unitxt.serializers module

class unitxt.serializers.DefaultListSerializer(__tags__: Dict[str, str] = {}, data_classification_policy: List[str] = None, caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | None = None, to_field: str | None = None, field_to_field: List[List[str]] | Dict[str, str] | None = None, use_query: bool | None = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: Serializer

class unitxt.serializers.DefaultSerializer(__tags__: Dict[str, str] = {}, data_classification_policy: List[str] = None, caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | None = None, to_field: str | None = None, field_to_field: List[List[str]] | Dict[str, str] | None = None, use_query: bool | None = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: Serializer

class unitxt.serializers.DialogSerializer(__tags__: ~typing.Dict[str, str] = {}, data_classification_policy: ~typing.List[str] = None, caching: bool = None, apply_to_streams: ~typing.List[str] = None, dont_apply_to_streams: ~typing.List[str] = None, field: str | None = None, to_field: str | None = None, field_to_field: ~typing.List[~typing.List[str]] | ~typing.Dict[str, str] | None = None, use_query: bool | None = None, process_every_value: bool = False, get_default: ~typing.Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False, serialized_type: object = <function NewType.<locals>.new_type>)

Bases: SingleTypeSerializer

serialized_type()

AbstractField(default: Any = <class ‘unitxt.dataclass.Undefined’>, name: str = None, type: None = None, init: bool = True, also_positional: bool = True, default_factory: Any = None, final: bool = False, abstract: bool = False, required: bool = False, internal: bool = False, origin_cls: None = None, metadata: Dict[str, str] = <factory>)

class unitxt.serializers.ImageSerializer(__tags__: ~typing.Dict[str, str] = {}, data_classification_policy: ~typing.List[str] = None, caching: bool = None, apply_to_streams: ~typing.List[str] = None, dont_apply_to_streams: ~typing.List[str] = None, field: str | None = None, to_field: str | None = None, field_to_field: ~typing.List[~typing.List[str]] | ~typing.Dict[str, str] | None = None, use_query: bool | None = None, process_every_value: bool = False, get_default: ~typing.Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False, serialized_type: object = <class 'unitxt.types.Image'>)

Bases: SingleTypeSerializer

serialized_type

alias of Image

class unitxt.serializers.ListSerializer(__tags__: ~typing.Dict[str, str] = {}, data_classification_policy: ~typing.List[str] = None, caching: bool = None, apply_to_streams: ~typing.List[str] = None, dont_apply_to_streams: ~typing.List[str] = None, field: str | None = None, to_field: str | None = None, field_to_field: ~typing.List[~typing.List[str]] | ~typing.Dict[str, str] | None = None, use_query: bool | None = None, process_every_value: bool = False, get_default: ~typing.Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False, serialized_type: object = <class 'list'>)

Bases: SingleTypeSerializer

serialized_type

alias of list

class unitxt.serializers.MultiTypeSerializer(__tags__: ~typing.Dict[str, str] = {}, data_classification_policy: ~typing.List[str] = None, caching: bool = None, apply_to_streams: ~typing.List[str] = None, dont_apply_to_streams: ~typing.List[str] = None, field: str | None = None, to_field: str | None = None, field_to_field: ~typing.List[~typing.List[str]] | ~typing.Dict[str, str] | None = None, use_query: bool | None = None, process_every_value: bool = False, get_default: ~typing.Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False, serializers: ~typing.List[~unitxt.serializers.SingleTypeSerializer] = [ImageSerializer(__type__='image_serializer', __description__=None, __tags__={}, __id__=None, data_classification_policy=None, _requirements_list=[], caching=None, apply_to_streams=None, dont_apply_to_streams=None, field=None, to_field=None, field_to_field=None, use_query=None, process_every_value=False, get_default=None, not_exist_ok=False, not_exist_do_nothing=False, serialized_type=<class 'unitxt.types.Image'>), TableSerializer(__type__='table_serializer', __description__=None, __tags__={}, __id__=None, data_classification_policy=None, _requirements_list=[], caching=None, apply_to_streams=None, dont_apply_to_streams=None, field=None, to_field=None, field_to_field=None, use_query=None, process_every_value=False, get_default=None, not_exist_ok=False, not_exist_do_nothing=False, serialized_type=<class 'unitxt.types.Table'>), DialogSerializer(__type__='dialog_serializer', __description__=None, __tags__={}, __id__=None, data_classification_policy=None, _requirements_list=[], caching=None, apply_to_streams=None, dont_apply_to_streams=None, field=None, to_field=None, field_to_field=None, use_query=None, process_every_value=False, get_default=None, not_exist_ok=False, not_exist_do_nothing=False, serialized_type=<function NewType.<locals>.new_type>)])

Bases: Serializer

class unitxt.serializers.NumberQuantizingSerializer(__tags__: ~typing.Dict[str, str] = {}, data_classification_policy: ~typing.List[str] = None, caching: bool = None, apply_to_streams: ~typing.List[str] = None, dont_apply_to_streams: ~typing.List[str] = None, field: str | None = None, to_field: str | None = None, field_to_field: ~typing.List[~typing.List[str]] | ~typing.Dict[str, str] | None = None, use_query: bool | None = None, process_every_value: bool = False, get_default: ~typing.Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False, serialized_type: object = <function NewType.<locals>.new_type>, quantum: float | int = 0.1)

Bases: NumberSerializer

serialized_type()

AbstractField(default: Any = <class ‘unitxt.dataclass.Undefined’>, name: str = None, type: None = None, init: bool = True, also_positional: bool = True, default_factory: Any = None, final: bool = False, abstract: bool = False, required: bool = False, internal: bool = False, origin_cls: None = None, metadata: Dict[str, str] = <factory>)

class unitxt.serializers.NumberSerializer(__tags__: ~typing.Dict[str, str] = {}, data_classification_policy: ~typing.List[str] = None, caching: bool = None, apply_to_streams: ~typing.List[str] = None, dont_apply_to_streams: ~typing.List[str] = None, field: str | None = None, to_field: str | None = None, field_to_field: ~typing.List[~typing.List[str]] | ~typing.Dict[str, str] | None = None, use_query: bool | None = None, process_every_value: bool = False, get_default: ~typing.Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False, serialized_type: object = <function NewType.<locals>.new_type>)

Bases: SingleTypeSerializer

serialized_type()

AbstractField(default: Any = <class ‘unitxt.dataclass.Undefined’>, name: str = None, type: None = None, init: bool = True, also_positional: bool = True, default_factory: Any = None, final: bool = False, abstract: bool = False, required: bool = False, internal: bool = False, origin_cls: None = None, metadata: Dict[str, str] = <factory>)

class unitxt.serializers.Serializer(__tags__: Dict[str, str] = {}, data_classification_policy: List[str] = None, caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | None = None, to_field: str | None = None, field_to_field: List[List[str]] | Dict[str, str] | None = None, use_query: bool | None = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: InstanceFieldOperator

class unitxt.serializers.SingleTypeSerializer(__tags__: ~typing.Dict[str, str] = {}, data_classification_policy: ~typing.List[str] = None, caching: bool = None, apply_to_streams: ~typing.List[str] = None, dont_apply_to_streams: ~typing.List[str] = None, field: str | None = None, to_field: str | None = None, field_to_field: ~typing.List[~typing.List[str]] | ~typing.Dict[str, str] | None = None, use_query: bool | None = None, process_every_value: bool = False, get_default: ~typing.Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False, serialized_type: object)

Bases: InstanceFieldOperator

class unitxt.serializers.TableSerializer(__tags__: ~typing.Dict[str, str] = {}, data_classification_policy: ~typing.List[str] = None, caching: bool = None, apply_to_streams: ~typing.List[str] = None, dont_apply_to_streams: ~typing.List[str] = None, field: str | None = None, to_field: str | None = None, field_to_field: ~typing.List[~typing.List[str]] | ~typing.Dict[str, str] | None = None, use_query: bool | None = None, process_every_value: bool = False, get_default: ~typing.Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False, serialized_type: object = <class 'unitxt.types.Table'>)

Bases: SingleTypeSerializer

serialized_type

alias of Table