Struct ChatCompletion

pub struct ChatCompletion {
    pub model: Model,
    pub messages: Vec<ChatMessage>,
    pub stream: Option<bool>,
    pub temperature: Option<f32>,
    pub top_p: Option<f32>,
    pub n: Option<u32>,
    pub stop: Option<Vec<String>>,
    pub max_tokens: Option<u32>,
    pub presence_penalty: Option<f32>,
    pub frequency_penalty: Option<f32>,
    pub logit_bias: Option<HashMap<String, f32>>,
    pub user: Option<String>,
}

Given a chat conversation, the model will return a chat completion response.

Fields

model: Model

messages: Vec<ChatMessage>

stream: Option<bool>

temperature: Option<f32>

top_p: Option<f32>

n: Option<u32>

stop: Option<Vec<String>>

max_tokens: Option<u32>

presence_penalty: Option<f32>

frequency_penalty: Option<f32>

logit_bias: Option<HashMap<String, f32>>

user: Option<String>

Implementations

impl ChatCompletion

pub fn model(self, model: Model) -> Self

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

Argument

• model - Target model to make use of

pub fn message(self, role: MessageRole, content: &str) -> Self

Add message to prompt by role and content.

The messages to generate chat completions for, in the chat format.

Arguments

• role - Message role enum variant
• content - Message content

pub fn messages(self, messages: Vec<ChatMessage>) -> Self

Add message to prompt by message instance.

The messages to generate chat completions for, in the chat format.

Argument

• messages - Message instance vector, will replace all existing messages

pub fn temperature(self, temperature: f32) -> Self

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.

pub fn top_p(self, top_p: f32) -> Self

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.

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

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

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

Up to 4 sequences where the API will stop generating further tokens.

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

The total length of input tokens and generated tokens is limited by the model’s context length.

pub fn presence_penalty(self, presence_penalty: f32) -> Self

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.

pub fn frequency_penalty(self, frequency_penalty: f32) -> Self

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.

pub fn logit_bias(self, logit_bias: HashMap<String, f32>) -> Self

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.

pub fn user(self, user: &str) -> Self

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

pub async fn streamed_completion( self, cb: Option<impl FnMut(Chunk)>, ) -> Result<Vec<Chunk>, Box<dyn Error>>

Send chat completion request to OpenAI using streamed method.

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. See the OpenAI Cookbook for example code.

pub async fn completion(self) -> Result<ChatCompletionResponse, Box<dyn Error>>

Send chat completion request to OpenAI.

Trait Implementations

impl Debug for ChatCompletion

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

Formats the value using the given formatter.

impl Default for ChatCompletion

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ChatCompletion

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for ChatCompletion

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

where __S: Serializer,

Serialize this value into the given Serde serializer.