Struct ChatArguments

pub struct ChatArguments {
    pub model: String,
    pub messages: Vec<Message>,
    pub temperature: Option<f32>,
    pub top_p: Option<f32>,
    pub n: Option<u32>,
    pub stop: Option<String>,
    pub max_tokens: Option<u32>,
    pub presence_penalty: Option<f32>,
    pub frequency_penalty: Option<f32>,
    pub user: Option<String>,
    /* private fields */
}

Request arguments for chat completion.

See https://platform.openai.com/docs/api-reference/chat/create.

let args = openai_rust::chat::ChatArguments::new("gpt-3.5-turbo", vec![
    openai_rust::chat::Message {
        role: "user".to_owned(),
        content: "Hello GPT!".to_owned(),
    }
]);

To use streaming, use crate::Client::create_chat_stream.

Fields

model: String

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

messages: Vec<Message>

The Messages to generate chat completions for

temperature: Option<f32>

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: Option<f32>

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.

n: Option<u32>

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

stop: Option<String>

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

max_tokens: Option<u32>

The maximum number of tokens to generate in the chat completion.

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

presence_penalty: Option<f32>

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.

frequency_penalty: Option<f32>

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.

user: Option<String>

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

Implementations

impl ChatArguments

pub fn new(model: impl AsRef<str>, messages: Vec<Message>) -> ChatArguments

Examples found in repository

examples/chat_example.rs (lines 7-13)

async fn main() {
    let client = openai_rust::Client::new(&std::env::var("OPENAI_API_KEY").unwrap());
    let args = openai_rust::chat::ChatArguments::new(
        "gpt-3.5-turbo",
        vec![openai_rust::chat::Message {
            role: "user".to_owned(),
            content: "Hello GPT!".to_owned(),
        }],
    );
    let res = client.create_chat(args).await.unwrap();
    println!("{}", res);
}

examples/chat_stream_example.rs (lines 9-15)

async fn main() {
    let client = openai_rust::Client::new(&std::env::var("OPENAI_API_KEY").unwrap());
    let args = openai_rust::chat::ChatArguments::new(
        "gpt-3.5-turbo",
        vec![openai_rust::chat::Message {
            role: "user".to_owned(),
            content: "Hello GPT!".to_owned(),
        }],
    );
    let mut res = client.create_chat_stream(args).await.unwrap();
    while let Some(chunk) = res.next().await {
        print!("{}", chunk.unwrap());
        std::io::stdout().flush().unwrap();
    }
}

Trait Implementations

impl Clone for ChatArguments

fn clone(&self) -> ChatArguments

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for ChatArguments

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

Formats the value using the given formatter.

impl Serialize for ChatArguments

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

where __S: Serializer,

Serialize this value into the given Serde serializer.