Vertex AI V1 API - Class Google::Cloud::AIPlatform::V1::AutoraterConfig (v1.40.0)

Reference documentation and code samples for the Vertex AI V1 API class Google::Cloud::AIPlatform::V1::AutoraterConfig.

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

Inherits

  • Object

Extended By

  • Google::Protobuf::MessageExts::ClassMethods

Includes

  • Google::Protobuf::MessageExts

Methods

#autorater_model

def autorater_model() -> ::String
Returns
  • (::String) — 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}

#autorater_model=

def autorater_model=(value) -> ::String
Parameter
  • value (::String) — 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}

Returns
  • (::String) — 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}

#flip_enabled

def flip_enabled() -> ::Boolean
Returns
  • (::Boolean) — Optional. Default is true. 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.

#flip_enabled=

def flip_enabled=(value) -> ::Boolean
Parameter
  • value (::Boolean) — Optional. Default is true. 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.
Returns
  • (::Boolean) — Optional. Default is true. 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.

#generation_config

def generation_config() -> ::Google::Cloud::AIPlatform::V1::GenerationConfig
Returns

#generation_config=

def generation_config=(value) -> ::Google::Cloud::AIPlatform::V1::GenerationConfig
Parameter
Returns

#sampling_count

def sampling_count() -> ::Integer
Returns
  • (::Integer) — 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.

#sampling_count=

def sampling_count=(value) -> ::Integer
Parameter
  • value (::Integer) — 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.
Returns
  • (::Integer) — 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.