DatasetItem

class opik.DatasetItem(*, input: Dict[str, Any], expected_output: Dict[str, Any] | None = None, metadata: Dict[str, Any] | None = None, trace_id: str | None = None, span_id: str | None = None, id: str | None = None, source: str = 'sdk')

Bases: BaseModel

A DatasetItem object representing an item in a dataset.

model_config: ClassVar[ConfigDict] = {'strict': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

input: Dict[str, Any]

The input data for the dataset item.

expected_output: Dict[str, Any] | None

The expected output for the dataset item.

metadata: Dict[str, Any] | None

Additional metadata associated with the dataset item.

trace_id: str | None

The ID of the trace associated with this dataset item.

model_computed_fields: ClassVar[Dict[str, ComputedFieldInfo]] = {}

A dictionary of computed field names and their corresponding ComputedFieldInfo objects.

model_fields: ClassVar[Dict[str, FieldInfo]] = {'expected_output': FieldInfo(annotation=Union[Dict[str, Any], NoneType], required=False, default=None), 'id': FieldInfo(annotation=Union[str, NoneType], required=False, default=None), 'input': FieldInfo(annotation=Dict[str, Any], required=True), 'metadata': FieldInfo(annotation=Union[Dict[str, Any], NoneType], required=False, default=None), 'source': FieldInfo(annotation=str, required=False, default='sdk'), 'span_id': FieldInfo(annotation=Union[str, NoneType], required=False, default=None), 'trace_id': FieldInfo(annotation=Union[str, NoneType], required=False, default=None)}

Metadata about the fields defined on the model, mapping of field names to [FieldInfo][pydantic.fields.FieldInfo] objects.

This replaces Model.__fields__ from Pydantic V1.

span_id: str | None

The ID of the span associated with this dataset item.

id: str | None

The unique identifier for this dataset item.

source: str

The source of the dataset item. Defaults to DATASET_SOURCE_SDK.

get_content() → Dict[str, Any]