import type { ChatCompletionFunctionCallOption } from "./ChatCompletionFunctionCallOption";
import type { ChatCompletionFunctions } from "./ChatCompletionFunctions";
import type { ChatCompletionRequestMessage } from "./ChatCompletionRequestMessage";
export type CreateChatCompletionRequest = {
    /**
     * A list of messages comprising the conversation so far. [Example Python code](https://cookbook.openai.com/examples/how_to_format_inputs_to_chatgpt_models).
     */
    messages: Array<ChatCompletionRequestMessage>;
    /**
     * ID of the model to use. See the [model endpoint compatibility](/docs/models/model-endpoint-compatibility) table for details on which models work with the Chat API.
     */
    model: string | "gpt-4" | "gpt-4-0314" | "gpt-4-0613" | "gpt-4-32k" | "gpt-4-32k-0314" | "gpt-4-32k-0613" | "gpt-3.5-turbo" | "gpt-3.5-turbo-16k" | "gpt-3.5-turbo-0301" | "gpt-3.5-turbo-0613" | "gpt-3.5-turbo-16k-0613";
    /**
     * 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/gpt/parameter-details)
     *
     */
    frequency_penalty?: number | null;
    /**
     * Controls how the model calls functions. "none" means the model will not call a function and instead generates a message. "auto" means the model can pick between generating a message or calling a function.  Specifying a particular function via `{"name": "my_function"}` forces the model to call that function. "none" is the default when no functions are present. "auto" is the default if functions are present.
     *
     */
    function_call?: "none" | "auto" | ChatCompletionFunctionCallOption;
    /**
     * A list of functions the model may generate JSON inputs for.
     */
    functions?: Array<ChatCompletionFunctions>;
    /**
     * 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.
     *
     */
    logit_bias?: Record<string, number> | null;
    /**
     * The maximum number of [tokens](/tokenizer) to generate in the chat completion.
     *
     * The total length of input tokens and generated tokens is limited by the model's context length. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens.
     *
     */
    max_tokens?: number | null;
    /**
     * How many chat completion choices to generate for each input message.
     */
    n?: number | null;
    /**
     * 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/gpt/parameter-details)
     *
     */
    presence_penalty?: number | null;
    /**
     * Up to 4 sequences where the API will stop generating further tokens.
     *
     */
    stop?: string | null | Array<string>;
    /**
     * If set, partial message deltas will be sent, like in ChatGPT. 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).
     *
     */
    stream?: boolean | 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.
     *
     */
    temperature?: number | null;
    /**
     * 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.
     *
     */
    top_p?: number | null;
    /**
     * 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).
     *
     */
    user?: string;
};