commonMain.com.xebia.functional.openai.generated.model.CreateCompletionRequest.kt Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of xef-openai-client Show documentation
Show all versions of xef-openai-client Show documentation
Building applications with LLMs through composability in Kotlin
/**
*
* Please note:
* This class is auto generated by OpenAPI Generator (https://openapi-generator.tech).
* Do not edit this file manually.
*
*/
@file:Suppress(
"ArrayInDataClass",
"EnumEntryName",
"RemoveRedundantQualifierName",
"UnusedImport"
)
package com.xebia.functional.openai.generated.model
import com.xebia.functional.openai.generated.model.ChatCompletionStreamOptions
import com.xebia.functional.openai.generated.model.CreateCompletionRequestModel
import com.xebia.functional.openai.generated.model.CreateCompletionRequestPrompt
import com.xebia.functional.openai.generated.model.CreateCompletionRequestStop
import kotlinx.serialization.Serializable
import kotlinx.serialization.SerialName
import kotlinx.serialization.Contextual
import kotlin.js.JsName
import kotlinx.serialization.json.*
/**
*
*
* @param model
* @param prompt
* @param bestOf 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`.
* @param echo Echo back the prompt in addition to the completion
* @param frequencyPenalty 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)
* @param logitBias 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 `{\"50256\": -100}` to prevent the <|endoftext|> token from being generated.
* @param logprobs 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.
* @param maxTokens 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](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens.
* @param n 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`.
* @param presencePenalty 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)
* @param seed 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.
* @param stop
* @param stream Whether to stream back partial progress. If set, tokens will be sent as data-only [server-sent events](https://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](https://cookbook.openai.com/examples/how_to_stream_completions).
* @param streamOptions
* @param suffix The suffix that comes after a completion of inserted text. This parameter is only supported for `gpt-3.5-turbo-instruct`.
* @param temperature 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.
* @param topP 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.
* @param user 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).
*/
@Serializable
data class CreateCompletionRequest (
@SerialName(value = "model") val model: CreateCompletionRequestModel,
@SerialName(value = "prompt") val prompt: CreateCompletionRequestPrompt?,
/* 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`. */
@SerialName(value = "best_of") val bestOf: kotlin.Int? = 1,
/* Echo back the prompt in addition to the completion */
@SerialName(value = "echo") val echo: kotlin.Boolean? = false,
/* 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) */
@SerialName(value = "frequency_penalty") val frequencyPenalty: kotlin.Double? = (0).toDouble(),
/* 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 `{\"50256\": -100}` to prevent the <|endoftext|> token from being generated. */
@SerialName(value = "logit_bias") val logitBias: kotlin.collections.Map? = null,
/* 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. */
@SerialName(value = "logprobs") val logprobs: kotlin.Int? = null,
/* 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](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens. */
@SerialName(value = "max_tokens") val maxTokens: kotlin.Int? = 16,
/* 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`. */
@SerialName(value = "n") val n: kotlin.Int? = 1,
/* 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) */
@SerialName(value = "presence_penalty") val presencePenalty: kotlin.Double? = (0).toDouble(),
/* 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. */
@SerialName(value = "seed") val seed: kotlin.Int? = null,
@SerialName(value = "stop") val stop: CreateCompletionRequestStop? = null,
/* Whether to stream back partial progress. If set, tokens will be sent as data-only [server-sent events](https://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](https://cookbook.openai.com/examples/how_to_stream_completions). */
@SerialName(value = "stream") val stream: kotlin.Boolean? = false,
@SerialName(value = "stream_options") val streamOptions: ChatCompletionStreamOptions? = null,
/* The suffix that comes after a completion of inserted text. This parameter is only supported for `gpt-3.5-turbo-instruct`. */
@SerialName(value = "suffix") val suffix: kotlin.String? = null,
/* 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. */
@SerialName(value = "temperature") val temperature: kotlin.Double? = (1).toDouble(),
/* 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. */
@SerialName(value = "top_p") val topP: kotlin.Double? = (1).toDouble(),
/* 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). */
@SerialName(value = "user") val user: kotlin.String? = null
) {
}