AutoML Studio is a powerful No-Code Machine Learning Platform that empowers users to build, train, and evaluate machine learning models using an intuitive drag-and-drop interface. Whether you are a data scientist or a beginner, AutoML Studio streamlines the complex process of ML workflows into simple, visual steps.
- Visual Workflow Builder: Create complex ML pipelines by dragging and dropping nodes (powered by
@xyflow/react). - No-Code Interface: Perform data preprocessing, cleaning, and model training without writing a single line of code.
- Multi-Backend Architecture: Robust microservices architecture for scalability and performance.
- Real-time Analysis: Interactive data visualization and analysis tools.
- Secure Authentication: Integrated user management and authentication system.
The project follows a microservices architecture to ensure modularity and scalability.
graph TD
Client["Frontend (Next.js)"]
Node["Node Backend (Express)"]
Ops["Operations Backend (FastAPI)"]
DB[("MongoDB")]
Redis[("Redis")]
Client -->|API REST/WebSocket| Node
Client -->|Direct Upload/Ops| Ops
Node -->|Auth & Metadata| DB
Node -->|Data Mgmt| Ops
Ops -->|Data Processing| DB
subgraph Services
Node
Ops
end
-
Frontend (
/frontend):- Tech Stack: Next.js 16, React 19, Redux Toolkit, Tailwind CSS.
- Role: The user interface for designing workflows and managing datasets. Features the drag-and-drop canvas.
-
Primary Backend (
/primary-backend):- Tech Stack: Express.js, TypeScript, Mongoose.
- Role: Acts as the primary API gateway. Handles user authentication, project management, and orchestration between services.
-
Operations Backend (
/operations-backend):- Tech Stack: FastAPI.
- Role: Dedicated service for high-throughput data operations, dataset processing, and file management.
The frontend is built with Next.js and runs on port 5173 by default.
cd frontend
npm install
npm run devThe primary backend handles API requests, authentication, and workflow manaagement. It runs on port 3000.
cd primary-backend
npm install
npm run devThe operations backend is a FastAPI service for data-intensive tasks.
cd operations-backend
python -m venv venv
.\venv\Scripts\activate
or
source venv/bin/activate
pip install -r requirements.txt
python run.pyHere is a visual representation of a typical machine learning workflow you can build in AutoML Studio:
graph LR
input((Dataset))
split[Data Splitter]
train[Model Training]
eval[Evaluation]
deploy[Deployment]
input --> split
split -->|Training Set| train
split -->|Test Set| eval
train -->|Model| eval
eval -->|Metrics Verification| deploy
style input fill:#f9f,stroke:#333
style train fill:#bbf,stroke:#333
style deploy fill:#dfd,stroke:#333
- Frontend: Built with Next.js App Router. Workflows are managed using React Flow (xyflow).
- Backend Communication: Services communicate via REST APIs. Long-running ML tasks are offloaded to background workers via Redis queues.
We welcome contributions to AutoML Studio! Whether you're fixing a bug, adding a new feature, or improving documentation, we appreciate your help.
- Fork the Repository: Click the "Fork" button at the top right of this page to create your own copy of the repository.
- Clone the Repository:
git clone https://github.com/your-username/AutoML-Studio.git cd AutoML-Studio - Create a Branch:
git checkout -b feature/your-feature-name
- Make Changes: Implement your changes and ensure everything is working as expected.
- Commit Changes:
git add . git commit -m "feat: Add your feature description"
- Push to Your Fork:
git push origin feature/your-feature-name
- Create a Pull Request: Go to the original repository on GitHub and open a Pull Request from your forked branch.
- Please follow the existing code style.
- Ensure that you have tested your changes locally.
- Provide a clear description of your changes in the Pull Request.
Made with ❤️ by Udaykumar Dhokia using Next.js, TypeScript & Python.