openai-oxide 0.2.0

Idiomatic Rust client for the OpenAI API — 1:1 parity with the official Python SDK
Documentation

openai-oxide

Idiomatic Rust client for the OpenAI API — 1:1 parity with the official Python SDK.

Features

  • Async-first (tokio + reqwest)
  • Strongly typed requests and responses (serde)
  • SSE streaming support
  • Automatic retries with exponential backoff
  • Builder pattern for requests
  • Same resource structure as Python SDK: client.chat().completions().create()

Quick Start

Add to Cargo.toml:

[dependencies]
openai-oxide = "0.1"
tokio = { version = "1", features = ["full"] }

use openai_oxide::{OpenAI, types::chat::*};

#[tokio::main]
async fn main() -> Result<(), openai_oxide::OpenAIError> {
    let client = OpenAI::from_env()?;

    let request = ChatCompletionRequest::new(
        "gpt-4o-mini",
        vec![
            ChatCompletionMessageParam::System {
                content: "You are a helpful assistant.".into(),
                name: None,
            },
            ChatCompletionMessageParam::User {
                content: UserContent::Text("Hello!".into()),
                name: None,
            },
        ],
    );

    let response = client.chat().completions().create(request).await?;
    println!("{}", response.choices[0].message.content.as_deref().unwrap_or(""));
    Ok(())
}

Streaming

use futures_util::StreamExt;
use openai_oxide::{OpenAI, types::chat::*};

#[tokio::main]
async fn main() -> Result<(), openai_oxide::OpenAIError> {
    let client = OpenAI::from_env()?;

    let request = ChatCompletionRequest::new(
        "gpt-4o-mini",
        vec![ChatCompletionMessageParam::User {
            content: UserContent::Text("Tell me a joke".into()),
            name: None,
        }],
    );

    let mut stream = client.chat().completions().create_stream(request).await?;
    while let Some(chunk) = stream.next().await {
        let chunk = chunk?;
        if let Some(delta) = chunk.choices.first().and_then(|c| c.delta.content.as_deref()) {
            print!("{delta}");
        }
    }
    Ok(())
}

Configuration

use openai_oxide::{OpenAI, ClientConfig};

// From environment variable OPENAI_API_KEY
let client = OpenAI::from_env()?;

// Explicit API key
let client = OpenAI::new("sk-...");

// Full configuration
let config = ClientConfig::new("sk-...")
    .base_url("https://api.openai.com/v1")
    .timeout_secs(30)
    .max_retries(3);
let client = OpenAI::with_config(config);

Implemented APIs

API Method Status
Chat Completions client.chat().completions().create() Done
Chat Completions (streaming) client.chat().completions().create_stream() Done
Responses client.responses().create() Done
Embeddings client.embeddings().create() Done
Models client.models().list() / retrieve() / delete() Done
Images client.images().generate() / edit() / create_variation() Done
Audio Transcription client.audio().transcriptions().create() Done
Audio Translation client.audio().translations().create() Done
Audio Speech (TTS) client.audio().speech().create() Done
Files client.files().create() / list() / retrieve() / delete() / content() Done
Fine-tuning client.fine_tuning().jobs().create() / list() / cancel() / list_events() Done
Moderations client.moderations().create() Done
Batches client.batches().create() / list() / retrieve() / cancel() Done
Uploads client.uploads().create() / cancel() / complete() Done
Assistants (beta) client.beta().assistants().create() / list() / retrieve() / delete() Done
Threads (beta) client.beta().threads().create() / retrieve() / delete() / messages() Done
Runs (beta) client.beta().runs(thread_id).create() / retrieve() / cancel() Done
Vector Stores (beta) client.beta().vector_stores().create() / list() / retrieve() / delete() Done

Development

cargo test                          # all tests
cargo test --features live-tests    # tests hitting real API (needs OPENAI_API_KEY)
cargo clippy -- -D warnings         # lint
cargo fmt -- --check                # format check

License

MIT