OpenAI Interface

A low-level Rust interface for interacting with OpenAI's API. Both streaming and non-streaming APIs are supported.

Currently, only chat completion and file management are supported. Image generation and other features are still in development.

Repository:

GitCode: GitCode Repo
GitHub: GitHub Repo

You are welcome to contribute to this project through any of the links above.

Features

• Chat Completions: Full support for OpenAI's chat completion and completion API, including both streaming and non-streaming responses.
• File: Full support for OpenAI's file API.
• Streaming and Non-streaming: Support for both streaming and non-streaming responses.
• Strong Typing: Complete type definitions for all API requests and responses, utilizing Rust's powerful type system.
• Error Handling: Comprehensive error handling with detailed error types defined in the [errors] module.
• Async/Await: Built with async/await support.
• Musl Support: Designed to work with musl libc out-of-the-box.
• Multiple Provider Support: Expected to work with OpenAI, DeepSeek, Qwen, and other compatible API providers.

Installation

Add this to your Cargo.toml:

[dependencies]
openai-interface = "0.5.0-alpha.1"

Usage

Chat Completion

This crate provides methods for both streaming and non-streaming chat completions. The following examples demonstrate how to use these features.

Non-streaming Chat Completion

use std::sync::LazyLock;
use openai_interface::chat::create::request::{Message, RequestBody};
use openai_interface::chat::create::response::no_streaming::ChatCompletion;
use std::str::FromStr;

// You need to provide your own DeepSeek API key at /keys/deepseek_domestic_key
const DEEPSEEK_API_KEY: LazyLock<&str> =
    LazyLock::new(|| include_str!("../keys/deepseek_domestic_key").trim());
const DEEPSEEK_CHAT_URL: &'static str = "https://api.deepseek.com/chat/completions";
const DEEPSEEK_MODEL: &'static str = "deepseek-chat";

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let request = RequestBody {
        messages: vec![
            Message::System {
                content: "You are a helpful assistant.".to_string(),
                name: None,
            },
            Message::User {
                content: "Hello, how are you?".to_string(),
                name: None,
            },
        ],
        model: DEEPSEEK_MODEL.to_string(),
        stream: false,
        ..Default::default()
    };

    // Send the request
    let response: String = request
        .get_response(DEEPSEEK_CHAT_URL, &*DEEPSEEK_API_KEY)
        .await?;
    let chat_completion = ChatCompletion::from_str(&response).unwrap();
    let text = chat_completion.choices[0]
        .message
        .content
        .as_deref()
        .unwrap();
    println!("{:?}", text);
    Ok(())
}

Streaming Chat Completion

This example demonstrates how to handle streaming responses from the API.

use openai_interface::chat::create::request::{Message, RequestBody};
use openai_interface::chat::create::response::streaming::{CompletionContent, ChatCompletionChunk};
use futures_util::StreamExt;

use std::str::FromStr;
use std::sync::LazyLock;

// You need to provide your own DeepSeek API key at /keys/deepseek_domestic_key
const DEEPSEEK_API_KEY: LazyLock<&str> =
    LazyLock::new(|| include_str!("../keys/deepseek_domestic_key").trim());
const DEEPSEEK_CHAT_URL: &'static str = "https://api.deepseek.com/chat/completions";
const DEEPSEEK_MODEL: &'static str = "deepseek-chat";

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let request = RequestBody {
        messages: vec![
            Message::System {
                content: "You are a helpful assistant.".to_string(),
                name: None,
            },
            Message::User {
                content: "Who are you?".to_string(),
                name: None,
            },
        ],
        model: DEEPSEEK_MODEL.to_string(),
        stream: true,
        ..Default::default()
    };

    // Send the request
    let mut response_stream = request
        .get_stream_response(DEEPSEEK_CHAT_URL, *DEEPSEEK_API_KEY)
        .await?;

    let mut message = String::new();

    while let Some(chunk_result) = response_stream.next().await {
        let chunk_string = chunk_result?;
        if &chunk_string == "[DONE]" {
            // SSE stream ends.
            break;
        }
        let chunk = ChatCompletionChunk::from_str(&chunk_string).unwrap();
        let content: &String = match chunk.choices[0].delta.content.as_ref().unwrap() {
            CompletionContent::Content(s) => s,
            // `ReasoningContent` is a field from DeepSeek.
            CompletionContent::ReasoningContent(s) => s,
        };
        println!("lib::test_streaming message: {}", content);
        message.push_str(content);
    }

    println!("lib::test_streaming message: {}", message);
    Ok(())
}

Custom Request Parameters

You can customize request parameters as needed. If you require provider-specific fields, you can add them to extra_body or extra_body_map.

Modules

• [chat]: Contains all chat completion related structs, enums, and methods.
• [completion]: Contains all completion related structs, enums, and methods. Note that this API is getting deprecated in favour of chat and is only available for out-dated LLM models.
• [files]: Providing the capacity to upload and manage files.
• [rest]: Providing all REST related traits and methods.
• [errors]: Defines error types used throughout the crate.

Error Handling

All errors are converted into crate::error::OapiError

Musl Build

This crate is designed to work with musl libc, making it suitable for lightweight deployments in containerized environments. Longer compile times may be required as OpenSSL needs to be built from source.

To build for musl:

rustup target add x86_64-unknown-linux-musl
cargo build --target x86_64-unknown-linux-musl

Supported Providers

This crate aims to support standard OpenAI-compatible API endpoints. Unfortunately, OpenAI aggressively restricts the access from the People's Republic of China. As a result, the implementation has been tested primarily with DeepSeek and Qwen. Please open an issue if you find any mistakes or inaccuracies in the implementation.

Contributing

Contributions are welcome! Please feel free to submit pull requests or open issues for bugs and feature requests.

License

This project is licensed under the AGPL-3.0 License - see the LICENSE file for details.