Class: VeniceClient::ChatCompletionRequest
- Inherits:
-
Object
- Object
- VeniceClient::ChatCompletionRequest
- Defined in:
- lib/venice_client/models/chat_completion_request.rb
Instance Attribute Summary collapse
-
#frequency_penalty ⇒ Object
Number between -2.0 and 2.0.
-
#logprobs ⇒ Object
Whether to include log probabilities in the response.
-
#max_completion_tokens ⇒ Object
An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.
-
#max_temp ⇒ Object
Maximum temperature value for dynamic temperature scaling.
-
#max_tokens ⇒ Object
The maximum number of tokens that can be generated in the chat completion.
-
#messages ⇒ Object
A list of messages comprising the conversation so far.
-
#min_p ⇒ Object
Sets a minimum probability threshold for token selection.
-
#min_temp ⇒ Object
Minimum temperature value for dynamic temperature scaling.
-
#model ⇒ Object
The ID of the model you wish to prompt.
-
#n ⇒ Object
How many chat completion choices to generate for each input message.
-
#parallel_tool_calls ⇒ Object
Whether to enable parallel function calling during tool use.
-
#presence_penalty ⇒ Object
Number between -2.0 and 2.0.
-
#repetition_penalty ⇒ Object
The parameter for repetition penalty.
-
#response_format ⇒ Object
Format in which the response should be returned.
-
#seed ⇒ Object
The random seed used to generate the response.
-
#stop ⇒ Object
Up to 4 sequences where the API will stop generating further tokens.
-
#stop_token_ids ⇒ Object
Array of token IDs where the API will stop generating further tokens.
-
#stream ⇒ Object
Whether to stream back partial progress.
-
#stream_options ⇒ Object
Returns the value of attribute stream_options.
-
#temperature ⇒ Object
What sampling temperature to use, between 0 and 2.
-
#tool_choice ⇒ Object
Returns the value of attribute tool_choice.
-
#tools ⇒ Object
A list of tools the model may call.
-
#top_k ⇒ Object
The number of highest probability vocabulary tokens to keep for top-k-filtering.
-
#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
This field is discarded on the request but is supported in the Venice API for compatibility with OpenAPI clients.
-
#venice_parameters ⇒ Object
Returns the value of attribute venice_parameters.
Class Method Summary collapse
-
.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.
-
#_deserialize(type, value) ⇒ Object
Deserializes the data based on type.
-
#_to_hash(value) ⇒ Hash
Outputs non-array value in the form of hash For object, use to_hash.
-
#build_from_hash(attributes) ⇒ Object
Builds the object from hash.
- #eql?(o) ⇒ Boolean
-
#hash ⇒ Integer
Calculates hash code according to all attributes.
-
#initialize(attributes = {}) ⇒ ChatCompletionRequest
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 = {}) ⇒ ChatCompletionRequest
Initializes the object
164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 164 def initialize(attributes = {}) if (!attributes.is_a?(Hash)) fail ArgumentError, "The input argument (attributes) must be a hash in `VeniceClient::ChatCompletionRequest` 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 `VeniceClient::ChatCompletionRequest`. 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?(:'frequency_penalty') self.frequency_penalty = attributes[:'frequency_penalty'] else self.frequency_penalty = 0 end if attributes.key?(:'logprobs') self.logprobs = attributes[:'logprobs'] end if attributes.key?(:'max_completion_tokens') self.max_completion_tokens = attributes[:'max_completion_tokens'] end if attributes.key?(:'max_temp') self.max_temp = attributes[:'max_temp'] end if attributes.key?(:'max_tokens') self.max_tokens = attributes[:'max_tokens'] end if attributes.key?(:'messages') if (value = attributes[:'messages']).is_a?(Array) self. = value end end if attributes.key?(:'min_p') self.min_p = attributes[:'min_p'] end if attributes.key?(:'min_temp') self.min_temp = attributes[:'min_temp'] end if attributes.key?(:'model') self.model = attributes[:'model'] 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?(:'repetition_penalty') self.repetition_penalty = attributes[:'repetition_penalty'] end if attributes.key?(:'seed') self.seed = attributes[:'seed'] end if attributes.key?(:'stop') self.stop = attributes[:'stop'] end if attributes.key?(:'stop_token_ids') if (value = attributes[:'stop_token_ids']).is_a?(Array) self.stop_token_ids = value end end if attributes.key?(:'stream') self.stream = attributes[:'stream'] end if attributes.key?(:'stream_options') self. = attributes[:'stream_options'] end if attributes.key?(:'temperature') self.temperature = attributes[:'temperature'] else self.temperature = 0.3 end if attributes.key?(:'top_k') self.top_k = attributes[:'top_k'] 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 if attributes.key?(:'venice_parameters') self.venice_parameters = attributes[:'venice_parameters'] end if attributes.key?(:'parallel_tool_calls') self.parallel_tool_calls = attributes[:'parallel_tool_calls'] else self.parallel_tool_calls = true end if attributes.key?(:'response_format') self.response_format = attributes[:'response_format'] end if attributes.key?(:'tool_choice') self.tool_choice = attributes[:'tool_choice'] end if attributes.key?(:'tools') if (value = attributes[:'tools']).is_a?(Array) self.tools = value end end end |
Instance Attribute Details
#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.
17 18 19 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 17 def frequency_penalty @frequency_penalty end |
#logprobs ⇒ Object
Whether to include log probabilities in the response. This is not supported by all models.
20 21 22 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 20 def logprobs @logprobs end |
#max_completion_tokens ⇒ Object
An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.
23 24 25 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 23 def max_completion_tokens @max_completion_tokens end |
#max_temp ⇒ Object
Maximum temperature value for dynamic temperature scaling.
26 27 28 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 26 def max_temp @max_temp end |
#max_tokens ⇒ Object
The maximum number of tokens that can be generated in the chat completion. This value can be used to control costs for text generated via API. This value is now deprecated in favor of max_completion_tokens.
29 30 31 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 29 def max_tokens @max_tokens end |
#messages ⇒ Object
A list of messages comprising the conversation so far. Depending on the model you use, different message types (modalities) are supported, like text and images. For compatibility purposes, the schema supports submitting multiple image_url messages, however, only the last image_url message will be passed to and processed by the model.
32 33 34 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 32 def end |
#min_p ⇒ Object
Sets a minimum probability threshold for token selection. Tokens with probabilities below this value are filtered out.
35 36 37 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 35 def min_p @min_p end |
#min_temp ⇒ Object
Minimum temperature value for dynamic temperature scaling.
38 39 40 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 38 def min_temp @min_temp end |
#model ⇒ Object
The ID of the model you wish to prompt. May also be a model trait, or a compatibility mapping. See the models endpoint for a list of models available to you. You can use feature suffixes to enable features from the venice_parameters object. Please see "Model Feature Suffix" documentation for more details.
41 42 43 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 41 def model @model end |
#n ⇒ Object
How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs.
44 45 46 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 44 def n @n end |
#parallel_tool_calls ⇒ Object
Whether to enable parallel function calling during tool use.
81 82 83 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 81 def parallel_tool_calls @parallel_tool_calls 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.
47 48 49 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 47 def presence_penalty @presence_penalty end |
#repetition_penalty ⇒ Object
The parameter for repetition penalty. 1.0 means no penalty. Values > 1.0 discourage repetition.
50 51 52 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 50 def repetition_penalty @repetition_penalty end |
#response_format ⇒ Object
Format in which the response should be returned.
84 85 86 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 84 def response_format @response_format end |
#seed ⇒ Object
The random seed used to generate the response. This is useful for reproducibility.
53 54 55 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 53 def seed @seed end |
#stop ⇒ Object
Up to 4 sequences where the API will stop generating further tokens. Defaults to null.
56 57 58 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 56 def stop @stop end |
#stop_token_ids ⇒ Object
Array of token IDs where the API will stop generating further tokens.
59 60 61 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 59 def stop_token_ids @stop_token_ids end |
#stream ⇒ Object
Whether to stream back partial progress. Defaults to false.
62 63 64 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 62 def stream @stream end |
#stream_options ⇒ Object
Returns the value of attribute stream_options.
64 65 66 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 64 def 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.
67 68 69 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 67 def temperature @temperature end |
#tool_choice ⇒ Object
Returns the value of attribute tool_choice.
86 87 88 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 86 def tool_choice @tool_choice end |
#tools ⇒ Object
A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for.
89 90 91 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 89 def tools @tools end |
#top_k ⇒ Object
The number of highest probability vocabulary tokens to keep for top-k-filtering.
70 71 72 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 70 def top_k @top_k 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.
73 74 75 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 73 def top_p @top_p end |
#user ⇒ Object
This field is discarded on the request but is supported in the Venice API for compatibility with OpenAPI clients.
76 77 78 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 76 def user @user end |
#venice_parameters ⇒ Object
Returns the value of attribute venice_parameters.
78 79 80 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 78 def venice_parameters @venice_parameters end |
Class Method Details
.attribute_map ⇒ Object
Attribute mapping from ruby-style variable name to JSON key.
92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 92 def self.attribute_map { :'frequency_penalty' => :'frequency_penalty', :'logprobs' => :'logprobs', :'max_completion_tokens' => :'max_completion_tokens', :'max_temp' => :'max_temp', :'max_tokens' => :'max_tokens', :'messages' => :'messages', :'min_p' => :'min_p', :'min_temp' => :'min_temp', :'model' => :'model', :'n' => :'n', :'presence_penalty' => :'presence_penalty', :'repetition_penalty' => :'repetition_penalty', :'seed' => :'seed', :'stop' => :'stop', :'stop_token_ids' => :'stop_token_ids', :'stream' => :'stream', :'stream_options' => :'stream_options', :'temperature' => :'temperature', :'top_k' => :'top_k', :'top_p' => :'top_p', :'user' => :'user', :'venice_parameters' => :'venice_parameters', :'parallel_tool_calls' => :'parallel_tool_calls', :'response_format' => :'response_format', :'tool_choice' => :'tool_choice', :'tools' => :'tools' } end |
.build_from_hash(attributes) ⇒ Object
Builds the object from hash
371 372 373 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 371 def self.build_from_hash(attributes) new.build_from_hash(attributes) end |
.openapi_nullable ⇒ Object
List of attributes with nullable: true
156 157 158 159 160 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 156 def self.openapi_nullable Set.new([ :'tools' ]) end |
.openapi_types ⇒ Object
Attribute type mapping.
124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 124 def self.openapi_types { :'frequency_penalty' => :'Object', :'logprobs' => :'Object', :'max_completion_tokens' => :'Object', :'max_temp' => :'Object', :'max_tokens' => :'Object', :'messages' => :'Object', :'min_p' => :'Object', :'min_temp' => :'Object', :'model' => :'Object', :'n' => :'Object', :'presence_penalty' => :'Object', :'repetition_penalty' => :'Object', :'seed' => :'Object', :'stop' => :'Object', :'stop_token_ids' => :'Object', :'stream' => :'Object', :'stream_options' => :'Object', :'temperature' => :'Object', :'top_k' => :'Object', :'top_p' => :'Object', :'user' => :'Object', :'venice_parameters' => :'Object', :'parallel_tool_calls' => :'Object', :'response_format' => :'Object', :'tool_choice' => :'Object', :'tools' => :'Object' } end |
Instance Method Details
#==(o) ⇒ Object
Checks equality by comparing each attribute.
325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 325 def ==(o) return true if self.equal?(o) self.class == o.class && frequency_penalty == o.frequency_penalty && logprobs == o.logprobs && max_completion_tokens == o.max_completion_tokens && max_temp == o.max_temp && max_tokens == o.max_tokens && == o. && min_p == o.min_p && min_temp == o.min_temp && model == o.model && n == o.n && presence_penalty == o.presence_penalty && repetition_penalty == o.repetition_penalty && seed == o.seed && stop == o.stop && stop_token_ids == o.stop_token_ids && stream == o.stream && == o. && temperature == o.temperature && top_k == o.top_k && top_p == o.top_p && user == o.user && venice_parameters == o.venice_parameters && parallel_tool_calls == o.parallel_tool_calls && response_format == o.response_format && tool_choice == o.tool_choice && tools == o.tools end |
#_deserialize(type, value) ⇒ Object
Deserializes the data based on type
401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 401 def _deserialize(type, value) case type.to_sym when :DateTime DateTime.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 VeniceClient.const_get(type).build_from_hash(value) end end |
#_to_hash(value) ⇒ Hash
Outputs non-array value in the form of hash For object, use to_hash. Otherwise, just return the value
470 471 472 473 474 475 476 477 478 479 480 481 482 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 470 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 |
#build_from_hash(attributes) ⇒ Object
Builds the object from hash
378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 378 def build_from_hash(attributes) return nil unless attributes.is_a?(Hash) self.class.openapi_types.each_pair do |key, type| if 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[self.class.attribute_map[key]].is_a?(Array) self.send("#{key}=", attributes[self.class.attribute_map[key]].map { |v| _deserialize($1, v) }) end elsif !attributes[self.class.attribute_map[key]].nil? self.send("#{key}=", _deserialize(type, attributes[self.class.attribute_map[key]])) elsif attributes[self.class.attribute_map[key]].nil? && self.class.openapi_nullable.include?(key) self.send("#{key}=", nil) end end self end |
#eql?(o) ⇒ Boolean
358 359 360 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 358 def eql?(o) self == o end |
#hash ⇒ Integer
Calculates hash code according to all attributes.
364 365 366 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 364 def hash [frequency_penalty, logprobs, max_completion_tokens, max_temp, max_tokens, , min_p, min_temp, model, n, presence_penalty, repetition_penalty, seed, stop, stop_token_ids, stream, , temperature, top_k, top_p, user, venice_parameters, parallel_tool_calls, response_format, tool_choice, tools].hash end |
#list_invalid_properties ⇒ Object
Show invalid properties with the reasons. Usually used together with valid?
302 303 304 305 306 307 308 309 310 311 312 313 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 302 def list_invalid_properties invalid_properties = Array.new if .nil? invalid_properties.push('invalid value for "messages", messages cannot be nil.') end if @model.nil? invalid_properties.push('invalid value for "model", model cannot be nil.') end invalid_properties end |
#to_body ⇒ Hash
to_body is an alias to to_hash (backward compatibility)
446 447 448 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 446 def to_body to_hash end |
#to_hash ⇒ Hash
Returns the object in the form of hash
452 453 454 455 456 457 458 459 460 461 462 463 464 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 452 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
440 441 442 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 440 def to_s to_hash.to_s end |
#valid? ⇒ Boolean
Check to see if the all the properties in the model are valid
317 318 319 320 321 |
# File 'lib/venice_client/models/chat_completion_request.rb', line 317 def valid? return false if .nil? return false if @model.nil? true end |