type	Description
Self	A new Dataset instance created from the dictionary.

Raises:

Type	Description
ValidationError	If the dictionary cannot be converted to a valid dataset.

Source code in pydantic_evals/pydantic_evals/dataset.py

@classmethod
def from_dict(
    cls,
    data: dict[str, Any],
    custom_evaluator_types: Sequence[type[Evaluator[InputsT, OutputT, MetadataT]]] = (),
) -> Self:
    """Load a dataset from a dictionary.

    Args:
        data: Dictionary representation of the dataset.
        custom_evaluator_types: Custom evaluator classes to use when deserializing the dataset.
            These are additional evaluators beyond the default ones.

    Returns:
        A new Dataset instance created from the dictionary.

    Raises:
        ValidationError: If the dictionary cannot be converted to a valid dataset.
    """
    dataset_model_type = cls._serialization_type()
    dataset_model = dataset_model_type.model_validate(data)
    return cls._from_dataset_model(dataset_model, custom_evaluator_types)

to_file

to_file(
    path: Path | str,
    fmt: Literal["yaml", "json"] | None = None,
    schema_path: (
        Path | str | None
    ) = DEFAULT_SCHEMA_PATH_TEMPLATE,
    custom_evaluator_types: Sequence[
        type[Evaluator[InputsT, OutputT, MetadataT]]
    ] = (),
)

Save the dataset to a file.

Parameters:

Name	Type	Description	Default
path	Path | str	Path to save the dataset to.	required
fmt	Literal['yaml', 'json'] | None	Format to use. If None, the format will be inferred from the file extension. Must be either 'yaml' or 'json'.	None
schema_path	Path | str | None	Path to save the JSON schema to. If None, no schema will be saved. Can be a string template with {stem} which will be replaced with the dataset filename stem.	DEFAULT_SCHEMA_PATH_TEMPLATE
custom_evaluator_types	Sequence[type[Evaluator[InputsT, OutputT, MetadataT]]]	Custom evaluator classes to include in the schema.	()

Source code in pydantic_evals/pydantic_evals/dataset.py

def to_file(
    self,
    path: Path | str,
    fmt: Literal['yaml', 'json'] | None = None,
    schema_path: Path | str | None = DEFAULT_SCHEMA_PATH_TEMPLATE,
    custom_evaluator_types: Sequence[type[Evaluator[InputsT, OutputT, MetadataT]]] = (),
):
    """Save the dataset to a file.

    Args:
        path: Path to save the dataset to.
        fmt: Format to use. If None, the format will be inferred from the file extension.
            Must be either 'yaml' or 'json'.
        schema_path: Path to save the JSON schema to. If None, no schema will be saved.
            Can be a string template with {stem} which will be replaced with the dataset filename stem.
        custom_evaluator_types: Custom evaluator classes to include in the schema.
    """
    path = Path(path)
    fmt = self._infer_fmt(path, fmt)

    schema_ref: str | None = None
    if schema_path is not None:
        if isinstance(schema_path, str):
            schema_path = Path(schema_path.format(stem=path.stem))

        if not schema_path.is_absolute():
            schema_ref = str(schema_path)
            schema_path = path.parent / schema_path
        elif schema_path.is_relative_to(path):  # pragma: no cover
            schema_ref = str(_get_relative_path_reference(schema_path, path))
        else:  # pragma: no cover
            schema_ref = str(schema_path)
        self._save_schema(schema_path, custom_evaluator_types)

    context: dict[str, Any] = {'use_short_form': True}
    if fmt == 'yaml':
        dumped_data = self.model_dump(mode='json', by_alias=True, exclude_defaults=True, context=context)
        content = yaml.dump(dumped_data, sort_keys=False)
        if schema_ref:
            yaml_language_server_line = f'{_YAML_SCHEMA_LINE_PREFIX}{schema_ref}'
            content = f'{yaml_language_server_line}\n{content}'
        path.write_text(content)
    else:
        context['$schema'] = schema_ref
        json_data = self.model_dump_json(indent=2, by_alias=True, exclude_defaults=True, context=context)
        path.write_text(json_data + '\n')

model_json_schema_with_evaluators classmethod

model_json_schema_with_evaluators(
    custom_evaluator_types: Sequence[
        type[Evaluator[InputsT, OutputT, MetadataT]]
    ] = (),
) -> dict[str, Any]

Generate a JSON schema for this dataset type, including evaluator details.

This is useful for generating a schema that can be used to validate YAML-format dataset files.

Parameters:

Name	Type	Description	Default
custom_evaluator_types	Sequence[type[Evaluator[InputsT, OutputT, MetadataT]]]	Custom evaluator classes to include in the schema.	()

Returns:

Type	Description
dict[str, Any]	A dictionary representing the JSON schema.

Source code in pydantic_evals/pydantic_evals/dataset.py

@classmethod
def model_json_schema_with_evaluators(
    cls,
    custom_evaluator_types: Sequence[type[Evaluator[InputsT, OutputT, MetadataT]]] = (),
) -> dict[str, Any]:
    """Generate a JSON schema for this dataset type, including evaluator details.

    This is useful for generating a schema that can be used to validate YAML-format dataset files.

    Args:
        custom_evaluator_types: Custom evaluator classes to include in the schema.

    Returns:
        A dictionary representing the JSON schema.
    """
    # Note: this function could maybe be simplified now that Evaluators are always dataclasses
    registry = _get_registry(custom_evaluator_types)

    evaluator_schema_types: list[Any] = []
    for name, evaluator_class in registry.items():
        type_hints = _typing_extra.get_function_type_hints(evaluator_class)
        type_hints.pop('return', None)
        required_type_hints: dict[str, Any] = {}

        for p in inspect.signature(evaluator_class).parameters.values():
            type_hints.setdefault(p.name, Any)
            if p.default is not p.empty:
                type_hints[p.name] = NotRequired[type_hints[p.name]]
            else:
                required_type_hints[p.name] = type_hints[p.name]

        def _make_typed_dict(cls_name_prefix: str, fields: dict[str, Any]) -> Any:
            td = TypedDict(f'{cls_name_prefix}_{name}', fields)  # pyright: ignore[reportArgumentType]
            config = ConfigDict(extra='forbid', arbitrary_types_allowed=True)
            # TODO: Replace with pydantic.with_config after pydantic 2.11 is released
            td.__pydantic_config__ = config  # pyright: ignore[reportAttributeAccessIssue]
            return td

        # Shortest form: just the call name
        if len(type_hints) == 0 or not required_type_hints:
            evaluator_schema_types.append(Literal[name])

        # Short form: can be called with only one parameter
        if len(type_hints) == 1:
            [type_hint_type] = type_hints.values()
            evaluator_schema_types.append(_make_typed_dict('short_evaluator', {name: type_hint_type}))
        elif len(required_type_hints) == 1:
            [type_hint_type] = required_type_hints.values()
            evaluator_schema_types.append(_make_typed_dict('short_evaluator', {name: type_hint_type}))

        # Long form: multiple parameters, possibly required
        if len(type_hints) > 1:
            params_td = _make_typed_dict('evaluator_params', type_hints)
            evaluator_schema_types.append(_make_typed_dict('evaluator', {name: params_td}))

    in_type, out_type, meta_type = cls._params()

    # Note: we shadow the `Case` and `Dataset` class names here to generate a clean JSON schema
    class Case(BaseModel, extra='forbid'):  # pyright: ignore[reportUnusedClass]  # this _is_ used below, but pyright doesn't seem to notice..
        name: str | None = None
        inputs: in_type  # pyright: ignore[reportInvalidTypeForm]
        metadata: meta_type | None = None  # pyright: ignore[reportInvalidTypeForm,reportUnknownVariableType]
        expected_output: out_type | None = None  # pyright: ignore[reportInvalidTypeForm,reportUnknownVariableType]
        if evaluator_schema_types:
            evaluators: list[Union[tuple(evaluator_schema_types)]] = []  # pyright: ignore  # noqa UP007

    class Dataset(BaseModel, extra='forbid'):
        cases: list[Case]
        if evaluator_schema_types:
            evaluators: list[Union[tuple(evaluator_schema_types)]] = []  # pyright: ignore  # noqa UP007

    json_schema = Dataset.model_json_schema()
    # See `_add_json_schema` below, since `$schema` is added to the JSON, it has to be supported in the JSON
    json_schema['properties']['$schema'] = {'type': 'string'}
    return json_schema

set_eval_attribute

set_eval_attribute(name: str, value: Any) -> None

Set an attribute on the current task run.

Parameters:

Name	Type	Description	Default
name	str	The name of the attribute.	required
value	Any	The value of the attribute.	required

Source code in pydantic_evals/pydantic_evals/dataset.py

def set_eval_attribute(name: str, value: Any) -> None:
    """Set an attribute on the current task run.

    Args:
        name: The name of the attribute.
        value: The value of the attribute.
    """
    current_case = _CURRENT_TASK_RUN.get()
    if current_case is not None:
        current_case.record_attribute(name, value)

increment_eval_metric

increment_eval_metric(
    name: str, amount: int | float
) -> None

Increment a metric on the current task run.

Parameters:

Name	Type	Description	Default
name	str	The name of the metric.	required
amount	int | float	The amount to increment by.	required

Source code in pydantic_evals/pydantic_evals/dataset.py

def increment_eval_metric(name: str, amount: int | float) -> None:
    """Increment a metric on the current task run.

    Args:
        name: The name of the metric.
        amount: The amount to increment by.
    """
    current_case = _CURRENT_TASK_RUN.get()
    if current_case is not None:
        current_case.increment_metric(name, amount)