Struct tokio_openai::ChatRequest

pub struct ChatRequest {
    pub model: ChatModel,
    pub messages: Vec<Msg>,
    pub temperature: f64,
    pub top_p: f64,
    pub n: u32,
    pub stop_at: Vec<String>,
    pub max_tokens: u32,
}

Fields

model: ChatModel

messages: Vec<Msg>

temperature: f64

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.

OpenAI generally recommend altering this or top_p but not both.

top_p: f64

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.

OpenAI generally recommends altering this or temperature but not both.

n: u32

How many chat completion choices to generate for each input message.

stop_at: Vec<String>

max_tokens: u32

max tokens to generate

if 0, then no limit

Implementations

impl ChatRequest

pub fn new() -> Self

pub fn model(self, model: impl Into<ChatModel>) -> Self

pub fn message(self, message: impl Into<Msg>) -> Self

pub fn temperature(self, temperature: impl Into<f64>) -> Self

pub fn top_p(self, top_p: impl Into<f64>) -> Self

pub fn n(self, n: u32) -> Self

pub fn stop_at(self, stop_at: impl Into<String>) -> Self

pub fn max_tokens(self, max_tokens: u32) -> Self

impl ChatRequest

pub fn sys_msg(self, msg: impl Into<String>) -> Self

pub fn user_msg(self, msg: impl Into<String>) -> Self

pub fn assistant_msg(self, msg: impl Into<String>) -> Self

Trait Implementations

impl Debug for ChatRequest

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for ChatRequest

fn default() -> Self

Returns the “default value” for a type.

impl<'a> From<&'a [Msg]> for ChatRequest

fn from(input: &'a [Msg]) -> Self

Converts to this type from the input type.

impl<'a> From<&'a String> for ChatRequest

fn from(input: &'a String) -> Self

Converts to this type from the input type.

impl<'a> From<&'a str> for ChatRequest

fn from(input: &'a str) -> Self

Converts to this type from the input type.

impl<const N: usize> From<[Msg; N]> for ChatRequest

fn from(input: [Msg; N]) -> Self

Converts to this type from the input type.

impl Serialize for ChatRequest

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>where __S: Serializer,

Serialize this value into the given Serde serializer.