unitxt.templates module

class unitxt.templates.ApplyRandomTemplate(__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, demos_field: str | None = None, templates: ~typing.List[~unitxt.templates.Template])

Bases: ApplyTemplate

class unitxt.templates.ApplySingleTemplate(__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, demos_field: str | None = None, template: ~unitxt.templates.Template)

Bases: ApplyTemplate

class unitxt.templates.ApplyTemplate(__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, demos_field: str | None = None)

Bases: InstanceOperator

class unitxt.templates.DialogFieldsData(__tags__: ~typing.Dict[str, str] = {}, data_classification_policy: ~typing.List[str] = None, user_role_label: str, assistant_role_label: str, system_role_label: str, dialog_field: str)

Bases: Artifact

class unitxt.templates.DialogPairwiseChoiceTemplate(__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, skip_rendered_instance: bool = True, postprocessors: ~typing.List[str] = ['processors.to_string_stripped'], instruction: str = '', target_prefix: str = '', title_fields: ~typing.List[str] = [], serializer: ~unitxt.serializers.Serializer = MultiTypeSerializer(__type__='multi_type_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, serializers=[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>), ListSerializer(__type__='list_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 'list'>)]), output_format: str = None, input_format: str, choice_a_field: str, choice_b_field: str, answer_field: str, choice_a_label: str, choice_b_label: str, choice_tie_label: str, shuffle: bool, dialog_fields: ~typing.List[~unitxt.templates.DialogFieldsData], turns_separator: str = '\n\n', label_separator: str = ' ')

Bases: DialogTemplate, PairwiseChoiceTemplate

class unitxt.templates.DialogTemplate(__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, skip_rendered_instance: bool = True, postprocessors: ~typing.List[str] = ['processors.to_string_stripped'], instruction: str = '', target_prefix: str = '', title_fields: ~typing.List[str] = [], serializer: ~unitxt.serializers.Serializer = MultiTypeSerializer(__type__='multi_type_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, serializers=[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>), ListSerializer(__type__='list_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 'list'>)]), output_format: str = None, input_format: str, dialog_fields: ~typing.List[~unitxt.templates.DialogFieldsData], turns_separator: str = '\n\n', label_separator: str = ' ')

Bases: InputOutputTemplate

class unitxt.templates.InputFormatTemplate(__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, skip_rendered_instance: bool = True, postprocessors: ~typing.List[str] = ['processors.to_string_stripped'], instruction: str = '', target_prefix: str = '', title_fields: ~typing.List[str] = [], serializer: ~unitxt.serializers.Serializer = MultiTypeSerializer(__type__='multi_type_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, serializers=[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>), ListSerializer(__type__='list_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 'list'>)]), input_format: str)

Bases: Template

class unitxt.templates.InputOutputTemplate(__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, skip_rendered_instance: bool = True, postprocessors: ~typing.List[str] = ['processors.to_string_stripped'], instruction: str = '', target_prefix: str = '', title_fields: ~typing.List[str] = [], serializer: ~unitxt.serializers.Serializer = MultiTypeSerializer(__type__='multi_type_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, serializers=[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>), ListSerializer(__type__='list_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 'list'>)]), output_format: str = None, input_format: str)

Bases: InputFormatTemplate, OutputFormatTemplate

Generate field ‘source’ from fields designated as input, and fields ‘target’ and ‘references’ from fields designated as output, of the processed instance.

Args specify the formatting strings with which to glue together the input and reference fields of the processed instance into one string (‘source’ and ‘target’), and into a list of strings (‘references’).

class unitxt.templates.InputOutputTemplateWithCustomTarget(__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, skip_rendered_instance: bool = True, postprocessors: ~typing.List[str] = ['processors.to_string_stripped'], instruction: str = '', target_prefix: str = '', title_fields: ~typing.List[str] = [], serializer: ~unitxt.serializers.Serializer = MultiTypeSerializer(__type__='multi_type_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, serializers=[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>), ListSerializer(__type__='list_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 'list'>)]), output_format: str = None, input_format: str, reference: str)

Bases: InputOutputTemplate

class unitxt.templates.KeyValTemplate(__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, skip_rendered_instance: bool = True, postprocessors: ~typing.List[str] = ['processors.to_string_stripped'], instruction: str = '', target_prefix: str = '', title_fields: ~typing.List[str] = [], serializer: ~unitxt.serializers.Serializer = MultiTypeSerializer(__type__='multi_type_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, serializers=[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>), ListSerializer(__type__='list_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 'list'>)]), pairs_separator: str = ', ', key_val_separator: str = ': ', use_keys_for_inputs: bool = True, outputs_key_val_separator: str = ': ', use_keys_for_outputs: bool = False)

Bases: Template

Generate field ‘source’ from fields designated as input, and fields ‘target’ and ‘references’ from fields designated as output, of the processed instance.

Args specify with what separators to glue together the input and output designated fields of the processed instance into one string (‘source’ and ‘target’), and into a list of strings (‘references’).

class unitxt.templates.MultiLabelTemplate(__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, skip_rendered_instance: bool = True, postprocessors: ~typing.List[str] = ['processors.to_list_by_comma'], instruction: str = '', target_prefix: str = '', title_fields: ~typing.List[str] = [], serializer: ~unitxt.serializers.Serializer = MultiTypeSerializer(__type__='multi_type_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, serializers=[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>), ListSerializer(__type__='list_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 'list'>)]), output_format: str = '{labels}', input_format: str, labels_field: str = 'labels', labels_separator: str = ', ', empty_label: str = 'None')

Bases: InputOutputTemplate

postprocessors: List[str] = ['processors.to_list_by_comma']
class unitxt.templates.MultiReferenceTemplate(__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, skip_rendered_instance: bool = True, postprocessors: ~typing.List[str] = ['processors.to_string_stripped'], instruction: str = '', target_prefix: str = '', title_fields: ~typing.List[str] = [], serializer: ~unitxt.serializers.Serializer = MultiTypeSerializer(__type__='multi_type_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, serializers=[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>)]), output_format: str = None, input_format: str, references_field: str = 'references', random_reference: bool = False)

Bases: InputOutputTemplate

class unitxt.templates.MultipleChoiceTemplate(__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, skip_rendered_instance: bool = True, postprocessors: ~typing.List[str] = ['processors.to_string_stripped'], instruction: str = '', target_prefix: str = '', title_fields: ~typing.List[str] = [], serializer: ~unitxt.serializers.Serializer = MultiTypeSerializer(__type__='multi_type_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, serializers=[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>), ListSerializer(__type__='list_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 'list'>)]), input_format: str, choices_field: str = 'choices', target_field: str = 'label', choices_separator: str = ', ', source_choice_format: str = '{choice_numeral}. {choice_text}', target_choice_format: str = '{choice_numeral}', enumerator: str = 'capitals', shuffle_choices: bool = False)

Bases: InputFormatTemplate

Formats the input (that specifies the question), the multiple choices to select the answer from, and specifies the field with the correct answer.

class unitxt.templates.OutputFormatTemplate(__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, skip_rendered_instance: bool = True, postprocessors: ~typing.List[str] = ['processors.to_string_stripped'], instruction: str = '', target_prefix: str = '', title_fields: ~typing.List[str] = [], serializer: ~unitxt.serializers.Serializer = MultiTypeSerializer(__type__='multi_type_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, serializers=[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>), ListSerializer(__type__='list_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 'list'>)]), output_format: str = None)

Bases: Template

class unitxt.templates.OutputQuantizingTemplate(__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, skip_rendered_instance: bool = True, postprocessors: ~typing.List[str] = ['processors.to_string_stripped'], instruction: str = '', target_prefix: str = '', title_fields: ~typing.List[str] = [], serializer: ~unitxt.serializers.MultiTypeSerializer = MultiTypeSerializer(__type__='multi_type_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, serializers=[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>)]), output_format: str = None, input_format: str, quantum: float | int = 0.1)

Bases: InputOutputTemplate

class unitxt.templates.PairwiseChoiceTemplate(__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, skip_rendered_instance: bool = True, postprocessors: ~typing.List[str] = ['processors.to_string_stripped'], instruction: str = '', target_prefix: str = '', title_fields: ~typing.List[str] = [], serializer: ~unitxt.serializers.Serializer = MultiTypeSerializer(__type__='multi_type_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, serializers=[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>), ListSerializer(__type__='list_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 'list'>)]), output_format: str = None, input_format: str, choice_a_field: str, choice_b_field: str, answer_field: str, choice_a_label: str, choice_b_label: str, choice_tie_label: str, shuffle: bool)

Bases: InputOutputTemplate

PairwiseChoiceTemplate.

Requirements:

The answer field value should be of type Literal[“choice_a”, “choice_b”, “tie”]

Parameters:
  • choice_a_field (str) – The field which contains choice_a value

  • choice_b_field (str) – The field which contains choice_b value

  • answer_field (str) – The field which contains the answer value. Should be of type Literal[“choice_1”, “choice_2”, “tie”]

  • choice_a_label (str) – The label of choice A answer as it is verbalized in the template.

  • choice_b_label (str) – The label of choice B answer as it is verbalized in the template.

  • choice_tie_label (str) – The label of a tie answer as it should be verbalized in the template.

  • shuffle (bool) – whether to shuffle the choices or not. This is done to take into account position bias.

shuffle: 50% of the time:
  1. The values of choice_a_field and choice_b_field will be swapped.

  2. If the values of answer_field is choice_a_label, set it to choice_b_label.

    Else if the values of answer_field is choice_b_label, set it to choice_a_label. Else if the value of answer_field is choice_tie_label, do nothing.

class unitxt.templates.PairwiseComparativeRatingTemplate(__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, skip_rendered_instance: bool = True, postprocessors: ~typing.List[str] = ['processors.to_string_stripped'], instruction: str = '', target_prefix: str = '', title_fields: ~typing.List[str] = [], serializer: ~unitxt.serializers.Serializer = MultiTypeSerializer(__type__='multi_type_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, serializers=[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>), ListSerializer(__type__='list_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 'list'>)]), output_format: str = None, input_format: str, choice_a_field: str, choice_b_field: str, choice_a_id_field: str, choice_b_id_field: str, answer_field: str, shuffle: bool)

Bases: InputOutputTemplate

PairwiseChoiceTemplate.

Parameters:
  • choice_a_field (str) – The field which contains choice_a value

  • choice_b_field (str) – The field which contains choice_b value

  • answer_field (str) – The field which contains the answer value. The value should be an int. Positive for preferring choice_a, and negative for preferring choice_b

  • shuffle (bool) – whether to shuffle the choices or not. This is done to take into account position bias.

shuffle: 50% of the time:
  1. The values of choice_a_field and choice_b_field will be swapped.

  2. Replace the values of answer_field with its mapped value according to the reverse_preference_map Dict.

class unitxt.templates.SpanLabelingBaseTemplate(__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, skip_rendered_instance: bool = True, postprocessors: ~typing.List[str] = ['processors.to_list_by_comma'], instruction: str = '', target_prefix: str = '', title_fields: ~typing.List[str] = [], serializer: ~unitxt.serializers.Serializer = MultiTypeSerializer(__type__='multi_type_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, serializers=[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>), ListSerializer(__type__='list_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 'list'>)]), output_format: str = '{labels}', input_format: str, labels_field: str = 'labels', labels_separator: str = ', ', empty_label: str = 'None', spans_starts_field: str = 'spans_starts', spans_ends_field: str = 'spans_ends', text_field: str = 'text', labels_support: list = None)

Bases: MultiLabelTemplate

class unitxt.templates.SpanLabelingJsonTemplate(__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, skip_rendered_instance: bool = True, postprocessors: ~typing.List[str] = ['processors.load_json', 'processors.dict_of_lists_to_value_key_pairs'], instruction: str = '', target_prefix: str = '', title_fields: ~typing.List[str] = [], serializer: ~unitxt.serializers.Serializer = MultiTypeSerializer(__type__='multi_type_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, serializers=[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>), ListSerializer(__type__='list_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 'list'>)]), output_format: str = '{labels}', input_format: str, labels_field: str = 'labels', labels_separator: str = ', ', empty_label: str = 'None', spans_starts_field: str = 'spans_starts', spans_ends_field: str = 'spans_ends', text_field: str = 'text', labels_support: list = None)

Bases: SpanLabelingBaseTemplate

postprocessors: List[str] = ['processors.load_json', 'processors.dict_of_lists_to_value_key_pairs']
class unitxt.templates.SpanLabelingTemplate(__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, skip_rendered_instance: bool = True, postprocessors: ~typing.List[str] = ['processors.to_span_label_pairs'], instruction: str = '', target_prefix: str = '', title_fields: ~typing.List[str] = [], serializer: ~unitxt.serializers.Serializer = MultiTypeSerializer(__type__='multi_type_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, serializers=[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>), ListSerializer(__type__='list_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 'list'>)]), output_format: str = '{labels}', input_format: str, labels_field: str = 'labels', labels_separator: str = ', ', empty_label: str = 'None', spans_starts_field: str = 'spans_starts', spans_ends_field: str = 'spans_ends', text_field: str = 'text', labels_support: list = None, span_label_format: str = '{span}: {label}', escape_characters: ~typing.List[str] = [':', ','])

Bases: SpanLabelingBaseTemplate

escape_characters: List[str] = [':', ',']
postprocessors: List[str] = ['processors.to_span_label_pairs']
class unitxt.templates.Template(__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, skip_rendered_instance: bool = True, postprocessors: ~typing.List[str] = ['processors.to_string_stripped'], instruction: str = '', target_prefix: str = '', title_fields: ~typing.List[str] = [], serializer: ~unitxt.serializers.Serializer = MultiTypeSerializer(__type__='multi_type_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, serializers=[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>), ListSerializer(__type__='list_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 'list'>)]))

Bases: InstanceOperator

The role of template is to take the fields of every instance and verbalize it.

Meaning the template is taking the instance and generating source, target and references.

Parameters:
  • skip_rendered_instance (bool) – if “source”, “target”, and “references” are already defined fields in the instance, skip its processing

  • postprocessors – a list of strings being artifact names of text processors, to be applied on the model output

  • instruction – a formatting string that yields an instruction with potential participation of values from the “input_fields” part of the instance

  • target_prefix – a string to be used to format the prompt. Not a formatting string.

exception unitxt.templates.TemplateFormatKeyError(template, data, data_type, format_str, format_name)

Bases: UnitxtError

class unitxt.templates.TemplatesDict(__tags__: ~typing.Dict[str, str] = {}, data_classification_policy: ~typing.List[str] = None, items: ~typing.Dict[str, ~unitxt.artifact.Artifact])

Bases: DictCollection

class unitxt.templates.TemplatesList(__tags__: ~typing.Dict[str, str] = {}, data_classification_policy: ~typing.List[str] = None, items: ~typing.List[~unitxt.artifact.Artifact])

Bases: ListCollection

class unitxt.templates.YesNoTemplate(__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, skip_rendered_instance: bool = True, postprocessors: ~typing.List[str] = ['processors.to_string_stripped'], instruction: str = '', target_prefix: str = '', title_fields: ~typing.List[str] = [], serializer: ~unitxt.serializers.Serializer = MultiTypeSerializer(__type__='multi_type_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, serializers=[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>), ListSerializer(__type__='list_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 'list'>)]), input_format: str = None, class_field: str = None, label_field: str = None, yes_answer: str = 'Yes', no_answer: str = 'No')

Bases: InputFormatTemplate

A template for generating binary Yes/No questions asking whether an input text is of a specific class.

input_format:

Defines the format of the question.

class_field:

Defines the field that contains the name of the class that this template asks of.

label_field:

Defines the field which contains the true label of the input text. If a gold label is equal to the value in class_name, then the correct output is self.yes_answer (by default, “Yes”). Otherwise the correct output is self.no_answer (by default, “No”).

yes_answer:

The output value for when the gold label equals self.class_name. Defaults to “Yes”.

no_answer:

The output value for when the gold label differs from self.class_name. Defaults to “No”.

unitxt.templates.escape_chars(s, chars_to_escape)
unitxt.templates.random() x in the interval [0, 1).