/**
 * This file was auto-generated by Fern from our API Definition.
 */
import * as OctoAI from "../../../../index";
/**
 * @example
 *     {
 *         bestOf: 1,
 *         echo: true,
 *         frequencyPenalty: 1.1,
 *         ignoreEos: true,
 *         logPrompt: true,
 *         logitBias: {
 *             "string": {
 *                 "key": "value"
 *             }
 *         },
 *         loglikelihood: true,
 *         logprobs: 1,
 *         maxTokens: 1,
 *         minP: 1.1,
 *         model: "string",
 *         n: 1,
 *         peft: "string",
 *         presencePenalty: 1.1,
 *         prompt: "string",
 *         repetitionPenalty: 1.1,
 *         seed: 1,
 *         stop: "string",
 *         streamOptions: {
 *             includeUsage: true
 *         },
 *         suffix: "string",
 *         temperature: 1.1,
 *         topP: 1.1,
 *         user: "string"
 *     }
 */
export interface CreateCompletionStreamRequest {
    /** Number of sequences that are generated from the prompt.`best_of` must be greater than or equal to `n`. */
    bestOf?: number;
    /** Echo back the prompt in addition to the completion. */
    echo?: boolean;
    /** Penalizes new tokens based on their frequency in the generated text so far. */
    frequencyPenalty?: number;
    /** Whether to ignore the EOS token and continue generating tokens after the EOS token is generated. */
    ignoreEos?: boolean;
    /** OctoAI stores request prompt if True. */
    logPrompt?: boolean;
    /** Modify the likelihood of specified tokens appearing in the completion. Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. 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. */
    logitBias?: Record<string, number | undefined>;
    /** Return log probabilities for all prompt tokens excluding the first one from prefill step if True. */
    loglikelihood?: boolean;
    /** Number of log probabilities to return per output token. */
    logprobs?: number;
    /** Maximum number of tokens to generate per output sequence. */
    maxTokens?: number;
    /** Sets a dynamic threshold of the top tokens to consider based on the probability value of the most likely next token. Following https://arxiv.org/abs/2407.01082. */
    minP?: number;
    /** The identifier of the model to use. Can be a shared tenancy or custom model identifier. */
    model: string;
    /** Number of output sequences to return. */
    n?: number;
    /** Parameter-efficient fine-tuning ID. */
    peft?: string;
    /** Penalizes new tokens based on whether they appear in the generated text so far. */
    presencePenalty?: number;
    /** The prompt to generate completions from. */
    prompt?: OctoAI.textGen.Prompt;
    /** Controls the likelihood of the model generating repeated texts. */
    repetitionPenalty?: number;
    /** 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. */
    seed?: number;
    /** Generation stop condition. */
    stop?: OctoAI.textGen.Stop;
    /** If set, usageStats will be streamed on the last content-containing chunk. */
    streamOptions?: OctoAI.textGen.StreamOptions;
    /** The suffix that comes after a completion of inserted text. */
    suffix?: string;
    /** Controls the randomness of the sampling. */
    temperature?: number;
    /** Controls the cumulative probability of the top tokens to consider. */
    topP?: number;
    /** A unique identifier representing your end-user. */
    user?: string;
}