Class AutoraterConfig (1.93.0)

AutoraterConfig(mapping=None, *, ignore_unknown_fields=False, **kwargs)

The configs for autorater. This is applicable to both EvaluateInstances and EvaluateDataset.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

Attributes

Name Description
sampling_count int
Optional. Number of samples for each instance in the dataset. If not specified, the default is 4. Minimum value is 1, maximum value is 32. This field is a member of oneof_ _sampling_count.
flip_enabled bool
Optional. Whether to flip the candidate and baseline responses. This is only applicable to the pairwise metric. If enabled, also provide PairwiseMetricSpec.candidate_response_field_name and PairwiseMetricSpec.baseline_response_field_name. When rendering PairwiseMetricSpec.metric_prompt_template, the candidate and baseline fields will be flipped for half of the samples to reduce bias. This field is a member of oneof_ _flip_enabled.
autorater_model str
Optional. The fully qualified name of the publisher model or tuned autorater endpoint to use. Publisher model format: projects/{project}/locations/{location}/publishers/*/models/* Tuned model endpoint format: projects/{project}/locations/{location}/endpoints/{endpoint}

Methods

AutoraterConfig

AutoraterConfig(mapping=None, *, ignore_unknown_fields=False, **kwargs)

The configs for autorater. This is applicable to both EvaluateInstances and EvaluateDataset.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields