Struct ChatCompletionRequest

pub struct ChatCompletionRequest {
    pub model: String,
    pub messages: Vec<ChatCompletionMessage>,
    pub temperature: Option<f64>,
    pub max_tokens: Option<u32>,
    pub top_p: Option<f64>,
    pub stream: Option<bool>,
    pub stop: Option<Vec<String>>,
    pub seed: Option<u64>,
}

Represents a request to the OpenAI chat completion API.

• model: The language model to use for the chat completion.
• messages: The messages to provide as context for the chat completion.
• temperature: The temperature parameter to control the randomness of the generated response.
• max_tokens: The maximum number of tokens to generate in the response.
• top_p: The top-p parameter to control the nucleus sampling.
• stream: Whether to stream the response or return it all at once.
• stop: A list of strings to stop the generation when encountered.
• seed: The seed value to use for the random number generator.

Fields

model: String

messages: Vec<ChatCompletionMessage>

temperature: Option<f64>

max_tokens: Option<u32>

top_p: Option<f64>

stream: Option<bool>

stop: Option<Vec<String>>

seed: Option<u64>

Implementations

impl ChatCompletionRequest

Represents a request to the OpenAI chat completion API.

This struct provides a builder-style API for constructing a ChatCompletionRequest with various optional parameters. The new method creates a new instance with default values, and the other methods allow modifying individual parameters.

• model: The language model to use for the chat completion.
• messages: The messages to provide as context for the chat completion.
• temperature: The temperature parameter to control the randomness of the generated response.
• max_tokens: The maximum number of tokens to generate in the response.
• top_p: The top-p parameter to control the nucleus sampling.
• stream: Whether to stream the response or return it all at once.
• stop: A list of strings to stop the generation when encountered.
• seed: The seed value to use for the random number generator.

pub fn new(model: &str, messages: Vec<ChatCompletionMessage>) -> Self

Creates a new ChatCompletionRequest instance with the given model and messages.

Arguments

• model - The language model to use for the chat completion.
• messages - The messages to provide as context for the chat completion.

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

Sets the temperature parameter for the chat completion request.

The temperature parameter controls the randomness of the generated response. Higher values (up to 1.0) make the output more random, while lower values make it more deterministic.

Arguments

• temperature - The temperature value to use.

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

Sets the maximum number of tokens to generate in the response.

Arguments

• max_tokens - The maximum number of tokens to generate.

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

Sets the top-p parameter for the chat completion request.

The top-p parameter controls the nucleus sampling, which is a technique for sampling from the most likely tokens.

Arguments

• top_p - The top-p value to use.

pub fn stream(self, stream: bool) -> Self

Sets whether to stream the response or return it all at once.

Arguments

• stream - Whether to stream the response or not.

pub fn stop(self, stop: Vec<String>) -> Self

Sets the list of strings to stop the generation when encountered.

Arguments

• stop - The list of stop strings.

pub fn seed(self, seed: u64) -> Self

Sets the seed value to use for the random number generator.

Arguments

• seed - The seed value to use.

Trait Implementations

impl Clone for ChatCompletionRequest

fn clone(&self) -> ChatCompletionRequest

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for ChatCompletionRequest

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

Formats the value using the given formatter.