Task Typing¶
ChatType = List[ChatItem]
module-attribute
¶
ChatType is a type alias for a list
of dict
s following the OpenAI conversational format.
FormattedInput = Union[StandardInput, StructuredInput]
module-attribute
¶
FormattedInput is an alias for the union of StandardInput
and StructuredInput
as generated by format_input
and expected by the LLM
s.
StandardInput = ChatType
module-attribute
¶
StandardInput is an alias for ChatType that defines the default / standard input produced by format_input
.
StructuredInput = Tuple[StandardInput, Union[StructuredOutputType, None]]
module-attribute
¶
StructuredInput defines a type produced by format_input
when using either StructuredGeneration
or a subclass of it.
StructuredOutputType = Union[OutlinesStructuredOutputType, InstructorStructuredOutputType]
module-attribute
¶
StructuredOutputType is an alias for the union of OutlinesStructuredOutputType
and InstructorStructuredOutputType
.
InstructorStructuredOutputType
¶
Bases: TypedDict
TypedDict to represent the structured output configuration from instructor
.
Source code in src/distilabel/steps/tasks/typing.py
max_retries: int
instance-attribute
¶
Number of times to reask the model in case of error, if not set will default to the model's default.
mode: Optional[str]
instance-attribute
¶
Generation mode. Take a look at instructor.Mode
for more information, if not informed it will
be determined automatically.
schema: Union[Type[BaseModel], Dict[str, Any]]
instance-attribute
¶
The schema to use for the structured output, a pydantic.BaseModel
class.
OutlinesStructuredOutputType
¶
Bases: TypedDict
TypedDict to represent the structured output configuration from outlines
.
Source code in src/distilabel/steps/tasks/typing.py
format: Literal['json', 'regex']
instance-attribute
¶
One of "json" or "regex".
schema: Union[str, Type[BaseModel], Dict[str, Any]]
instance-attribute
¶
The schema to use for the structured output. If "json", it
can be a pydantic.BaseModel class, or the schema as a string,
as obtained from model_to_schema(BaseModel)
, if "regex", it
should be a regex pattern as a string.
whitespace_pattern: Optional[Union[str, List[str]]] = None
class-attribute
instance-attribute
¶
If "json" corresponds to a string or a list of
strings with a pattern (doesn't impact string literals).
For example, to allow only a single space or newline with
whitespace_pattern=r"[
]?"