Class: Google::Apis::AiplatformV1::GoogleCloudAiplatformV1EvaluationResult

Inherits:
Object
  • Object
show all
Includes:
Core::Hashable, Core::JsonObjectSupport
Defined in:
lib/google/apis/aiplatform_v1/classes.rb,
lib/google/apis/aiplatform_v1/representations.rb,
lib/google/apis/aiplatform_v1/representations.rb

Overview

Evaluation result.

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(**args) ⇒ GoogleCloudAiplatformV1EvaluationResult

Returns a new instance of GoogleCloudAiplatformV1EvaluationResult.



10974
10975
10976
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 10974

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

Instance Attribute Details

#candidate_results ⇒ Array<Google::Apis::AiplatformV1::GoogleCloudAiplatformV1CandidateResult>

Optional. The results for the metric. Corresponds to the JSON property candidateResults

Returns:



10939
10940
10941
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 10939

def candidate_results
  @candidate_results
end

#evaluation_request ⇒ String

Required. The request item that was evaluated. Format: projects/project/ locations/location/evaluationItems/evaluation_item Corresponds to the JSON property evaluationRequest

Returns:

  • (String) 


10945
10946
10947
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 10945

def evaluation_request
  @evaluation_request
end

#evaluation_run ⇒ String

Required. The evaluation run that was used to generate the result. Format: projects/project/locations/location/evaluationRuns/evaluation_run Corresponds to the JSON property evaluationRun

Returns:

  • (String) 


10951
10952
10953
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 10951

def evaluation_run
  @evaluation_run
end

#metadata ⇒ Object

Optional. Metadata about the evaluation result. Corresponds to the JSON property metadata

Returns:

  • (Object) 


10956
10957
10958
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 10956

def metadata
  @metadata
end

#metric ⇒ String

Required. The metric that was evaluated. Corresponds to the JSON property metric

Returns:

  • (String) 


10961
10962
10963
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 10961

def metric
  @metric
end

#request ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1EvaluationRequest

A single evaluation request supporting input for both single-turn model generation and multi-turn agent execution traces. Valid input modes: 1. Inference Mode: prompt is set (containing text or AgentData context). 2. Offline Eval Mode: prompt is unset, and candidate_responses contains agent_data (the completed execution trace). Validation Rule: Either prompt must be set, OR at least one of the candidate_responses must contain agent_data. Corresponds to the JSON property request

Returns:



10972
10973
10974
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 10972

def request
  @request
end

Instance Method Details

#update!(**args) ⇒ Object

Update properties of this object



10979
10980
10981
10982
10983
10984
10985
10986
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 10979

def update!(**args)
  @candidate_results = args[:candidate_results] if args.key?(:candidate_results)
  @evaluation_request = args[:evaluation_request] if args.key?(:evaluation_request)
  @evaluation_run = args[:evaluation_run] if args.key?(:evaluation_run)
  @metadata = args[:metadata] if args.key?(:metadata)
  @metric = args[:metric] if args.key?(:metric)
  @request = args[:request] if args.key?(:request)
end