Class: Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1AutoraterConfig

Inherits:
Object
  • Object
show all
Includes:
Core::Hashable, Core::JsonObjectSupport
Defined in:
lib/google/apis/aiplatform_v1beta1/classes.rb,
lib/google/apis/aiplatform_v1beta1/representations.rb,
lib/google/apis/aiplatform_v1beta1/representations.rb

Overview

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

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(**args) ⇒ GoogleCloudAiplatformV1beta1AutoraterConfig

Returns a new instance of GoogleCloudAiplatformV1beta1AutoraterConfig.



9936
9937
9938
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 9936

def initialize(**args)
   update!(**args)
end

Instance Attribute Details

#autorater_model ⇒ 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` Corresponds to the JSON propertyautoraterModel`

Returns:

  • (String) 


9910
9911
9912
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 9910

def autorater_model
  @autorater_model
end

#flip_enabled ⇒ Boolean Also known as: flip_enabled?

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. Corresponds to the JSON property flipEnabled

Returns:

  • (Boolean) 


9920
9921
9922
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 9920

def flip_enabled
  @flip_enabled
end

#generation_config ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1GenerationConfig

Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. Corresponds to the JSON property generationConfig

Returns:



9928
9929
9930
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 9928

def generation_config
  @generation_config
end

#sampling_count ⇒ Fixnum

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. Corresponds to the JSON property samplingCount

Returns:

  • (Fixnum) 


9934
9935
9936
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 9934

def sampling_count
  @sampling_count
end

Instance Method Details

#update!(**args) ⇒ Object

Update properties of this object



9941
9942
9943
9944
9945
9946
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 9941

def update!(**args)
  @autorater_model = args[:autorater_model] if args.key?(:autorater_model)
  @flip_enabled = args[:flip_enabled] if args.key?(:flip_enabled)
  @generation_config = args[:generation_config] if args.key?(:generation_config)
  @sampling_count = args[:sampling_count] if args.key?(:sampling_count)
end