Skip to content

Base

GeneratorTask

Bases: _Task, GeneratorStep

GeneratorTask is a class that implements the _Task abstract class and adds the GeneratorStep interface to be used as a step in the pipeline.

Attributes:

Name Type Description
llm

the LLM to be used to generate the outputs of the task.
group_generations

whether to group the num_generations generated per input in a list or create a row per generation. Defaults to False.
num_generations

The number of generations to be produced per input.
Source code in src/distilabel/steps/tasks/base.py 
167
168
169
170
171
172
173
174
175
176
177
178
class GeneratorTask(_Task, GeneratorStep):
    """GeneratorTask is a class that implements the `_Task` abstract class and adds the
    `GeneratorStep` interface to be used as a step in the pipeline.

    Attributes:
        llm: the `LLM` to be used to generate the outputs of the task.
        group_generations: whether to group the `num_generations` generated per input in
            a list or create a row per generation. Defaults to `False`.
        num_generations: The number of generations to be produced per input.
    """

    pass

Task

Bases: _Task, Step

Task is a class that implements the _Task abstract class and adds the Step interface to be used as a step in the pipeline.

Attributes:

Name Type Description
llm

the LLM to be used to generate the outputs of the task.
group_generations

whether to group the num_generations generated per input in a list or create a row per generation. Defaults to False.
num_generations

The number of generations to be produced per input.
Source code in src/distilabel/steps/tasks/base.py 
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
class Task(_Task, Step):
    """Task is a class that implements the `_Task` abstract class and adds the `Step`
    interface to be used as a step in the pipeline.

    Attributes:
        llm: the `LLM` to be used to generate the outputs of the task.
        group_generations: whether to group the `num_generations` generated per input in
            a list or create a row per generation. Defaults to `False`.
        num_generations: The number of generations to be produced per input.
    """

    @abstractmethod
    def format_input(self, input: Dict[str, Any]) -> "ChatType":
        """Abstract method to format the inputs of the task. It needs to receive an input
        as a Python dictionary, and generates an OpenAI chat-like list of dicts."""
        pass

    def _format_inputs(self, inputs: List[Dict[str, Any]]) -> List["ChatType"]:
        """Formats the inputs of the task using the `format_input` method.

        Args:
            inputs: A list of Python dictionaries with the inputs of the task.

        Returns:
            A list containing the formatted inputs, which are `ChatType`-like following
            the OpenAI formatting.
        """
        return [self.format_input(input) for input in inputs]

    def process(self, inputs: StepInput) -> "StepOutput":  # type: ignore
        """Processes the inputs of the task and generates the outputs using the LLM.

        Args:
            inputs: A list of Python dictionaries with the inputs of the task.

        Yields:
            A list of Python dictionaries with the outputs of the task.
        """

        formatted_inputs = self._format_inputs(inputs)
        outputs = self.llm.generate(
            inputs=formatted_inputs,
            num_generations=self.num_generations,  # type: ignore
            **self.llm.generation_kwargs,  # type: ignore
        )

        task_outputs = []
        for input, input_outputs in zip(inputs, outputs):
            formatted_outputs = self._format_outputs(input_outputs, inputs)

            if self.group_generations:
                combined = combine_dicts(*formatted_outputs)
                task_outputs.append(
                    {**input, "model_name": self.llm.model_name, **combined}
                )
                continue

            # Create a row per generation
            for formatted_output in formatted_outputs:
                task_outputs.append(
                    {**input, "model_name": self.llm.model_name, **formatted_output}
                )

        yield task_outputs

format_input(input) abstractmethod

Abstract method to format the inputs of the task. It needs to receive an input as a Python dictionary, and generates an OpenAI chat-like list of dicts.

Source code in src/distilabel/steps/tasks/base.py 
112
113
114
115
116
@abstractmethod
def format_input(self, input: Dict[str, Any]) -> "ChatType":
    """Abstract method to format the inputs of the task. It needs to receive an input
    as a Python dictionary, and generates an OpenAI chat-like list of dicts."""
    pass

process(inputs)

Processes the inputs of the task and generates the outputs using the LLM.

Parameters:

Name Type Description Default
inputs StepInput

A list of Python dictionaries with the inputs of the task.

 required

Yields:

Type Description
StepOutput

A list of Python dictionaries with the outputs of the task.
Source code in src/distilabel/steps/tasks/base.py 
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
def process(self, inputs: StepInput) -> "StepOutput":  # type: ignore
    """Processes the inputs of the task and generates the outputs using the LLM.

    Args:
        inputs: A list of Python dictionaries with the inputs of the task.

    Yields:
        A list of Python dictionaries with the outputs of the task.
    """

    formatted_inputs = self._format_inputs(inputs)
    outputs = self.llm.generate(
        inputs=formatted_inputs,
        num_generations=self.num_generations,  # type: ignore
        **self.llm.generation_kwargs,  # type: ignore
    )

    task_outputs = []
    for input, input_outputs in zip(inputs, outputs):
        formatted_outputs = self._format_outputs(input_outputs, inputs)

        if self.group_generations:
            combined = combine_dicts(*formatted_outputs)
            task_outputs.append(
                {**input, "model_name": self.llm.model_name, **combined}
            )
            continue

        # Create a row per generation
        for formatted_output in formatted_outputs:
            task_outputs.append(
                {**input, "model_name": self.llm.model_name, **formatted_output}
            )

    yield task_outputs