Crate libopenai

libopenai - Rust client to interact with OpenAI’s API

Rust client for OpenAI’s API, written with tokio and reqwest

How to use

To add libopenai to your project, you just need to run the following command on your project’s main foler:

cargo add libopenai

Example

use libopenai::prelude::*;

#[tokio::main]
async fn main() -> Result<()> {
    // OPTIONAL: Load variables in a `.env` file into the enviroment
    dotenv::dotenv().unwrap();

    let client = Client::new(
        None, // Gets api key from `OPENAI_API_KEY` enviroment variable
        None, // No organization specified
    )?;

    // Send basic completion request
    let basic = Completion::new(
        "text-davinci-003",
        "Whats the best way to calculate a factorial?",
        &client,
    )
    .await?;

    // Print the result
    println!("{:#?}", basic);
    return Ok(());
}

Features

• Text generation
  • Regular completion
  • Chat completion
  • Edit
• Embeddings
• Moderations
• Files and fine-tuning
• Image generation with automatic conversion to desired formats
• Audio-to-text conversions
• Support for streaming

Cargo features

Currently, the only feature available is tracing, which enables some minor logging

Modules

audio

Learn how to turn audio into text.

chat

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

common

Structures and methods commonly used throughout the library

completion

Given a prompt, the model will return one or more predicted completions, and can also return the probabilities of alternative tokens at each position.

edit

Given a prompt and an instruction, the model will return an edited version of the prompt.

embeddings

Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms.

error

Library’s error types

file

Files are used to upload documents that can be used with features like fine-tuning.

finetune

Manage fine-tuning jobs to tailor a model to your specific training data.

image

Given a prompt and/or an input image, the model will generate a new image.

model

List and describe the various models available in the API.

moderations

Given a input text, outputs if the model classifies it as violating OpenAI’s content policy.

prelude

Structs

Client

A client that’s used to connect to the OpenAI API

OpenAiStream

A Stream of server-sent events, sent by OpenAI