Class: Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1GenerationConfig
- Inherits:
-
Object
- Object
- Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1GenerationConfig
- 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
Generation config.
Instance Attribute Summary collapse
-
#candidate_count ⇒ Fixnum
Optional.
-
#frequency_penalty ⇒ Float
Optional.
-
#max_output_tokens ⇒ Fixnum
Optional.
-
#presence_penalty ⇒ Float
Optional.
-
#response_mime_type ⇒ String
Optional.
-
#response_schema ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1Schema
Schema is used to define the format of input/output data.
-
#stop_sequences ⇒ Array<String>
Optional.
-
#temperature ⇒ Float
Optional.
-
#top_k ⇒ Float
Optional.
-
#top_p ⇒ Float
Optional.
Instance Method Summary collapse
-
#initialize(**args) ⇒ GoogleCloudAiplatformV1beta1GenerationConfig
constructor
A new instance of GoogleCloudAiplatformV1beta1GenerationConfig.
-
#update!(**args) ⇒ Object
Update properties of this object.
Constructor Details
#initialize(**args) ⇒ GoogleCloudAiplatformV1beta1GenerationConfig
Returns a new instance of GoogleCloudAiplatformV1beta1GenerationConfig.
11250 11251 11252 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 11250 def initialize(**args) update!(**args) end |
Instance Attribute Details
#candidate_count ⇒ Fixnum
Optional. Number of candidates to generate.
Corresponds to the JSON property candidateCount
11197 11198 11199 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 11197 def candidate_count @candidate_count end |
#frequency_penalty ⇒ Float
Optional. Frequency penalties.
Corresponds to the JSON property frequencyPenalty
11202 11203 11204 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 11202 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
11207 11208 11209 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 11207 def max_output_tokens @max_output_tokens end |
#presence_penalty ⇒ Float
Optional. Positive penalties.
Corresponds to the JSON property presencePenalty
11212 11213 11214 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 11212 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
11221 11222 11223 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 11221 def response_mime_type @response_mime_type end |
#response_schema ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1Schema
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
11228 11229 11230 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 11228 def response_schema @response_schema end |
#stop_sequences ⇒ Array<String>
Optional. Stop sequences.
Corresponds to the JSON property stopSequences
11233 11234 11235 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 11233 def stop_sequences @stop_sequences end |
#temperature ⇒ Float
Optional. Controls the randomness of predictions.
Corresponds to the JSON property temperature
11238 11239 11240 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 11238 def temperature @temperature end |
#top_k ⇒ Float
Optional. If specified, top-k sampling will be used.
Corresponds to the JSON property topK
11243 11244 11245 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 11243 def top_k @top_k end |
#top_p ⇒ Float
Optional. If specified, nucleus sampling will be used.
Corresponds to the JSON property topP
11248 11249 11250 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 11248 def top_p @top_p end |
Instance Method Details
#update!(**args) ⇒ Object
Update properties of this object
11255 11256 11257 11258 11259 11260 11261 11262 11263 11264 11265 11266 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 11255 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) @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 |