unofficial OpenAI API client library for Rust

Installation:

Cargo.toml

[dependencies]
openai-api-rs = "0.1.5"

Usage

The library needs to be configured with your account's secret key, which is available on the website. We recommend setting it as an environment variable. Here's an example of initializing the library with the API key loaded from an environment variable and creating a completion:

Set OPENAI_API_KEY to environment variable

$ export OPENAI_API_KEY=sk-xxxxxxx

Create client

use openai_api_rs::v1::api::Client;
use std::env;
let client = Client::new(env::var("OPENAI_API_KEY").unwrap().to_string());

Create request

use openai_api_rs::v1::chat_completion::{self, ChatCompletionRequest};
let req = ChatCompletionRequest {
    model: chat_completion::GPT4.to_string(),
    messages: vec![chat_completion::ChatCompletionMessage {
        role: chat_completion::MessageRole::user,
        content: String::from("Hello OpenAI!"),
    }],
};

Send request

let result = client.completion(req).await?;
println!("{:?}", result.choices[0].text);

Example of chat completion

use openai_api_rs::v1::api::Client;
use openai_api_rs::v1::chat_completion::{self, ChatCompletionRequest};
use std::env;

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let client = Client::new(env::var("OPENAI_API_KEY").unwrap().to_string());
    let req = ChatCompletionRequest {
        model: chat_completion::GPT4.to_string(),
        messages: vec![chat_completion::ChatCompletionMessage {
            role: chat_completion::MessageRole::user,
            content: String::from("Hello OpenAI!"),
        }],
    };
    let result = client.chat_completion(req).await?;
    println!("{:?}", result.choices[0].message.content);
    Ok(())
}

Check out the full API documentation for examples of all the available functions.

Supported APIs

• completions
• Chat
• Edits
• Images
• Embeddings
• Audio
• Files
• Fine-tunes
• Moderations