async-openai

Async Rust library for OpenAI

Overview

async-openai is an unofficial Rust library for OpenAI REST API.

• It's based on OpenAI OpenAPI spec
• Current features:
  • [x] Audio
  • [x] Chat (including SSE streaming)
  • [x] Completions (including SSE streaming)
  • [x] Edits
  • [x] Embeddings
  • [x] Files
  • [x] Fine-Tuning (including SSE streaming)
  • [x] Images
  • [ ] Microsoft Azure Endpoints / AD Authentication (see issue)
  • [x] Models
  • [x] Moderations
• Non-streaming requests are retried with exponential backoff when rate limited by the API server.
• Ergonomic Rust library with builder pattern for all request objects.

Being a young project there could be rough edges.

Usage

The library reads API key from the environment variable OPENAI_API_KEY.

```bash

On macOS/Linux

export OPENAIAPIKEY='sk-...' ```

```powershell

On Windows Powershell

$Env:OPENAIAPIKEY='sk-...' ```

• Visit examples directory on how to use async-openai.
• Visit docs.rs/async-openai for docs.

Image Generation Example

```rust use async_openai::{ types::{CreateImageRequestArgs, ImageSize, ResponseFormat}, Client, }; use std::error::Error;

[tokio::main]

async fn main() -> Result<(), Box> { // create client, reads OPENAIAPIKEY environment variable for API key. let client = Client::new();

let request = CreateImageRequestArgs::default()
    .prompt("cats on sofa and carpet in living room")
    .n(2)
    .response_format(ResponseFormat::Url)
    .size(ImageSize::S256x256)
    .user("async-openai")
    .build()?;

let response = client.images().create(request).await?;

// Download and save images to ./data directory.
// Each url is downloaded and saved in dedicated Tokio task.
// Directory is created if it doesn't exist.
let paths = response.save("./data").await?;

paths
    .iter()
    .for_each(|path| println!("Image file path: {}", path.display()));

Ok(())

} ```

<sub>Scaled up for README, actual size 256x256</sub>

Contributing

Thank you for your time to contribute and improve the project, I'd be happy to have you!

A good starting point would be an open issue.

License

This project is licensed under MIT license.