AISDK

An open-source Rust library for building AI-powered applications, inspired by the Vercel AI SDK. It provides a type-safe interface for interacting with Large Language Models (LLMs).

⚠️ Early Stage Warning: This project is in very early development and not ready for production use. APIs may change significantly, and features are limited. Use at your own risk.

Key Features

• OpenAI Provider Support: Initial support for OpenAI models with text generation and streaming.
• Type-Safe API: Built with Rust's type system for reliability.
• Asynchronous: Uses Tokio for async operations.
• Prompt Templating: Filesystem-based prompts using Tera templates (coming soon).

Installation

Add aisdk to your Cargo.toml:

[dependencies]
aisdk = "0.1.0"

Enable the OpenAI feature:

aisdk = { version = "0.1.0", features = ["openai"] }

Usage

Basic Text Generation

use ai_sdk_rs::{
    core::{GenerateTextCallOptions, generate_text},
    providers::openai::{OpenAI, OpenAIProviderSettings},
};

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let settings = OpenAIProviderSettings::builder()
        .api_key("your-api-key".to_string())
        .model_name("gpt-4o".to_string())
        .build()?;

    let openai = OpenAI::new(settings);

    let options = GenerateTextCallOptions::builder()
        .prompt("Say hello.")
        .build()?;

    let result = generate_text(openai, options).await?;
    println!("{}", result.text);
    Ok(())
}

Streaming Text Generation

use ai_sdk_rs::{
    core::{GenerateTextCallOptions, generate_stream},
    providers::openai::{OpenAI, OpenAIProviderSettings},
};
use futures::StreamExt;

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let settings = OpenAIProviderSettings::builder()
        .api_key("your-api-key".to_string())
        .model_name("gpt-4o".to_string())
        .build()?;

    let openai = OpenAI::new(settings);

    let options = GenerateTextCallOptions::builder()
        .prompt("Count from 1 to 10.")
        .build()?;

    let mut stream = generate_stream(openai, options).await?;
    while let Some(chunk) = stream.stream.next().await {
        print!("{}", chunk.text);
    }
    Ok(())
}

Technologies Used

• Rust: Core language.
• Tokio: Async runtime.
• Tera: Template engine for prompts.
• async-openai: OpenAI API client.

Contributing

We welcome contributions! Please see CONTRIBUTING.md for guidelines.

License

Licensed under the MIT License. See LICENSE for details.