Class: OCI::GenerativeAiInference::Models::CohereLlmInferenceRequest

Inherits:
LlmInferenceRequest show all
Defined in:
lib/oci/generative_ai_inference/models/cohere_llm_inference_request.rb

Overview

Details for the text generation request for Cohere models.

Constant Summary collapse

RETURN_LIKELIHOODS_ENUM = 
[
  RETURN_LIKELIHOODS_NONE = 'NONE'.freeze,
  RETURN_LIKELIHOODS_ALL = 'ALL'.freeze,
  RETURN_LIKELIHOODS_GENERATION = 'GENERATION'.freeze
].freeze
TRUNCATE_ENUM = 
[
  TRUNCATE_NONE = 'NONE'.freeze,
  TRUNCATE_START = 'START'.freeze,
  TRUNCATE_END = 'END'.freeze
].freeze

Constants inherited from LlmInferenceRequest

LlmInferenceRequest::RUNTIME_TYPE_ENUM

Instance Attribute Summary collapse

Attributes inherited from LlmInferenceRequest

#runtime_type

Class Method Summary collapse

Instance Method Summary collapse

Methods inherited from LlmInferenceRequest

get_subtype

Constructor Details

#initialize(attributes = {}) ⇒ CohereLlmInferenceRequest

Initializes the object

Parameters:

  • attributes (Hash) (defaults to: {}) —

    Model attributes in the form of hash

Options Hash (attributes):

  • :prompt (String) —

    The value to assign to the #prompt property

  • :is_stream (BOOLEAN) —

    The value to assign to the #is_stream property

  • :num_generations (Integer) —

    The value to assign to the #num_generations property

  • :is_echo (BOOLEAN) —

    The value to assign to the #is_echo property

  • :max_tokens (Integer) —

    The value to assign to the #max_tokens property

  • :temperature (Float) —

    The value to assign to the #temperature property

  • :top_k (Integer) —

    The value to assign to the #top_k property

  • :top_p (Float) —

    The value to assign to the #top_p property

  • :frequency_penalty (Float) —

    The value to assign to the #frequency_penalty property

  • :presence_penalty (Float) —

    The value to assign to the #presence_penalty property

  • :stop_sequences (Array<String>) —

    The value to assign to the #stop_sequences property

  • :return_likelihoods (String) —

    The value to assign to the #return_likelihoods property

  • :truncate (String) —

    The value to assign to the #truncate property



152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
 
# File 'lib/oci/generative_ai_inference/models/cohere_llm_inference_request.rb', line 152

def initialize(attributes = {})
  return unless attributes.is_a?(Hash)

  attributes['runtimeType'] = 'COHERE'

  super(attributes)

  # convert string to symbol for hash key
  attributes = attributes.each_with_object({}) { |(k, v), h| h[k.to_sym] = v }

  self.prompt = attributes[:'prompt'] if attributes[:'prompt']

  self.is_stream = attributes[:'isStream'] unless attributes[:'isStream'].nil?
  self.is_stream = false if is_stream.nil? && !attributes.key?(:'isStream') # rubocop:disable Style/StringLiterals

  raise 'You cannot provide both :isStream and :is_stream' if attributes.key?(:'isStream') && attributes.key?(:'is_stream')

  self.is_stream = attributes[:'is_stream'] unless attributes[:'is_stream'].nil?
  self.is_stream = false if is_stream.nil? && !attributes.key?(:'isStream') && !attributes.key?(:'is_stream') # rubocop:disable Style/StringLiterals

  self.num_generations = attributes[:'numGenerations'] if attributes[:'numGenerations']

  raise 'You cannot provide both :numGenerations and :num_generations' if attributes.key?(:'numGenerations') && attributes.key?(:'num_generations')

  self.num_generations = attributes[:'num_generations'] if attributes[:'num_generations']

  self.is_echo = attributes[:'isEcho'] unless attributes[:'isEcho'].nil?
  self.is_echo = false if is_echo.nil? && !attributes.key?(:'isEcho') # rubocop:disable Style/StringLiterals

  raise 'You cannot provide both :isEcho and :is_echo' if attributes.key?(:'isEcho') && attributes.key?(:'is_echo')

  self.is_echo = attributes[:'is_echo'] unless attributes[:'is_echo'].nil?
  self.is_echo = false if is_echo.nil? && !attributes.key?(:'isEcho') && !attributes.key?(:'is_echo') # rubocop:disable Style/StringLiterals

  self.max_tokens = attributes[:'maxTokens'] if attributes[:'maxTokens']

  raise 'You cannot provide both :maxTokens and :max_tokens' if attributes.key?(:'maxTokens') && attributes.key?(:'max_tokens')

  self.max_tokens = attributes[:'max_tokens'] if attributes[:'max_tokens']

  self.temperature = attributes[:'temperature'] if attributes[:'temperature']
  self.temperature = 1.0 if temperature.nil? && !attributes.key?(:'temperature') # rubocop:disable Style/StringLiterals

  self.top_k = attributes[:'topK'] if attributes[:'topK']

  raise 'You cannot provide both :topK and :top_k' if attributes.key?(:'topK') && attributes.key?(:'top_k')

  self.top_k = attributes[:'top_k'] if attributes[:'top_k']

  self.top_p = attributes[:'topP'] if attributes[:'topP']
  self.top_p = 0.75 if top_p.nil? && !attributes.key?(:'topP') # rubocop:disable Style/StringLiterals

  raise 'You cannot provide both :topP and :top_p' if attributes.key?(:'topP') && attributes.key?(:'top_p')

  self.top_p = attributes[:'top_p'] if attributes[:'top_p']
  self.top_p = 0.75 if top_p.nil? && !attributes.key?(:'topP') && !attributes.key?(:'top_p') # rubocop:disable Style/StringLiterals

  self.frequency_penalty = attributes[:'frequencyPenalty'] if attributes[:'frequencyPenalty']
  self.frequency_penalty = 0.0 if frequency_penalty.nil? && !attributes.key?(:'frequencyPenalty') # rubocop:disable Style/StringLiterals

  raise 'You cannot provide both :frequencyPenalty and :frequency_penalty' if attributes.key?(:'frequencyPenalty') && attributes.key?(:'frequency_penalty')

  self.frequency_penalty = attributes[:'frequency_penalty'] if attributes[:'frequency_penalty']
  self.frequency_penalty = 0.0 if frequency_penalty.nil? && !attributes.key?(:'frequencyPenalty') && !attributes.key?(:'frequency_penalty') # rubocop:disable Style/StringLiterals

  self.presence_penalty = attributes[:'presencePenalty'] if attributes[:'presencePenalty']
  self.presence_penalty = 0.0 if presence_penalty.nil? && !attributes.key?(:'presencePenalty') # rubocop:disable Style/StringLiterals

  raise 'You cannot provide both :presencePenalty and :presence_penalty' if attributes.key?(:'presencePenalty') && attributes.key?(:'presence_penalty')

  self.presence_penalty = attributes[:'presence_penalty'] if attributes[:'presence_penalty']
  self.presence_penalty = 0.0 if presence_penalty.nil? && !attributes.key?(:'presencePenalty') && !attributes.key?(:'presence_penalty') # rubocop:disable Style/StringLiterals

  self.stop_sequences = attributes[:'stopSequences'] if attributes[:'stopSequences']

  raise 'You cannot provide both :stopSequences and :stop_sequences' if attributes.key?(:'stopSequences') && attributes.key?(:'stop_sequences')

  self.stop_sequences = attributes[:'stop_sequences'] if attributes[:'stop_sequences']

  self.return_likelihoods = attributes[:'returnLikelihoods'] if attributes[:'returnLikelihoods']
  self.return_likelihoods = "NONE" if return_likelihoods.nil? && !attributes.key?(:'returnLikelihoods') # rubocop:disable Style/StringLiterals

  raise 'You cannot provide both :returnLikelihoods and :return_likelihoods' if attributes.key?(:'returnLikelihoods') && attributes.key?(:'return_likelihoods')

  self.return_likelihoods = attributes[:'return_likelihoods'] if attributes[:'return_likelihoods']
  self.return_likelihoods = "NONE" if return_likelihoods.nil? && !attributes.key?(:'returnLikelihoods') && !attributes.key?(:'return_likelihoods') # rubocop:disable Style/StringLiterals

  self.truncate = attributes[:'truncate'] if attributes[:'truncate']
  self.truncate = "NONE" if truncate.nil? && !attributes.key?(:'truncate') # rubocop:disable Style/StringLiterals
end

Instance Attribute Details

#frequency_penalty ⇒ Float

To reduce repetitiveness of generated tokens, this number penalizes new tokens based on their frequency in the generated text so far. Greater numbers encourage the model to use new tokens, while lower numbers encourage the model to repeat the tokens. Set to 0 to disable.

Returns:

  • (Float) 


68
69
70
 
# File 'lib/oci/generative_ai_inference/models/cohere_llm_inference_request.rb', line 68

def frequency_penalty
  @frequency_penalty
end

#is_echo ⇒ BOOLEAN

Whether or not to return the user prompt in the response. This option only applies to non-stream results.

Returns:

  • (BOOLEAN) 


38
39
40
 
# File 'lib/oci/generative_ai_inference/models/cohere_llm_inference_request.rb', line 38

def is_echo
  @is_echo
end

#is_stream ⇒ BOOLEAN

Whether to stream back partial progress. If set, tokens are sent as data-only server-sent events as they become available.

Returns:

  • (BOOLEAN) 


30
31
32
 
# File 'lib/oci/generative_ai_inference/models/cohere_llm_inference_request.rb', line 30

def is_stream
  @is_stream
end

#max_tokens ⇒ Integer

The maximum number of tokens to predict for each response. Includes input plus output tokens.

Returns:

  • (Integer) 


42
43
44
 
# File 'lib/oci/generative_ai_inference/models/cohere_llm_inference_request.rb', line 42

def max_tokens
  @max_tokens
end

#num_generations ⇒ Integer

The number of generated texts that will be returned.

Returns:

  • (Integer) 


34
35
36
 
# File 'lib/oci/generative_ai_inference/models/cohere_llm_inference_request.rb', line 34

def num_generations
  @num_generations
end

#presence_penalty ⇒ Float

To reduce repetitiveness of generated tokens, this number penalizes new tokens based on whether they've appeared in the generated text so far. Greater numbers encourage the model to use new tokens, while lower numbers encourage the model to repeat the tokens.

Similar to frequency penalty, a penalty is applied to previously present tokens, except that this penalty is applied equally to all tokens that have already appeared, regardless of how many times they've appeared. Set to 0 to disable.

Returns:

  • (Float) 


75
76
77
 
# File 'lib/oci/generative_ai_inference/models/cohere_llm_inference_request.rb', line 75

def presence_penalty
  @presence_penalty
end

#prompt ⇒ String

[Required] Represents the prompt to be completed. The trailing white spaces are trimmed before completion.

Returns:

  • (String) 


26
27
28
 
# File 'lib/oci/generative_ai_inference/models/cohere_llm_inference_request.rb', line 26

def prompt
  @prompt
end

#return_likelihoods ⇒ String

Specifies how and if the token likelihoods are returned with the response.

Returns:

  • (String) 


83
84
85
 
# File 'lib/oci/generative_ai_inference/models/cohere_llm_inference_request.rb', line 83

def return_likelihoods
  @return_likelihoods
end

#stop_sequences ⇒ Array<String>

The generated text is cut at the end of the earliest occurrence of this stop sequence. The generated text will include this stop sequence.

Returns:

  • (Array<String>) 


79
80
81
 
# File 'lib/oci/generative_ai_inference/models/cohere_llm_inference_request.rb', line 79

def stop_sequences
  @stop_sequences
end

#temperature ⇒ Float

A number that sets the randomness of the generated output. A lower temperature means a less random generations.

Use lower numbers for tasks with a correct answer such as question answering or summarizing. High temperatures can generate hallucinations or factually incorrect information. Start with temperatures lower than 1.0 and increase the temperature for more creative outputs, as you regenerate the prompts to refine the outputs.

Returns:

  • (Float) 


49
50
51
 
# File 'lib/oci/generative_ai_inference/models/cohere_llm_inference_request.rb', line 49

def temperature
  @temperature
end

#top_k ⇒ Integer

An integer that sets up the model to use only the top k most likely tokens in the generated output. A higher k introduces more randomness into the output making the output text sound more natural. Default value is 0 which disables this method and considers all tokens. To set a number for the likely tokens, choose an integer between 1 and 500.

If also using top p, then the model considers only the top tokens whose probabilities add up to p percent and ignores the rest of the k tokens. For example, if k is 20, but the probabilities of the top 10 add up to .75, then only the top 10 tokens are chosen.

Returns:

  • (Integer) 


56
57
58
 
# File 'lib/oci/generative_ai_inference/models/cohere_llm_inference_request.rb', line 56

def top_k
  @top_k
end

#top_p ⇒ Float

If set to a probability 0.0 < p < 1.0, it ensures that only the most likely tokens, with total probability mass of p, are considered for generation at each step.

To eliminate tokens with low likelihood, assign p a minimum percentage for the next token's likelihood. For example, when p is set to 0.75, the model eliminates the bottom 25 percent for the next token. Set to 1.0 to consider all tokens and set to 0 to disable. If both k and p are enabled, p acts after k.

Returns:

  • (Float) 


63
64
65
 
# File 'lib/oci/generative_ai_inference/models/cohere_llm_inference_request.rb', line 63

def top_p
  @top_p
end

#truncate ⇒ String

For an input that's longer than the maximum token length, specifies which part of the input text will be truncated.

Returns:

  • (String) 


87
88
89
 
# File 'lib/oci/generative_ai_inference/models/cohere_llm_inference_request.rb', line 87

def truncate
  @truncate
end

Class Method Details

.attribute_map ⇒ Object

Attribute mapping from ruby-style variable name to JSON key.



90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
 
# File 'lib/oci/generative_ai_inference/models/cohere_llm_inference_request.rb', line 90

def self.attribute_map
  {
    # rubocop:disable Style/SymbolLiteral
    'runtime_type': :'runtimeType',
    'prompt': :'prompt',
    'is_stream': :'isStream',
    'num_generations': :'numGenerations',
    'is_echo': :'isEcho',
    'max_tokens': :'maxTokens',
    'temperature': :'temperature',
    'top_k': :'topK',
    'top_p': :'topP',
    'frequency_penalty': :'frequencyPenalty',
    'presence_penalty': :'presencePenalty',
    'stop_sequences': :'stopSequences',
    'return_likelihoods': :'returnLikelihoods',
    'truncate': :'truncate'
    # rubocop:enable Style/SymbolLiteral
  }
end

.swagger_types ⇒ Object

Attribute type mapping.



112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
 
# File 'lib/oci/generative_ai_inference/models/cohere_llm_inference_request.rb', line 112

def self.swagger_types
  {
    # rubocop:disable Style/SymbolLiteral
    'runtime_type': :'String',
    'prompt': :'String',
    'is_stream': :'BOOLEAN',
    'num_generations': :'Integer',
    'is_echo': :'BOOLEAN',
    'max_tokens': :'Integer',
    'temperature': :'Float',
    'top_k': :'Integer',
    'top_p': :'Float',
    'frequency_penalty': :'Float',
    'presence_penalty': :'Float',
    'stop_sequences': :'Array<String>',
    'return_likelihoods': :'String',
    'truncate': :'String'
    # rubocop:enable Style/SymbolLiteral
  }
end

Instance Method Details

#==(other) ⇒ Object

Checks equality by comparing each attribute.

Parameters:

  • other (Object) —

    the other object to be compared



266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
 
# File 'lib/oci/generative_ai_inference/models/cohere_llm_inference_request.rb', line 266

def ==(other)
  return true if equal?(other)

  self.class == other.class &&
    runtime_type == other.runtime_type &&
    prompt == other.prompt &&
    is_stream == other.is_stream &&
    num_generations == other.num_generations &&
    is_echo == other.is_echo &&
    max_tokens == other.max_tokens &&
    temperature == other.temperature &&
    top_k == other.top_k &&
    top_p == other.top_p &&
    frequency_penalty == other.frequency_penalty &&
    presence_penalty == other.presence_penalty &&
    stop_sequences == other.stop_sequences &&
    return_likelihoods == other.return_likelihoods &&
    truncate == other.truncate
end

#build_from_hash(attributes) ⇒ Object

Builds the object from hash

Parameters:

  • attributes (Hash) —

    Model attributes in the form of hash

Returns:

  • (Object) —

    Returns the model itself



309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
 
# File 'lib/oci/generative_ai_inference/models/cohere_llm_inference_request.rb', line 309

def build_from_hash(attributes)
  return nil unless attributes.is_a?(Hash)

  self.class.swagger_types.each_pair do |key, type|
    if type =~ /^Array<(.*)>/i
      # check to ensure the input is an array given that the the attribute
      # is documented as an array but the input is not
      if attributes[self.class.attribute_map[key]].is_a?(Array)
        public_method("#{key}=").call(
          attributes[self.class.attribute_map[key]]
            .map { |v| OCI::Internal::Util.convert_to_type(Regexp.last_match(1), v) }
        )
      end
    elsif !attributes[self.class.attribute_map[key]].nil?
      public_method("#{key}=").call(
        OCI::Internal::Util.convert_to_type(type, attributes[self.class.attribute_map[key]])
      )
    end
    # or else data not found in attributes(hash), not an issue as the data can be optional
  end

  self
end

#eql?(other) ⇒ Boolean

Parameters:

  • other (Object) —

    the other object to be compared

Returns:

  • (Boolean)

See Also:

  • `==` method


289
290
291
 
# File 'lib/oci/generative_ai_inference/models/cohere_llm_inference_request.rb', line 289

def eql?(other)
  self == other
end

#hash ⇒ Fixnum

Calculates hash code according to all attributes.

Returns:

  • (Fixnum) —

    Hash code



298
299
300
 
# File 'lib/oci/generative_ai_inference/models/cohere_llm_inference_request.rb', line 298

def hash
  [runtime_type, prompt, is_stream, num_generations, is_echo, max_tokens, temperature, top_k, top_p, frequency_penalty, presence_penalty, stop_sequences, return_likelihoods, truncate].hash
end

#to_hash ⇒ Hash

Returns the object in the form of hash

Returns:

  • (Hash) —

    Returns the object in the form of hash



342
343
344
345
346
347
348
349
350
351
 
# File 'lib/oci/generative_ai_inference/models/cohere_llm_inference_request.rb', line 342

def to_hash
  hash = {}
  self.class.attribute_map.each_pair do |attr, param|
    value = public_method(attr).call
    next if value.nil? && !instance_variable_defined?("@#{attr}")

    hash[param] = _to_hash(value)
  end
  hash
end

#to_s ⇒ String

Returns the string representation of the object

Returns:

  • (String) —

    String presentation of the object



336
337
338
 
# File 'lib/oci/generative_ai_inference/models/cohere_llm_inference_request.rb', line 336

def to_s
  to_hash.to_s
end