Struct CreateChatCompletionRequest

pub struct CreateChatCompletionRequest {
    pub model: Model,
    pub messages: Vec<ChatMessage>,
    pub temperature: Option<f64>,
    pub top_p: Option<f64>,
    pub n: Option<u32>,
    pub stream: Option<bool>,
    pub max_tokens: Option<u32>,
    pub logit_bias: Option<HashMap<String, i32>>,
    pub user: Option<String>,
}

A request struct for creating chat completions with the OpenAI Chat Completions API.

Fields

• model: The ID of the model to use (e.g., “gpt-3.5-turbo”).
• messages: A list of ChatMessage items providing the conversation history.
• stream: Whether or not to stream responses via server-sent events.
• max_tokens, temperature, top_p, etc.: Parameters controlling the generation.
• n: Number of chat completion choices to generate.
• logit_bias, user: Additional advanced parameters.

Fields

model: Model

Required. The model used for this chat request. Examples: “Model::O1Mini”, “Model::Other(“gpt-4”.to_string)“.

messages: Vec<ChatMessage>

Required. The messages that make up the conversation so far.

temperature: Option<f64>

Controls the creativity of the output. 0 is the most deterministic, 2 is the most creative.

top_p: Option<f64>

The nucleus sampling parameter. Like temperature, but a value like 0.1 means only the top 10% probability mass is considered.

n: Option<u32>

How many chat completion choices to generate for each input message. Defaults to 1.

stream: Option<bool>

If set, partial message deltas are sent as data-only server-sent events (SSE) as they become available.

max_tokens: Option<u32>

The maximum number of tokens allowed for the generated answer. Defaults to the max tokens allowed by the model minus the prompt.

logit_bias: Option<HashMap<String, i32>>

A map between token (encoded as a string) and an associated bias from -100 to 100 that adjusts the likelihood of the token appearing.

user: Option<String>

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

Trait Implementations

impl Clone for CreateChatCompletionRequest

fn clone(&self) -> CreateChatCompletionRequest

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for CreateChatCompletionRequest

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

Formats the value using the given formatter.

impl Default for CreateChatCompletionRequest

fn default() -> CreateChatCompletionRequest

Returns the “default value” for a type.

impl Serialize for CreateChatCompletionRequest

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

where __S: Serializer,

Serialize this value into the given Serde serializer.