Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/modclub-app/rust-connect-py-ai-to-ic
A streamlined open-source tool for deploying Python AI models on the Internet Computer (IC). Enables easy uploading and inference.
https://github.com/modclub-app/rust-connect-py-ai-to-ic
Last synced: about 2 months ago
JSON representation
A streamlined open-source tool for deploying Python AI models on the Internet Computer (IC). Enables easy uploading and inference.
- Host: GitHub
- URL: https://github.com/modclub-app/rust-connect-py-ai-to-ic
- Owner: modclub-app
- License: other
- Created: 2024-01-21T05:34:13.000Z (12 months ago)
- Default Branch: main
- Last Pushed: 2024-07-26T19:28:49.000Z (6 months ago)
- Last Synced: 2024-07-26T21:14:43.743Z (6 months ago)
- Language: Rust
- Size: 247 KB
- Stars: 5
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-internet-computer - Rust-Connect-Py-AI-to-IC - A streamlined open-source tool for deploying Python AI models on ICP. (Decentralized AI / Solana)
README
# rust-connect-py-ai-to-ic
Seamlessly Bridge Python AI Models with the Internet Computer.
## Overview
"Python (design and train), Rust (upload), IC (run)" - this succinct mantra captures the essence of `rust-connect-py-ai-to-ic`. Our toolkit is an open-source solution designed to enable AI researchers and developers to effortlessly upload and deploy Python-based machine learning models for inference on the Internet Computer (IC) platform.
Focused on ease of use and versatility, `rust-connect-py-ai-to-ic` aims to streamline the integration of advanced AI capabilities into the decentralized environment of the IC. This project represents a pivotal step towards harnessing the power of the IC for AI, with potential future expansions into model training and user-friendly drag-and-drop functionalities.
## Features
- **Effortless Upload**: Simplify the process of uploading Python-based AI models to the IC using Rust.
- **Inference on IC**: Run your machine learning models on a decentralized platform, leveraging the unique capabilities of the Internet Computer.
- **Future Expansion**: Potential for extending the toolkit to include model training and easy-to-use drag-and-drop features.
## Getting Started
This section guides you through the initial setup of the necessary tools and environments for this project. We are using Rust with WebAssembly, Python with PyTorch, and the Dfinity platform.
### Rust Setup
First, ensure you have Rust installed. We will then set the default toolchain to stable and add the WebAssembly target.
1. Install Rust and Cargo (if not already installed): Visit [Rust's installation page](https://www.rust-lang.org/tools/install).
2. Set the default toolchain to stable:
```bash
rustup default stable
```
3. Add the WebAssembly target:
```bash
rustup target add wasm32-unknown-unknown
```
4. Add Cargo's bin directory to your PATH:
```bash
export PATH="$PATH:~/.cargo/bin"
```
### Python and PyTorch Setup
Ensure you have Python installed and then set up PyTorch.
1. Install Python (if not already installed): Visit [Python's download page](https://www.python.org/downloads/).
2. Install PyTorch using pip:
```bash
pip install torch
```
### Dfinity's DFX Setup
We will be using Dfinity's `dfx` for our development environment.
1. Install Dfinity's `dfx`: Follow the instructions on [Dfinity's SDK documentation](https://sdk.dfinity.org/docs/quickstart/quickstart.html).
## Contributing
We welcome contributions! Please read our contributing guidelines to get started.
## License
Apache 2.0/MIT
All original work licensed under either of
Apache License, Version 2.0 (LICENSE-APACHE or http://www.apache.org/licenses/LICENSE-2.0)
MIT license (LICENSE-MIT or http://opensource.org/licenses/MIT) at your option.