Class: Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1Candidate

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

A response candidate generated from the model.

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(**args) ⇒ GoogleCloudAiplatformV1beta1Candidate

Returns a new instance of GoogleCloudAiplatformV1beta1Candidate.



10673
10674
10675
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 10673

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

Instance Attribute Details

#avg_logprobs ⇒ Float

Output only. The average log probability of the tokens in this candidate. This is a length-normalized score that can be used to compare the quality of candidates of different lengths. A higher average log probability suggests a more confident and coherent response. Corresponds to the JSON property avgLogprobs

Returns:

  • (Float) 


10611
10612
10613
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 10611

def avg_logprobs
  @avg_logprobs
end

#citation_metadata ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1CitationMetadata

A collection of citations that apply to a piece of generated content. Corresponds to the JSON property citationMetadata

Returns:



10616
10617
10618
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 10616

def citation_metadata
  @citation_metadata
end

#content ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1Content

The structured data content of a message. A Content message contains a role field, which indicates the producer of the content, and a parts field, which contains the multi-part data of the message. Corresponds to the JSON property content

Returns:



10623
10624
10625
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 10623

def content
  @content
end

#finish_message ⇒ String

Output only. Describes the reason the model stopped generating tokens in more detail. This field is returned only when finish_reason is set. Corresponds to the JSON property finishMessage

Returns:

  • (String) 


10629
10630
10631
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 10629

def finish_message
  @finish_message
end

#finish_reason ⇒ String

Output only. The reason why the model stopped generating tokens. If empty, the model has not stopped generating. Corresponds to the JSON property finishReason

Returns:

  • (String) 


10635
10636
10637
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 10635

def finish_reason
  @finish_reason
end

#grounding_metadata ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1GroundingMetadata

Information about the sources that support the content of a response. When grounding is enabled, the model returns citations for claims in the response. This object contains the retrieved sources. Corresponds to the JSON property groundingMetadata

Returns:



10642
10643
10644
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 10642

def grounding_metadata
  @grounding_metadata
end

#index ⇒ Fixnum

Output only. The 0-based index of this candidate in the list of generated responses. This is useful for distinguishing between multiple candidates when candidate_count > 1. Corresponds to the JSON property index

Returns:

  • (Fixnum) 


10649
10650
10651
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 10649

def index
  @index
end

#logprobs_result ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1LogprobsResult

The log probabilities of the tokens generated by the model. This is useful for understanding the model's confidence in its predictions and for debugging. For example, you can use log probabilities to identify when the model is making a less confident prediction or to explore alternative responses that the model considered. A low log probability can also indicate that the model is " hallucinating" or generating factually incorrect information. Corresponds to the JSON property logprobsResult

Returns:



10659
10660
10661
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 10659

def logprobs_result
  @logprobs_result
end

#safety_ratings ⇒ Array<Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1SafetyRating>

Output only. A list of ratings for the safety of a response candidate. There is at most one rating per category. Corresponds to the JSON property safetyRatings

Returns:



10665
10666
10667
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 10665

def safety_ratings
  @safety_ratings
end

#url_context_metadata ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1UrlContextMetadata

Metadata returned when the model uses the url_context tool to get information from a user-provided URL. Corresponds to the JSON property urlContextMetadata

Returns:



10671
10672
10673
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 10671

def url_context_metadata
  @url_context_metadata
end

Instance Method Details

#update!(**args) ⇒ Object

Update properties of this object



10678
10679
10680
10681
10682
10683
10684
10685
10686
10687
10688
10689
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 10678

def update!(**args)
  @avg_logprobs = args[:avg_logprobs] if args.key?(:avg_logprobs)
  @citation_metadata = args[:citation_metadata] if args.key?(:citation_metadata)
  @content = args[:content] if args.key?(:content)
  @finish_message = args[:finish_message] if args.key?(:finish_message)
  @finish_reason = args[:finish_reason] if args.key?(:finish_reason)
  @grounding_metadata = args[:grounding_metadata] if args.key?(:grounding_metadata)
  @index = args[:index] if args.key?(:index)
  @logprobs_result = args[:logprobs_result] if args.key?(:logprobs_result)
  @safety_ratings = args[:safety_ratings] if args.key?(:safety_ratings)
  @url_context_metadata = args[:url_context_metadata] if args.key?(:url_context_metadata)
end