Class: OpenApiOpenAIClient::CreateCompletionRequest
- Inherits:
-
Object
- Object
- OpenApiOpenAIClient::CreateCompletionRequest
- Defined in:
- lib/openapi_openai/models/create_completion_request.rb
Instance Attribute Summary collapse
-
#best_of ⇒ Object
Generates ‘best_of` completions server-side and returns the "best" (the one with the highest log probability per token).
-
#echo ⇒ Object
Echo back the prompt in addition to the completion.
-
#frequency_penalty ⇒ Object
Number between -2.0 and 2.0.
-
#logit_bias ⇒ Object
Modify the likelihood of specified tokens appearing in the completion.
-
#logprobs ⇒ Object
Include the log probabilities on the ‘logprobs` most likely output tokens, as well the chosen tokens.
-
#max_tokens ⇒ Object
The maximum number of [tokens](/tokenizer) that can be generated in the completion.
-
#model ⇒ Object
Returns the value of attribute model.
-
#n ⇒ Object
How many completions to generate for each prompt.
-
#presence_penalty ⇒ Object
Number between -2.0 and 2.0.
-
#prompt ⇒ Object
Returns the value of attribute prompt.
-
#seed ⇒ Object
If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same ‘seed` and parameters should return the same result.
-
#stop ⇒ Object
Returns the value of attribute stop.
-
#stream ⇒ Object
Whether to stream back partial progress.
-
#suffix ⇒ Object
The suffix that comes after a completion of inserted text.
-
#temperature ⇒ Object
What sampling temperature to use, between 0 and 2.
-
#top_p ⇒ Object
An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass.
-
#user ⇒ Object
A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.
Class Method Summary collapse
-
._deserialize(type, value) ⇒ Object
Deserializes the data based on type.
-
.acceptable_attributes ⇒ Object
Returns all the JSON keys this model knows about.
-
.attribute_map ⇒ Object
Attribute mapping from ruby-style variable name to JSON key.
-
.build_from_hash(attributes) ⇒ Object
Builds the object from hash.
-
.openapi_nullable ⇒ Object
List of attributes with nullable: true.
-
.openapi_types ⇒ Object
Attribute type mapping.
Instance Method Summary collapse
-
#==(o) ⇒ Object
Checks equality by comparing each attribute.
-
#_to_hash(value) ⇒ Hash
Outputs non-array value in the form of hash For object, use to_hash.
- #eql?(o) ⇒ Boolean
-
#hash ⇒ Integer
Calculates hash code according to all attributes.
-
#initialize(attributes = {}) ⇒ CreateCompletionRequest
constructor
Initializes the object.
-
#list_invalid_properties ⇒ Object
Show invalid properties with the reasons.
-
#to_body ⇒ Hash
to_body is an alias to to_hash (backward compatibility).
-
#to_hash ⇒ Hash
Returns the object in the form of hash.
-
#to_s ⇒ String
Returns the string representation of the object.
-
#valid? ⇒ Boolean
Check to see if the all the properties in the model are valid.
Constructor Details
#initialize(attributes = {}) ⇒ CreateCompletionRequest
Initializes the object
140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 140 def initialize(attributes = {}) if (!attributes.is_a?(Hash)) fail ArgumentError, "The input argument (attributes) must be a hash in `OpenApiOpenAIClient::CreateCompletionRequest` initialize method" end # check to see if the attribute exists and convert string to symbol for hash key attributes = attributes.each_with_object({}) { |(k, v), h| if (!self.class.attribute_map.key?(k.to_sym)) fail ArgumentError, "`#{k}` is not a valid attribute in `OpenApiOpenAIClient::CreateCompletionRequest`. Please check the name to make sure it's valid. List of attributes: " + self.class.attribute_map.keys.inspect end h[k.to_sym] = v } if attributes.key?(:'model') self.model = attributes[:'model'] else self.model = nil end if attributes.key?(:'prompt') self.prompt = attributes[:'prompt'] else self.prompt = nil end if attributes.key?(:'best_of') self.best_of = attributes[:'best_of'] else self.best_of = 1 end if attributes.key?(:'echo') self.echo = attributes[:'echo'] else self.echo = false end if attributes.key?(:'frequency_penalty') self.frequency_penalty = attributes[:'frequency_penalty'] else self.frequency_penalty = 0 end if attributes.key?(:'logit_bias') if (value = attributes[:'logit_bias']).is_a?(Hash) self.logit_bias = value end end if attributes.key?(:'logprobs') self.logprobs = attributes[:'logprobs'] end if attributes.key?(:'max_tokens') self.max_tokens = attributes[:'max_tokens'] else self.max_tokens = 16 end if attributes.key?(:'n') self.n = attributes[:'n'] else self.n = 1 end if attributes.key?(:'presence_penalty') self.presence_penalty = attributes[:'presence_penalty'] else self.presence_penalty = 0 end if attributes.key?(:'seed') self.seed = attributes[:'seed'] end if attributes.key?(:'stop') self.stop = attributes[:'stop'] end if attributes.key?(:'stream') self.stream = attributes[:'stream'] else self.stream = false end if attributes.key?(:'suffix') self.suffix = attributes[:'suffix'] end if attributes.key?(:'temperature') self.temperature = attributes[:'temperature'] else self.temperature = 1 end if attributes.key?(:'top_p') self.top_p = attributes[:'top_p'] else self.top_p = 1 end if attributes.key?(:'user') self.user = attributes[:'user'] end end |
Instance Attribute Details
#best_of ⇒ Object
Generates ‘best_of` completions server-side and returns the "best" (the one with the highest log probability per token). Results cannot be streamed. When used with `n`, `best_of` controls the number of candidate completions and `n` specifies how many to return – `best_of` must be greater than `n`. Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for `max_tokens` and `stop`.
23 24 25 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 23 def best_of @best_of end |
#echo ⇒ Object
Echo back the prompt in addition to the completion
26 27 28 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 26 def echo @echo end |
#frequency_penalty ⇒ Object
Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model’s likelihood to repeat the same line verbatim. [See more information about frequency and presence penalties.](/docs/guides/text-generation/parameter-details)
29 30 31 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 29 def frequency_penalty @frequency_penalty end |
#logit_bias ⇒ Object
Modify the likelihood of specified tokens appearing in the completion. Accepts a JSON object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this [tokenizer tool](/tokenizer?view=bpe) to convert text to token IDs. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. As an example, you can pass ‘-100` to prevent the <|endoftext|> token from being generated.
32 33 34 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 32 def logit_bias @logit_bias end |
#logprobs ⇒ Object
Include the log probabilities on the ‘logprobs` most likely output tokens, as well the chosen tokens. For example, if `logprobs` is 5, the API will return a list of the 5 most likely tokens. The API will always return the `logprob` of the sampled token, so there may be up to `logprobs+1` elements in the response. The maximum value for `logprobs` is 5.
35 36 37 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 35 def logprobs @logprobs end |
#max_tokens ⇒ Object
The maximum number of [tokens](/tokenizer) that can be generated in the completion. The token count of your prompt plus ‘max_tokens` cannot exceed the model’s context length. [Example Python code](cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens.
38 39 40 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 38 def max_tokens @max_tokens end |
#model ⇒ Object
Returns the value of attribute model.
18 19 20 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 18 def model @model end |
#n ⇒ Object
How many completions to generate for each prompt. Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for ‘max_tokens` and `stop`.
41 42 43 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 41 def n @n end |
#presence_penalty ⇒ Object
Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model’s likelihood to talk about new topics. [See more information about frequency and presence penalties.](/docs/guides/text-generation/parameter-details)
44 45 46 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 44 def presence_penalty @presence_penalty end |
#prompt ⇒ Object
Returns the value of attribute prompt.
20 21 22 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 20 def prompt @prompt end |
#seed ⇒ Object
If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same ‘seed` and parameters should return the same result. Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend.
47 48 49 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 47 def seed @seed end |
#stop ⇒ Object
Returns the value of attribute stop.
49 50 51 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 49 def stop @stop end |
#stream ⇒ Object
Whether to stream back partial progress. If set, tokens will be sent as data-only [server-sent events](developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a ‘data: [DONE]` message. [Example Python code](cookbook.openai.com/examples/how_to_stream_completions).
52 53 54 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 52 def stream @stream end |
#suffix ⇒ Object
The suffix that comes after a completion of inserted text. This parameter is only supported for ‘gpt-3.5-turbo-instruct`.
55 56 57 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 55 def suffix @suffix end |
#temperature ⇒ Object
What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or ‘top_p` but not both.
58 59 60 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 58 def temperature @temperature end |
#top_p ⇒ Object
An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or ‘temperature` but not both.
61 62 63 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 61 def top_p @top_p end |
#user ⇒ Object
A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices/end-user-ids).
64 65 66 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 64 def user @user end |
Class Method Details
._deserialize(type, value) ⇒ Object
Deserializes the data based on type
536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 536 def self._deserialize(type, value) case type.to_sym when :Time Time.parse(value) when :Date Date.parse(value) when :String value.to_s when :Integer value.to_i when :Float value.to_f when :Boolean if value.to_s =~ /\A(true|t|yes|y|1)\z/i true else false end when :Object # generic object (usually a Hash), return directly value when /\AArray<(?<inner_type>.+)>\z/ inner_type = Regexp.last_match[:inner_type] value.map { |v| _deserialize(inner_type, v) } when /\AHash<(?<k_type>.+?), (?<v_type>.+)>\z/ k_type = Regexp.last_match[:k_type] v_type = Regexp.last_match[:v_type] {}.tap do |hash| value.each do |k, v| hash[_deserialize(k_type, k)] = _deserialize(v_type, v) end end else # model # models (e.g. Pet) or oneOf klass = OpenApiOpenAIClient.const_get(type) klass.respond_to?(:openapi_any_of) || klass.respond_to?(:openapi_one_of) ? klass.build(value) : klass.build_from_hash(value) end end |
.acceptable_attributes ⇒ Object
Returns all the JSON keys this model knows about
90 91 92 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 90 def self.acceptable_attributes attribute_map.values end |
.attribute_map ⇒ Object
Attribute mapping from ruby-style variable name to JSON key.
67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 67 def self.attribute_map { :'model' => :'model', :'prompt' => :'prompt', :'best_of' => :'best_of', :'echo' => :'echo', :'frequency_penalty' => :'frequency_penalty', :'logit_bias' => :'logit_bias', :'logprobs' => :'logprobs', :'max_tokens' => :'max_tokens', :'n' => :'n', :'presence_penalty' => :'presence_penalty', :'seed' => :'seed', :'stop' => :'stop', :'stream' => :'stream', :'suffix' => :'suffix', :'temperature' => :'temperature', :'top_p' => :'top_p', :'user' => :'user' } end |
.build_from_hash(attributes) ⇒ Object
Builds the object from hash
512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 512 def self.build_from_hash(attributes) return nil unless attributes.is_a?(Hash) attributes = attributes.transform_keys(&:to_sym) transformed_hash = {} openapi_types.each_pair do |key, type| if attributes.key?(attribute_map[key]) && attributes[attribute_map[key]].nil? transformed_hash["#{key}"] = nil elsif type =~ /\AArray<(.*)>/i # check to ensure the input is an array given that the attribute # is documented as an array but the input is not if attributes[attribute_map[key]].is_a?(Array) transformed_hash["#{key}"] = attributes[attribute_map[key]].map { |v| _deserialize($1, v) } end elsif !attributes[attribute_map[key]].nil? transformed_hash["#{key}"] = _deserialize(type, attributes[attribute_map[key]]) end end new(transformed_hash) end |
.openapi_nullable ⇒ Object
List of attributes with nullable: true
118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 118 def self.openapi_nullable Set.new([ :'prompt', :'best_of', :'echo', :'frequency_penalty', :'logit_bias', :'logprobs', :'max_tokens', :'n', :'presence_penalty', :'seed', :'stop', :'stream', :'suffix', :'temperature', :'top_p', ]) end |
.openapi_types ⇒ Object
Attribute type mapping.
95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 95 def self.openapi_types { :'model' => :'CreateCompletionRequestModel', :'prompt' => :'CreateCompletionRequestPrompt', :'best_of' => :'Integer', :'echo' => :'Boolean', :'frequency_penalty' => :'Float', :'logit_bias' => :'Hash<String, Integer>', :'logprobs' => :'Integer', :'max_tokens' => :'Integer', :'n' => :'Integer', :'presence_penalty' => :'Float', :'seed' => :'Integer', :'stop' => :'CreateCompletionRequestStop', :'stream' => :'Boolean', :'suffix' => :'String', :'temperature' => :'Float', :'top_p' => :'Float', :'user' => :'String' } end |
Instance Method Details
#==(o) ⇒ Object
Checks equality by comparing each attribute.
475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 475 def ==(o) return true if self.equal?(o) self.class == o.class && model == o.model && prompt == o.prompt && best_of == o.best_of && echo == o.echo && frequency_penalty == o.frequency_penalty && logit_bias == o.logit_bias && logprobs == o.logprobs && max_tokens == o.max_tokens && n == o.n && presence_penalty == o.presence_penalty && seed == o.seed && stop == o.stop && stream == o.stream && suffix == o.suffix && temperature == o.temperature && top_p == o.top_p && user == o.user end |
#_to_hash(value) ⇒ Hash
Outputs non-array value in the form of hash For object, use to_hash. Otherwise, just return the value
607 608 609 610 611 612 613 614 615 616 617 618 619 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 607 def _to_hash(value) if value.is_a?(Array) value.compact.map { |v| _to_hash(v) } elsif value.is_a?(Hash) {}.tap do |hash| value.each { |k, v| hash[k] = _to_hash(v) } end elsif value.respond_to? :to_hash value.to_hash else value end end |
#eql?(o) ⇒ Boolean
499 500 501 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 499 def eql?(o) self == o end |
#hash ⇒ Integer
Calculates hash code according to all attributes.
505 506 507 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 505 def hash [model, prompt, best_of, echo, frequency_penalty, logit_bias, logprobs, max_tokens, n, presence_penalty, seed, stop, stream, suffix, temperature, top_p, user].hash end |
#list_invalid_properties ⇒ Object
Show invalid properties with the reasons. Usually used together with valid?
248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 248 def list_invalid_properties warn '[DEPRECATED] the `list_invalid_properties` method is obsolete' invalid_properties = Array.new if @model.nil? invalid_properties.push('invalid value for "model", model cannot be nil.') end if !@best_of.nil? && @best_of > 20 invalid_properties.push('invalid value for "best_of", must be smaller than or equal to 20.') end if !@best_of.nil? && @best_of < 0 invalid_properties.push('invalid value for "best_of", must be greater than or equal to 0.') end if !@frequency_penalty.nil? && @frequency_penalty > 2 invalid_properties.push('invalid value for "frequency_penalty", must be smaller than or equal to 2.') end if !@frequency_penalty.nil? && @frequency_penalty < -2 invalid_properties.push('invalid value for "frequency_penalty", must be greater than or equal to -2.') end if !@logprobs.nil? && @logprobs > 5 invalid_properties.push('invalid value for "logprobs", must be smaller than or equal to 5.') end if !@logprobs.nil? && @logprobs < 0 invalid_properties.push('invalid value for "logprobs", must be greater than or equal to 0.') end if !@max_tokens.nil? && @max_tokens < 0 invalid_properties.push('invalid value for "max_tokens", must be greater than or equal to 0.') end if !@n.nil? && @n > 128 invalid_properties.push('invalid value for "n", must be smaller than or equal to 128.') end if !@n.nil? && @n < 1 invalid_properties.push('invalid value for "n", must be greater than or equal to 1.') end if !@presence_penalty.nil? && @presence_penalty > 2 invalid_properties.push('invalid value for "presence_penalty", must be smaller than or equal to 2.') end if !@presence_penalty.nil? && @presence_penalty < -2 invalid_properties.push('invalid value for "presence_penalty", must be greater than or equal to -2.') end if !@seed.nil? && @seed > 9223372036854775807 invalid_properties.push('invalid value for "seed", must be smaller than or equal to 9223372036854775807.') end if !@seed.nil? && @seed < -9223372036854775808 invalid_properties.push('invalid value for "seed", must be greater than or equal to -9223372036854775808.') end if !@temperature.nil? && @temperature > 2 invalid_properties.push('invalid value for "temperature", must be smaller than or equal to 2.') end if !@temperature.nil? && @temperature < 0 invalid_properties.push('invalid value for "temperature", must be greater than or equal to 0.') end if !@top_p.nil? && @top_p > 1 invalid_properties.push('invalid value for "top_p", must be smaller than or equal to 1.') end if !@top_p.nil? && @top_p < 0 invalid_properties.push('invalid value for "top_p", must be greater than or equal to 0.') end invalid_properties end |
#to_body ⇒ Hash
to_body is an alias to to_hash (backward compatibility)
583 584 585 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 583 def to_body to_hash end |
#to_hash ⇒ Hash
Returns the object in the form of hash
589 590 591 592 593 594 595 596 597 598 599 600 601 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 589 def to_hash hash = {} self.class.attribute_map.each_pair do |attr, param| value = self.send(attr) if value.nil? is_nullable = self.class.openapi_nullable.include?(attr) next if !is_nullable || (is_nullable && !instance_variable_defined?(:"@#{attr}")) end hash[param] = _to_hash(value) end hash end |
#to_s ⇒ String
Returns the string representation of the object
577 578 579 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 577 def to_s to_hash.to_s end |
#valid? ⇒ Boolean
Check to see if the all the properties in the model are valid
328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 |
# File 'lib/openapi_openai/models/create_completion_request.rb', line 328 def valid? warn '[DEPRECATED] the `valid?` method is obsolete' return false if @model.nil? return false if !@best_of.nil? && @best_of > 20 return false if !@best_of.nil? && @best_of < 0 return false if !@frequency_penalty.nil? && @frequency_penalty > 2 return false if !@frequency_penalty.nil? && @frequency_penalty < -2 return false if !@logprobs.nil? && @logprobs > 5 return false if !@logprobs.nil? && @logprobs < 0 return false if !@max_tokens.nil? && @max_tokens < 0 return false if !@n.nil? && @n > 128 return false if !@n.nil? && @n < 1 return false if !@presence_penalty.nil? && @presence_penalty > 2 return false if !@presence_penalty.nil? && @presence_penalty < -2 return false if !@seed.nil? && @seed > 9223372036854775807 return false if !@seed.nil? && @seed < -9223372036854775808 return false if !@temperature.nil? && @temperature > 2 return false if !@temperature.nil? && @temperature < 0 return false if !@top_p.nil? && @top_p > 1 return false if !@top_p.nil? && @top_p < 0 true end |