AIFlow 🚀

AIFlow is a full-stack AI workflow automation platform that enables users to create, manage, and execute AI-powered workflows with an intuitive visual interface.

✨ Features

• Visual Workflow Builder: Create complex AI workflows using a drag-and-drop interface powered by React Flow
• AI Chat Interface: Interactive chat functionality integrated with your workflows
• Knowledge Base Management: Upload and manage documents (PDF, DOCX) for AI context
• Workflow Execution: Execute workflows with custom queries and get real-time results
• Persistent Storage: PostgreSQL/Supabase backend for reliable data storage
• RESTful API: Well-documented FastAPI backend for seamless integration

🏗️ Tech Stack

Backend

• Framework: FastAPI
• Database: PostgreSQL with Supabase
• ORM: SQLAlchemy + SQLModel
• AI Integration: Google Gemini AI
• Document Processing: PyPDF, python-docx, pandas
• Async Support: asyncio, asyncpg

Frontend

• Framework: React 19 + TypeScript
• Build Tool: Vite
• UI Components: Radix UI
• Styling: Tailwind CSS
• State Management: Redux Toolkit
• Workflow Canvas: React Flow (@xyflow/react)
• Routing: React Router v7
• Markdown Rendering: React Markdown with LaTeX support

📋 Prerequisites

• Python 3.8+
• Node.js 18+
• PostgreSQL database (or Supabase account)
• Google Gemini API key

🚀 Getting Started

Backend Setup

1. Navigate to the backend directory:

cd backend

2. Create and activate a virtual environment:

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install dependencies:

pip install -r requirements.txt

4. Configure environment variables:

cp sample.env .env

Edit .env with your configuration:

DATABASE_URL=postgresql+asyncpg://user:password@host:port/database
SUPABASE_URL=your_supabase_url
SUPABASE_SERVICE_ROLE_KEY=your_supabase_key
SUPABASE_BUCKET_KB=your_bucket_name
EMBEDDING_SIZE=256
EMBEDDING_KEY_GEMINI=your_gemini_api_key
FRONTEND_URL=http://localhost:5173

5. Run database migrations:

alembic upgrade head

6. Start the backend server:

uvicorn app.main:app --reload --host 0.0.0.0 --port 8000

The API will be available at http://localhost:8000

Frontend Setup

1. Navigate to the frontend directory:

cd frontend

2. Install dependencies:

npm install

3. Configure environment variables:

cp sample.env .env

Edit .env with your configuration:

VITE_API_URL=http://localhost:8000

4. Start the development server:

npm run dev

The application will be available at http://localhost:5173

📖 Usage

Creating a Workflow

1. Navigate to the home page
2. Click "Create" to open the workflow builder
3. Drag and drop nodes to create your workflow:
   • Input Node: Entry point for your workflow
   • LLM Nodes: AI processing nodes
   • Output Node: Final result node
4. Connect nodes to define the flow
5. Configure each node with appropriate settings
6. Save your workflow

Running a Workflow

1. Go to the Chat interface
2. Select a workflow
3. Enter your query
4. View the AI-generated results

Uploading Knowledge Base Files

1. Use the file upload feature
2. Upload PDF or DOCX files
3. Files are processed and stored in the knowledge base
4. Reference these files in your workflows

🔌 API Documentation

Once the backend is running, visit:

• Swagger UI: http://localhost:8000/docs
• ReDoc: http://localhost:8000/redoc

Key Endpoints

• POST /workflow/ - Create a new workflow
• GET /workflow/{id} - Get workflow details
• POST /run/{workflow_id} - Execute a workflow
• POST /chat/create - Create a new chat
• POST /upload_kb_file - Upload knowledge base file

🏗️ Project Structure

AIFlow/
├── backend/
│   ├── alembic/              # Database migrations
│   ├── app/
│   │   ├── api/              # API routes
│   │   ├── models/           # SQLModel schemas
│   │   ├── services/         # Business logic
│   │   ├── repositories/     # Data access layer
│   │   ├── llm/              # LLM integration
│   │   ├── embeddings/       # Vector embeddings
│   │   ├── text_extraction/  # Document processing
│   │   └── main.py           # Application entry point
│   └── requirements.txt
└── frontend/
    ├── src/
    │   ├── apis/             # API client
    │   ├── components/       # React components
    │   ├── views/            # Page components
    │   ├── store/            # Redux store
    │   ├── types/            # TypeScript types
    │   └── main.tsx          # Application entry point
    └── package.json

🧪 Development

Backend

Run with auto-reload:

cd backend
uvicorn app.main:app --reload

Frontend

Run development server:

cd frontend
npm run dev

Build for production:

npm run build

Lint code:

npm run lint

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

📝 License

License information is to be determined.

🐛 Issues

If you encounter any issues or have suggestions, please file an issue on the GitHub repository.

👨‍💻 Author

Created by devshah23

---

Note: Make sure to keep your API keys and sensitive information secure. Never commit .env files to version control.