Class: Google::Apis::AiplatformV1::GoogleCloudAiplatformV1Candidate

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

A response candidate generated from the model.

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(**args) ⇒ GoogleCloudAiplatformV1Candidate

Returns a new instance of GoogleCloudAiplatformV1Candidate.



3707
3708
3709
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 3707

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) 


3645
3646
3647
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 3645

def avg_logprobs
  @avg_logprobs
end

#citation_metadata ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1CitationMetadata

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

Returns:



3650
3651
3652
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 3650

def citation_metadata
  @citation_metadata
end

#content ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1Content

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:



3657
3658
3659
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 3657

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) 


3663
3664
3665
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 3663

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) 


3669
3670
3671
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 3669

def finish_reason
  @finish_reason
end

#grounding_metadata ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1GroundingMetadata

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:



3676
3677
3678
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 3676

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) 


3683
3684
3685
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 3683

def index
  @index
end

#logprobs_result ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1LogprobsResult

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:



3693
3694
3695
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 3693

def logprobs_result
  @logprobs_result
end

#safety_ratings ⇒ Array<Google::Apis::AiplatformV1::GoogleCloudAiplatformV1SafetyRating>

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:



3699
3700
3701
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 3699

def safety_ratings
  @safety_ratings
end

#url_context_metadata ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1UrlContextMetadata

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:



3705
3706
3707
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 3705

def url_context_metadata
  @url_context_metadata
end

Instance Method Details

#update!(**args) ⇒ Object

Update properties of this object



3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 3712

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