Schema
AggregationFunction
¶
ConfidenceCacheEntry
¶
Bases: BaseModel
Source code in src/autolabel/schema.py
Dataset
¶
Bases: BaseModel
Contains Dataset parameters, including input file path, indexes for state management (e.g. job batching and retries), and a unique ID
Source code in src/autolabel/schema.py
create_id(dataset, config, start_index, max_items)
classmethod
¶
Generates a unique ID for the given Dataset configuration Args: dataset: either 1) input file name or 2) pandas Dataframe config: AutolabelConfig object containing project settings start_index: index to begin labeling job at (used for job batching, retries, state management) max_items: number of data points to label, beginning at start_index
Returns:
Name | Type | Description |
---|---|---|
filehash |
str
|
a unique ID generated from an MD5 hash of the functions parameters |
Source code in src/autolabel/schema.py
ErrorType
¶
Bases: str
, Enum
Enum of supported error types
Source code in src/autolabel/schema.py
FewShotAlgorithm
¶
Bases: str
, Enum
Enum of supported algorithms for choosing which examples to provide the LLM in its instruction prompt
Source code in src/autolabel/schema.py
GenerationCacheEntry
¶
Bases: BaseModel
Source code in src/autolabel/schema.py
LLMAnnotation
¶
Bases: BaseModel
Contains label information of a given data point, including the generated label, the prompt given to the LLM, and the LLMs response. Optionally includes a confidence_score if supported by the model
Source code in src/autolabel/schema.py
LabelingError
¶
Bases: BaseModel
Contains information about an error that occurred during the labeling process
Source code in src/autolabel/schema.py
MetricResult
¶
MetricType
¶
Bases: str
, Enum
Enum of supported performance metrics. Some metrics are always available (task agnostic), while others are only supported by certain types of tasks
Source code in src/autolabel/schema.py
ModelProvider
¶
Bases: str
, Enum
Enum containing all LLM providers currently supported by autolabeler
Source code in src/autolabel/schema.py
RefuelLLMResult
¶
Bases: BaseModel
List of generated outputs. This is a List[List[]] because each input could have multiple candidate generations.
Source code in src/autolabel/schema.py
costs: Optional[List[float]] = []
class-attribute
instance-attribute
¶
Latencies incurred during the labeling job
errors: List[Optional[LabelingError]]
instance-attribute
¶
Costs incurred during the labeling job
generations: List[List[Union[Generation, ChatGeneration]]]
instance-attribute
¶
Errors encountered while running the labeling job
TaskType
¶
Bases: str
, Enum
Enum containing all the types of tasks that autolabeler currently supports