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

Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output.

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(**args) ⇒ GoogleCloudAiplatformV1GenerationConfig

Returns a new instance of GoogleCloudAiplatformV1GenerationConfig.



16834
16835
16836
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 16834

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

Instance Attribute Details

#audio_timestamp ⇒ Boolean Also known as: audio_timestamp?

Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response. Corresponds to the JSON property audioTimestamp

Returns:

  • (Boolean) 


16665
16666
16667
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 16665

def audio_timestamp
  @audio_timestamp
end

#candidate_count ⇒ Fixnum

Optional. The number of candidate responses to generate. A higher candidate_count can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one. Corresponds to the JSON property candidateCount

Returns:

  • (Fixnum) 


16674
16675
16676
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 16674

def candidate_count
  @candidate_count
end

#enable_affective_dialog ⇒ Boolean Also known as: enable_affective_dialog?

Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response. Corresponds to the JSON property enableAffectiveDialog

Returns:

  • (Boolean) 


16681
16682
16683
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 16681

def enable_affective_dialog
  @enable_affective_dialog
end

#frequency_penalty ⇒ Float

Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0]. Corresponds to the JSON property frequencyPenalty

Returns:

  • (Float) 


16689
16690
16691
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 16689

def frequency_penalty
  @frequency_penalty
end

#image_config ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1ImageConfig

Configuration for image generation. This message allows you to control various aspects of image generation, such as the output format, aspect ratio, and whether the model can generate images of people. Corresponds to the JSON property imageConfig

Returns:



16696
16697
16698
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 16696

def image_config
  @image_config
end

#logprobs ⇒ Fixnum

Optional. The number of top log probabilities to return for each token. This can be used to see which other tokens were considered likely candidates for a given position. A higher value will return more options, but it will also increase the size of the response. Corresponds to the JSON property logprobs

Returns:

  • (Fixnum) 


16704
16705
16706
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 16704

def logprobs
  @logprobs
end

#max_output_tokens ⇒ Fixnum

Optional. The maximum number of tokens to generate in the response. A token is approximately four characters. The default value varies by model. This parameter can be used to control the length of the generated text and prevent overly long responses. Corresponds to the JSON property maxOutputTokens

Returns:

  • (Fixnum) 


16712
16713
16714
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 16712

def max_output_tokens
  @max_output_tokens
end

#media_resolution ⇒ String

Optional. The token resolution at which input media content is sampled. This is used to control the trade-off between the quality of the response and the number of tokens used to represent the media. A higher resolution allows the model to perceive more detail, which can lead to a more nuanced response, but it will also use more tokens. This does not affect the image dimensions sent to the model. Corresponds to the JSON property mediaResolution

Returns:

  • (String) 


16722
16723
16724
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 16722

def media_resolution
  @media_resolution
end

#presence_penalty ⇒ Float

Optional. Penalizes tokens that have already appeared in the generated text. A positive value encourages the model to generate more diverse and less repetitive text. Valid values can range from [-2.0, 2.0]. Corresponds to the JSON property presencePenalty

Returns:

  • (Float) 


16729
16730
16731
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 16729

def presence_penalty
  @presence_penalty
end

#response_json_schema ⇒ Object

Optional. When this field is set, response_schema must be omitted and response_mime_type must be set to application/json. Corresponds to the JSON property responseJsonSchema

Returns:

  • (Object) 


16735
16736
16737
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 16735

def response_json_schema
  @response_json_schema
end

#response_logprobs ⇒ Boolean Also known as: response_logprobs?

Optional. If set to true, the log probabilities of the output tokens are returned. Log probabilities are the logarithm of the probability of a token appearing in the output. A higher log probability means the token is more likely to be generated. This can be useful for analyzing the model's confidence in its own output and for debugging. Corresponds to the JSON property responseLogprobs

Returns:

  • (Boolean) 


16744
16745
16746
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 16744

def response_logprobs
  @response_logprobs
end

#response_mime_type ⇒ String

Optional. The IANA standard MIME type of the response. The model will generate output that conforms to this MIME type. Supported values include 'text/plain' ( default) and 'application/json'. The model needs to be prompted to output the appropriate response type, otherwise the behavior is undefined. Corresponds to the JSON property responseMimeType

Returns:

  • (String) 


16753
16754
16755
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 16753

def response_mime_type
  @response_mime_type
end

#response_modalities ⇒ Array<String>

Optional. The modalities of the response. The model will generate a response that includes all the specified modalities. For example, if this is set to [ TEXT, IMAGE], the response will include both text and an image. Corresponds to the JSON property responseModalities

Returns:

  • (Array<String>) 


16760
16761
16762
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 16760

def response_modalities
  @response_modalities
end

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

Defines the schema of input and output data. This is a subset of the OpenAPI 3.0 Schema Object. Corresponds to the JSON property responseSchema

Returns:



16766
16767
16768
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 16766

def response_schema
  @response_schema
end

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

The configuration for routing the request to a specific model. This can be used to control which model is used for the generation, either automatically or by specifying a model name. Corresponds to the JSON property routingConfig

Returns:



16773
16774
16775
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 16773

def routing_config
  @routing_config
end

#seed ⇒ Fixnum

Optional. A seed for the random number generator. By setting a seed, you can make the model's output mostly deterministic. For a given prompt and parameters (like temperature, top_p, etc.), the model will produce the same response every time. However, it's not a guaranteed absolute deterministic behavior. This is different from parameters like temperature, which control the level of randomness. seed ensures that the "random" choices the model makes are the same on every run, making it essential for testing and ensuring reproducible results. Corresponds to the JSON property seed

Returns:

  • (Fixnum) 


16785
16786
16787
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 16785

def seed
  @seed
end

#speech_config ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1SpeechConfig

Configuration for speech generation. Corresponds to the JSON property speechConfig

Returns:



16790
16791
16792
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 16790

def speech_config
  @speech_config
end

#stop_sequences ⇒ Array<String>

Optional. A list of character sequences that will stop the model from generating further tokens. If a stop sequence is generated, the output will end at that point. This is useful for controlling the length and structure of the output. For example, you can use ["\n", "###"] to stop generation at a new line or a specific marker. Corresponds to the JSON property stopSequences

Returns:

  • (Array<String>) 


16799
16800
16801
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 16799

def stop_sequences
  @stop_sequences
end

#temperature ⇒ Float

Optional. Controls the randomness of the output. A higher temperature results in more creative and diverse responses, while a lower temperature makes the output more predictable and focused. The valid range is (0.0, 2.0]. Corresponds to the JSON property temperature

Returns:

  • (Float) 


16806
16807
16808
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 16806

def temperature
  @temperature
end

#thinking_config ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1GenerationConfigThinkingConfig

Configuration for the model's thinking features. "Thinking" is a process where the model breaks down a complex task into smaller, manageable steps. This allows the model to reason about the task, plan its approach, and execute the plan to generate a high-quality response. Corresponds to the JSON property thinkingConfig

Returns:



16814
16815
16816
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 16814

def thinking_config
  @thinking_config
end

#top_k ⇒ Float

Optional. Specifies the top-k sampling threshold. The model considers only the top k most probable tokens for the next token. This can be useful for generating more coherent and less random text. For example, a top_k of 40 means the model will choose the next word from the 40 most likely words. Corresponds to the JSON property topK

Returns:

  • (Float) 


16822
16823
16824
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 16822

def top_k
  @top_k
end

#top_p ⇒ Float

Optional. Specifies the nucleus sampling threshold. The model considers only the smallest set of tokens whose cumulative probability is at least top_p. This helps generate more diverse and less repetitive responses. For example, a top_p of 0.9 means the model considers tokens until the cumulative probability of the tokens to select from reaches 0.9. It's recommended to adjust either temperature or top_p, but not both. Corresponds to the JSON property topP

Returns:

  • (Float) 


16832
16833
16834
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 16832

def top_p
  @top_p
end

Instance Method Details

#update!(**args) ⇒ Object

Update properties of this object



16839
16840
16841
16842
16843
16844
16845
16846
16847
16848
16849
16850
16851
16852
16853
16854
16855
16856
16857
16858
16859
16860
16861
16862
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 16839

def update!(**args)
  @audio_timestamp = args[:audio_timestamp] if args.key?(:audio_timestamp)
  @candidate_count = args[:candidate_count] if args.key?(:candidate_count)
  @enable_affective_dialog = args[:enable_affective_dialog] if args.key?(:enable_affective_dialog)
  @frequency_penalty = args[:frequency_penalty] if args.key?(:frequency_penalty)
  @image_config = args[:image_config] if args.key?(:image_config)
  @logprobs = args[:logprobs] if args.key?(:logprobs)
  @max_output_tokens = args[:max_output_tokens] if args.key?(:max_output_tokens)
  @media_resolution = args[:media_resolution] if args.key?(:media_resolution)
  @presence_penalty = args[:presence_penalty] if args.key?(:presence_penalty)
  @response_json_schema = args[:response_json_schema] if args.key?(:response_json_schema)
  @response_logprobs = args[:response_logprobs] if args.key?(:response_logprobs)
  @response_mime_type = args[:response_mime_type] if args.key?(:response_mime_type)
  @response_modalities = args[:response_modalities] if args.key?(:response_modalities)
  @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)
  @speech_config = args[:speech_config] if args.key?(:speech_config)
  @stop_sequences = args[:stop_sequences] if args.key?(:stop_sequences)
  @temperature = args[:temperature] if args.key?(:temperature)
  @thinking_config = args[:thinking_config] if args.key?(:thinking_config)
  @top_k = args[:top_k] if args.key?(:top_k)
  @top_p = args[:top_p] if args.key?(:top_p)
end