/**
 * This file was auto-generated by Fern from our API Definition.
 */
import * as OctoAI from "../../../../index";
/**
 * @example
 *     {
 *         frequencyPenalty: 1.1,
 *         ignoreEos: true,
 *         logPrompt: true,
 *         logitBias: {
 *             "string": {
 *                 "key": "value"
 *             }
 *         },
 *         loglikelihood: true,
 *         logprobs: true,
 *         maxTokens: 1,
 *         messages: [{
 *                 content: "string",
 *                 role: "string",
 *                 toolCalls: [{
 *                         function: {
 *                             arguments: "string",
 *                             name: "string"
 *                         },
 *                         id: {
 *                             "key": "value"
 *                         },
 *                         type: {
 *                             "key": "value"
 *                         }
 *                     }]
 *             }],
 *         minP: 1.1,
 *         model: "string",
 *         n: 1,
 *         peft: "string",
 *         presencePenalty: 1.1,
 *         repetitionPenalty: 1.1,
 *         responseFormat: {
 *             schema: {
 *                 "string": {
 *                     "key": "value"
 *                 }
 *             },
 *             type: "string"
 *         },
 *         stop: "string",
 *         streamOptions: {
 *             includeUsage: true
 *         },
 *         temperature: 1.1,
 *         toolChoice: "auto",
 *         tools: [{
 *                 function: {
 *                     description: "string",
 *                     name: "string",
 *                     parameters: {
 *                         "string": {
 *                             "key": "value"
 *                         }
 *                     }
 *                 },
 *                 type: "function"
 *             }],
 *         topLogprobs: 1,
 *         topP: 1.1,
 *         user: "string"
 *     }
 */
export interface CreateChatCompletionStreamRequest {
    /** 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;
    /** Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the content of message. */
    logprobs?: boolean;
    /** Maximum number of tokens to generate per output sequence. */
    maxTokens?: number;
    /** A list of messages comprising the conversation so far. */
    messages: OctoAI.textGen.ChatMessage[];
    /** 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;
    /** Controls the likelihood of the model generating repeated texts. */
    repetitionPenalty?: number;
    /** Allows specification of a response format and associated schema that will constrain the LLM output to that structure. For example, using the `json_object` type allows you to provide a desired json schema for the output to follow. */
    responseFormat?: OctoAI.textGen.ChatCompletionResponseFormat;
    /** Generation stop condition. */
    stop?: OctoAI.textGen.Stop;
    /** If set, usageStats will be streamed on the last content-containing chunk. */
    streamOptions?: OctoAI.textGen.StreamOptions;
    /** Controls the randomness of the sampling. */
    temperature?: number;
    /** Controls which (if any) tool is called by the model. none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools. Specifying a particular tool via {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool. none is the default when no tools are present. auto is the default if tools are present. */
    toolChoice?: OctoAI.textGen.CreateChatCompletionStreamRequestToolChoice;
    /** 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. A max of 128 functions are supported. */
    tools?: OctoAI.textGen.ToolDefinition[];
    /** An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. `logprobs` must be set to `true` if this parameter is used. */
    topLogprobs?: number;
    /** Controls the cumulative probability of the top tokens to consider. */
    topP?: number;
    /** A unique identifier representing your end-user. */
    user?: string;
}