ProcessBuddy AI

A comprehensive process management platform with AI-powered chat interface, configurable vector databases, and flexible task queues.

🚀 Features

Frontend (React + TypeScript)

• Modern UI: Clean, responsive interface built with React and Tailwind CSS
• Real-time Chat: AI-powered chat interface for process assistance
• Admin Dashboard: Comprehensive system configuration and monitoring
• Process Management: Create, manage, and interact with business processes
• Document Upload: Support for PDF, DOCX, and text files
• Vector Search: Semantic search across process documents

Backend (Python + FastAPI)

• Configurable Vector Database: Choose between Qdrant and Chroma DB
• Flexible Task Queue: Support for both Celery and RQ with Redis
• AI Integration: OpenAI and LangChain integration
• Document Processing: PDF, DOCX, and text file processing
• Background Tasks: Asynchronous document processing and embedding generation
• Health Monitoring: Comprehensive system health checks

🏗️ Architecture

┌─────────────────┐    ┌─────────────────┐    ┌─────────────────┐
│   React Frontend│    │   Python Backend│    │   Vector DB     │
│                 │    │                 │    │                 │
│ - Dashboard     │◄──►│ - FastAPI       │◄──►│ - Qdrant        │
│ - Chat Interface│    │ - Admin APIs    │    │ - Chroma DB     │
│ - Admin Panel   │    │ - Task Queue    │    │ - Embeddings    │
└─────────────────┘    └─────────────────┘    └─────────────────┘
          │                       │                       │
          ▼                       ▼                       ▼
┌─────────────────┐    ┌─────────────────┐    ┌─────────────────┐
│   Supabase      │    │   Redis         │    │   File Storage  │
│                 │    │                 │    │                 │
│ - Authentication│    │ - Task Queue    │    │ - Uploads       │
│ - User Data     │    │ - Caching       │    │ - Documents     │
│ - Metadata      │    │ - Sessions      │    │ - Temp Files    │
└─────────────────┘    └─────────────────┘    └─────────────────┘

🛠️ Tech Stack

Frontend

• React 18 with TypeScript
• Vite for build tooling
• Tailwind CSS for styling
• Lucide React for icons
• React Router for navigation

Backend

• FastAPI for API framework
• SQLAlchemy for ORM
• PostgreSQL for database
• Redis for caching and task queue
• Qdrant/Chroma DB for vector storage
• Celery/RQ for background tasks
• OpenAI for AI integration

📦 Installation

Prerequisites

• Node.js 18+ and npm
• Python 3.11+
• Docker and Docker Compose
• Redis
• PostgreSQL (optional, can use Supabase)

1. Clone the Repository

git clone <repository-url>
cd boltProcessGenie.ai

2. Frontend Setup

# Install dependencies
npm install

# Create environment file
cp .env.example .env.local

# Start development server
npm run dev

3. Backend Setup

# Navigate to backend directory
cd backend

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

# Install dependencies
pip install -r requirements.txt

# Create environment file
cp .env.example .env

# Start with Docker Compose (recommended)
docker-compose up -d

# Or start manually
uvicorn app.main:app --reload

4. Environment Configuration

Frontend (.env.local)

VITE_API_BASE_URL=http://localhost:8000
VITE_SUPABASE_URL=your-supabase-url
VITE_SUPABASE_ANON_KEY=your-supabase-anon-key

Backend (.env)

# App Settings
APP_NAME=ProcessBuddy AI
DEBUG=true

# Database
DATABASE_URL=postgresql://user:password@localhost/processbuddy

# Supabase
SUPABASE_URL=your-supabase-url
SUPABASE_ANON_KEY=your-supabase-anon-key
SUPABASE_SERVICE_KEY=your-supabase-service-key

# OpenAI
OPENAI_API_KEY=your-openai-api-key
OPENAI_MODEL=gpt-4

# Vector Database Configuration
VECTOR_DB_TYPE=qdrant  # or chroma
QDRANT_URL=http://localhost:6333
CHROMA_PERSIST_DIRECTORY=./chroma_db

# Task Queue Configuration
TASK_QUEUE_TYPE=celery  # or rq
REDIS_URL=redis://localhost:6379/0
CELERY_BROKER_URL=redis://localhost:6379/1
CELERY_RESULT_BACKEND=redis://localhost:6379/2

# Security
SECRET_KEY=your-secret-key-here

🚀 Quick Start

Using Docker Compose (Recommended)

1. Start all services:

cd backend
docker-compose up -d

2. Start frontend:

npm run dev

3. Access the application:

• Frontend: http://localhost:5173
• Backend API: http://localhost:8000
• API Documentation: http://localhost:8000/docs

Manual Setup

1. Start Redis:

docker run -d -p 6379:6379 redis:7-alpine

2. Start Qdrant:

docker run -d -p 6333:6333 qdrant/qdrant:latest

3. Start backend:

cd backend
uvicorn app.main:app --reload

4. Start frontend:

npm run dev

🔧 Configuration Options

Vector Database Selection

Qdrant (Recommended for production):

• Better performance for large datasets
• Advanced filtering and search capabilities
• Cloud-hosted options available
• Better scalability

Chroma DB (Good for development):

• Simpler setup
• Local storage
• Good for prototyping
• Built-in persistence

Task Queue Selection

Celery (Recommended for production):

• More features and flexibility
• Better monitoring tools (Flower)
• Scheduled tasks support
• Advanced task routing

RQ (Good for simple use cases):

• Simpler setup
• Easier to understand
• Good for basic background tasks
• Lightweight

📚 API Documentation

Once the backend is running, visit:

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

Key Endpoints

System Information

• GET / - Root endpoint with system info
• GET /health - Health check
• GET /api/v1/system-info - Detailed system information

Admin Configuration

• GET /api/v1/admin/system-config - Get current configuration
• POST /api/v1/admin/system-config - Update configuration
• GET /api/v1/admin/vector-db/status - Vector database status
• GET /api/v1/admin/task-queue/status - Task queue status
• GET /api/v1/admin/system-health - Overall system health

Process Management

• GET /api/v1/processes - List all processes
• POST /api/v1/processes - Create new process
• GET /api/v1/processes/{id} - Get process details
• PUT /api/v1/processes/{id} - Update process
• DELETE /api/v1/processes/{id} - Delete process

Chat Interface

• POST /api/v1/processes/{id}/chat - Send chat message
• GET /api/v1/processes/{id}/chat - Get chat history

Document Management

• POST /api/v1/documents/upload - Upload document
• GET /api/v1/processes/{id}/documents - Get process documents
• POST /api/v1/processes/{id}/search - Search documents

🧪 Testing

Frontend Tests

npm run test
npm run test:coverage

Backend Tests

cd backend
pytest tests/

📦 Deployment

Frontend Deployment

# Build for production
npm run build

# Deploy to Vercel, Netlify, or any static hosting

Backend Deployment

# Using Docker
cd backend
docker build -t processbuddy-backend .
docker run -d -p 8000:8000 processbuddy-backend

# Using Docker Compose
docker-compose -f docker-compose.prod.yml up -d

🔍 Monitoring

Celery Monitoring (Flower)

• URL: http://localhost:5555
• Monitor tasks, workers, and queues
• Real-time statistics

RQ Monitoring (RQ Dashboard)

• URL: http://localhost:9181
• Monitor RQ jobs and workers
• Job history and statistics

Health Checks

# System health
curl http://localhost:8000/health

# Vector DB status
curl http://localhost:8000/api/v1/admin/vector-db/status

# Task queue status
curl http://localhost:8000/api/v1/admin/task-queue/status

🤝 Contributing

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add some amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🆘 Support

For support, email support@processgenie.ai or join our Slack channel.

🔄 Changelog

v1.0.0

• Initial release
• React frontend with TypeScript
• Python FastAPI backend
• Configurable vector database (Qdrant/Chroma)
• Flexible task queue (Celery/RQ)
• AI-powered chat interface
• Admin configuration panel
• Document upload and processing
• Vector search capabilities