Class: Google::Apis::AiplatformV1::GoogleCloudAiplatformV1GenerationConfig

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

Generation config.

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(**args) ⇒ GoogleCloudAiplatformV1GenerationConfig

Returns a new instance of GoogleCloudAiplatformV1GenerationConfig.



10478
10479
10480
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 10478

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

Instance Attribute Details

#candidate_count ⇒ Fixnum

Optional. Number of candidates to generate. Corresponds to the JSON property candidateCount

Returns:

  • (Fixnum) 


10415
10416
10417
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 10415

def candidate_count
  @candidate_count
end

#frequency_penalty ⇒ Float

Optional. Frequency penalties. Corresponds to the JSON property frequencyPenalty

Returns:

  • (Float) 


10420
10421
10422
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 10420

def frequency_penalty
  @frequency_penalty
end

#max_output_tokens ⇒ Fixnum

Optional. The maximum number of output tokens to generate per message. Corresponds to the JSON property maxOutputTokens

Returns:

  • (Fixnum) 


10425
10426
10427
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 10425

def max_output_tokens
  @max_output_tokens
end

#presence_penalty ⇒ Float

Optional. Positive penalties. Corresponds to the JSON property presencePenalty

Returns:

  • (Float) 


10430
10431
10432
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 10430

def presence_penalty
  @presence_penalty
end

#response_mime_type ⇒ String

Optional. Output response mimetype of the generated candidate text. Supported mimetype: - text/plain: (default) Text output. - application/json: JSON response in the candidates. The model needs to be prompted to output the appropriate response type, otherwise the behavior is undefined. This is a preview feature. Corresponds to the JSON property responseMimeType

Returns:

  • (String) 


10439
10440
10441
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 10439

def response_mime_type
  @response_mime_type
end

#response_schema ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1Schema

Schema is used to define the format of input/output data. Represents a select subset of an OpenAPI 3.0 schema object. More fields may be added in the future as needed. Corresponds to the JSON property responseSchema

Returns:



10446
10447
10448
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 10446

def response_schema
  @response_schema
end

#routing_config ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1GenerationConfigRoutingConfig

Routing config. Corresponds to the JSON property routingConfig

Returns:



10451
10452
10453
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 10451

def routing_config
  @routing_config
end

#seed ⇒ Fixnum

Optional. Seed. Corresponds to the JSON property seed

Returns:

  • (Fixnum) 


10456
10457
10458
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 10456

def seed
  @seed
end

#stop_sequences ⇒ Array<String>

Optional. Stop sequences. Corresponds to the JSON property stopSequences

Returns:

  • (Array<String>) 


10461
10462
10463
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 10461

def stop_sequences
  @stop_sequences
end

#temperature ⇒ Float

Optional. Controls the randomness of predictions. Corresponds to the JSON property temperature

Returns:

  • (Float) 


10466
10467
10468
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 10466

def temperature
  @temperature
end

#top_k ⇒ Float

Optional. If specified, top-k sampling will be used. Corresponds to the JSON property topK

Returns:

  • (Float) 


10471
10472
10473
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 10471

def top_k
  @top_k
end

#top_p ⇒ Float

Optional. If specified, nucleus sampling will be used. Corresponds to the JSON property topP

Returns:

  • (Float) 


10476
10477
10478
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 10476

def top_p
  @top_p
end

Instance Method Details

#update!(**args) ⇒ Object

Update properties of this object



10483
10484
10485
10486
10487
10488
10489
10490
10491
10492
10493
10494
10495
10496
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 10483

def update!(**args)
  @candidate_count = args[:candidate_count] if args.key?(:candidate_count)
  @frequency_penalty = args[:frequency_penalty] if args.key?(:frequency_penalty)
  @max_output_tokens = args[:max_output_tokens] if args.key?(:max_output_tokens)
  @presence_penalty = args[:presence_penalty] if args.key?(:presence_penalty)
  @response_mime_type = args[:response_mime_type] if args.key?(:response_mime_type)
  @response_schema = args[:response_schema] if args.key?(:response_schema)
  @routing_config = args[:routing_config] if args.key?(:routing_config)
  @seed = args[:seed] if args.key?(:seed)
  @stop_sequences = args[:stop_sequences] if args.key?(:stop_sequences)
  @temperature = args[:temperature] if args.key?(:temperature)
  @top_k = args[:top_k] if args.key?(:top_k)
  @top_p = args[:top_p] if args.key?(:top_p)
end