Class: Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1EvaluationRunEvaluationConfig

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 Evalution configuration used for the evaluation run.

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(**args) ⇒ GoogleCloudAiplatformV1beta1EvaluationRunEvaluationConfig

Returns a new instance of GoogleCloudAiplatformV1beta1EvaluationRunEvaluationConfig.



18187
18188
18189
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 18187

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

Instance Attribute Details

#autorater_config ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1EvaluationRunEvaluationConfigAutoraterConfig

The autorater config used for the evaluation run. Corresponds to the JSON property autoraterConfig

Returns:



18147
18148
18149
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 18147

def autorater_config
  @autorater_config
end

#dataset_custom_metrics ⇒ Array<Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1DatasetCustomMetric>

Optional. Specifications for custom dataset-level aggregations. Corresponds to the JSON property datasetCustomMetrics

Returns:



18152
18153
18154
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 18152

def dataset_custom_metrics
  @dataset_custom_metrics
end

#loss_analysis_config ⇒ Array<Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1LossAnalysisConfig>

Optional. Specifications for loss analysis. Each config can be specified for one metric. Corresponds to the JSON property lossAnalysisConfig

Returns:



18158
18159
18160
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 18158

def loss_analysis_config
  @loss_analysis_config
end

#metrics ⇒ Array<Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1EvaluationRunMetric>

Optional. The metrics to be calculated in the evaluation run. Required when analysis_configs is not set. Corresponds to the JSON property metrics

Returns:



18164
18165
18166
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 18164

def metrics
  @metrics
end

#output_config ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1EvaluationRunEvaluationConfigOutputConfig

The output config for the evaluation run. Corresponds to the JSON property outputConfig

Returns:



18169
18170
18171
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 18169

def output_config
  @output_config
end

#prompt_template ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1EvaluationRunEvaluationConfigPromptTemplate

Prompt template used for inference. Corresponds to the JSON property promptTemplate

Returns:



18174
18175
18176
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 18174

def prompt_template
  @prompt_template
end

#rubric_configs ⇒ Array<Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1EvaluationRubricConfig>

Optional. The rubric configs for the evaluation run. They are used to generate rubrics which can be used by rubric-based metrics. Multiple rubric configs can be specified for rubric generation but only one rubric config can be used for a rubric-based metric. If more than one rubric config is provided, the evaluation metric must specify a rubric group key. Note that if a generation spec is specified on both a rubric config and an evaluation metric, the rubrics generated for the metric will be used for evaluation. Corresponds to the JSON property rubricConfigs

Returns:



18185
18186
18187
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 18185

def rubric_configs
  @rubric_configs
end

Instance Method Details

#update!(**args) ⇒ Object

Update properties of this object



18192
18193
18194
18195
18196
18197
18198
18199
18200
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 18192

def update!(**args)
  @autorater_config = args[:autorater_config] if args.key?(:autorater_config)
  @dataset_custom_metrics = args[:dataset_custom_metrics] if args.key?(:dataset_custom_metrics)
  @loss_analysis_config = args[:loss_analysis_config] if args.key?(:loss_analysis_config)
  @metrics = args[:metrics] if args.key?(:metrics)
  @output_config = args[:output_config] if args.key?(:output_config)
  @prompt_template = args[:prompt_template] if args.key?(:prompt_template)
  @rubric_configs = args[:rubric_configs] if args.key?(:rubric_configs)
end