open_ai_rust 0.2.11

use serde::{Deserialize, Serialize};

use crate::logoi::{message::ChatMessage, models::OpenAiModel};

use super::tool::{FunctionCall, ToolChoice};

pub mod templates;
pub mod builder;

// Chat
// Given a list of messages comprising a conversation, the model will return a response.

// Related guide: Chat Completions

// Create chat completion
// post

// https://api.openai.com/v1/chat/completions
// Creates a model response for the given chat conversation.

// Request body
// messages
// array

// Required
// A list of messages comprising the conversation so far. Example Python code.


// Show possible types
// model
// string

// Required
// ID of the model to use. See the model endpoint compatibility table for details on which models work with the Chat API.

// frequency_penalty
// number or null

// Optional
// Defaults to 0
// 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.

// logit_bias
// map

// Optional
// Defaults to null
// 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.

// logprobs
// boolean or null

// Optional
// Defaults to false
// 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.

// top_logprobs
// integer or null

// Optional
// 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.

// max_tokens
// integer or null

// Optional
// The maximum number of tokens that can be generated in the chat completion.

// The total length of input tokens and generated tokens is limited by the model's context length. Example Python code for counting tokens.

// n
// integer or null

// Optional
// Defaults to 1
// 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.

// presence_penalty
// number or null

// Optional
// Defaults to 0
// 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.

// response_format
// object

// Optional
// An object specifying the format that the model must output. Compatible with GPT-4o, GPT-4o mini, GPT-4 Turbo and all GPT-3.5 Turbo models newer than gpt-3.5-turbo-1106.

// Setting to { "type": "json_object" } enables JSON mode, which guarantees the message the model generates is valid JSON.

// Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.


// Show properties
// seed
// integer or null

// Optional
// This feature is in Beta. 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.

// service_tier
// string or null

// Optional
// Defaults to null
// Specifies the latency tier to use for processing the request. This parameter is relevant for customers subscribed to the scale tier service:

// If set to 'auto', the system will utilize scale tier credits until they are exhausted.
// If set to 'default', the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee.
// When not set, the default behavior is 'auto'.
// When this parameter is set, the response body will include the service_tier utilized.

// stop
// string / array / null

// Optional
// Defaults to null
// Up to 4 sequences where the API will stop generating further tokens.

// stream
// boolean or null

// Optional
// Defaults to false
// If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. Example Python code.

// stream_options
// object or null

// Optional
// Defaults to null
// Options for streaming response. Only set this when you set stream: true.


// Show properties
// temperature
// number or null

// Optional
// Defaults to 1
// 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.

// top_p
// number or null

// Optional
// Defaults to 1
// 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.

// tools
// array

// Optional
// 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.


// Show properties
// tool_choice
// string or object

// Optional
// 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.


// Show possible types
// parallel_tool_calls
// boolean

// Optional
// Defaults to true
// Whether to enable parallel function calling during tool use.

// user
// string

// Optional
// A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.

// function_call
// Deprecated
// string or object

// Optional
// Deprecated in favor of tool_choice.

// Controls which (if any) function is called by the model. 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.


// Show possible types
// functions
// Deprecated
// array

// Optional
// Deprecated in favor of tools.

// A list of functions the model may generate JSON inputs for.


// Show properties
// Returns

/// This payload covers regular chat, function calling, JSON mode and tool usage.
// from the docs above, make sure every case is covered to use except for deprecated properties

#[derive(Deserialize, Serialize, Debug, Clone)]
pub struct ChatPayLoad {
    pub model: OpenAiModel,
    pub messages: Vec<ChatMessage>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub tools: Option<Vec<ToolChoice>>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub tool_choice: Option<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub frequency_penalty: Option<f32>,
    // pub logit_bias: Option<LogitBias>, TODO: add. not urgent tho
    #[serde(skip_serializing_if = "Option::is_none")]
    pub logprobs: Option<bool>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub top_logprobs: Option<i32>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub max_tokens: Option<i32>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub n: Option<i32>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub presence_penalty: Option<f32>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub response_format: Option<ResponseFormatInput>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub seed: Option<i32>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub service_tier: Option<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub stop: Option<Vec<String>>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub stream: Option<bool>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub stream_options: Option<bool>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub temperature: Option<f32>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub top_p: Option<f32>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub user: Option<String>,
}

impl ChatPayLoad {
    pub fn new(model: OpenAiModel, messages: Vec<ChatMessage>) -> Self {
        Self {
            model,
            messages,
            frequency_penalty: None,
            logprobs: None,
            top_logprobs: None,
            max_tokens: None,
            n: None,
            presence_penalty: None,
            response_format: None,
            seed: None,
            service_tier: None,
            stop: None,
            stream: None,
            stream_options: None,
            temperature: None,
            top_p: None,
            tools: None,
            user: None,
            tool_choice: None,
        }
    }
}

// Must be one of text or json_object.
#[derive(Deserialize, Serialize, Debug, Clone)]
pub enum ResponseFormatInput {
    JsonObject,
    Text
}