https://github.com/minskylab/auto-rust

auto-rust is an experimental project that aims to automatically generate Rust code with LLM (Large Language Models) during compilation, utilizing procedural macros.
https://github.com/minskylab/auto-rust

ai ai-functions autogpt gpt-3 gpt-4 llm openai-api

Last synced: 3 months ago
JSON representation

auto-rust is an experimental project that aims to automatically generate Rust code with LLM (Large Language Models) during compilation, utilizing procedural macros.

• Host: GitHub
• URL: https://github.com/minskylab/auto-rust
• Owner: minskylab
• License: apache-2.0
• Created: 2023-05-02T11:59:01.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2023-12-15T14:58:23.000Z (7 months ago)
• Last Synced: 2024-01-22T12:59:30.561Z (5 months ago)
• Topics: ai, ai-functions, autogpt, gpt-3, gpt-4, llm, openai-api
• Language: Rust
• Homepage: https://crates.io/crates/auto-rust
• Size: 391 KB
• Stars: 21
• Watchers: 1
• Forks: 1
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE-APACHE

Lists

• awesome-rust-llm - autorust - macros that generate AI driven rust code in compile time (Projects)

README

        
# Auto Rust

`auto-rust` is an experimental project that aims to automatically generate Rust code with LLM (Large Language Models) during compilation, utilizing procedural macros.



  



## ⚠️ Warning

Please note that Auto-Rust is currently under development and is not yet suitable for production use. While you are welcome to try it out and provide feedback, we caution that it may have an incomplete implementation and may not function as intended.

## Installation

```toml

[dependencies]

auto-rust = "0.1.0"

```

You need to create a .env file in the root of your project with the following content:

```bash

OPENAI_API_KEY=

```

## Example

```rust

use auto_rust::auto_implement;

#[auto_implement]

#[doc = "This function calculates if the input is a valid email address without use regex."]

fn is_email(input: String) -> bool {

    todo!()

}

fn main() {

    let result = is_email("bregyminsky.cc".to_string());

    println!("result: {}", result);

}

```

## Limitations

- LLMs are non-deterministic. If you don't get what you want from the first attempt - iterate, experiment with it.

- Actually, the context is limited by whatever code is in your function definition, no knowledge of project structure or other files.

- The extension doesn't add imports when new dependencies are introduced in the created code.

## Contributing

Contributions are welcome. Feel free to open an issue if you have any questions or want to suggest an improvement.