README.md

metadata

title: PatChat
emoji: 💬
colorFrom: blue
colorTo: indigo
sdk: docker
app_file: app.py
pinned: false
health_check: false

PatChat - AI Chat Application

PatChat is a simple and intuitive chat application that enables users to have conversations with AI models and save their chat history for future reference.

Features

• 🤖 AI Chat Interface: Chat with OpenAI models (GPT-3.5, GPT-4, GPT-4o, GPT-4o-mini, GPT-4o-mini-high, GPT-4o3)
• 🎯 System Prompt Customization: Choose from predefined prompts or create custom ones
• 💾 Conversation History: Save and manage all your conversations
• 📱 Responsive Design: Works on desktop and mobile devices
• 🚀 Easy Deployment: Deploy on Hugging Face Spaces with Docker
• 💰 Free Database: Uses free cloud database options
• 💡 Model Information: See descriptions and costs for each AI model

System Prompts

PatChat comes with several predefined system prompts:

• Default: General helpful assistant
• Creative: Imaginative and innovative responses
• Professional: Business-appropriate responses
• Educational: Learning-focused explanations
• Coding: Programming and technical assistance
• Writing: Writing and editing help
• Custom: Your own custom prompt

Quick Start

Prerequisites

• Python 3.11+
• OpenAI API key
• Free database (Supabase recommended)

Local Development

1. Clone the repository

   git clone <repository-url>
   cd PatChat
   

2. Install dependencies

   pip install -r requirements.txt
   

3. Set up environment variables

   cp env.example .env
   # Edit .env with your OpenAI API key and database URL
   

4. Run the application

   python app.py
   

5. Open your browser

   http://localhost:5000
   

Database Setup

Option 1: SQLite (Development)

# No setup required - SQLite file will be created automatically

Option 2: Supabase (Recommended for Production)

1. Create a free account at supabase.com
2. Create a new project
3. Get your database connection string
4. Update your .env file:

   DATABASE_URL=postgresql://postgres:[password]@[host]:5432/postgres
   

Deployment

Hugging Face Spaces

1. Fork this repository
2. Create a new Space on Hugging Face
3. Set environment variables in Space settings:
   • OPENAI_API_KEY: Your OpenAI API key
   • DATABASE_URL: Your database connection string
   • SECRET_KEY: A secure random string
4. Deploy - Hugging Face will automatically build and deploy your app

Docker Deployment

1. Build the image

   docker build -t patchat .
   

2. Run the container

   docker run -p 5000:5000 \
     -e OPENAI_API_KEY=your-key \
     -e DATABASE_URL=your-db-url \
     -e SECRET_KEY=your-secret \
     patchat
   

API Endpoints

Web Routes

• GET / - Main chat interface
• GET /history - Conversation history
• GET /conversation/:id - View specific conversation
• POST /send_message - Send message to AI
• POST /new_conversation - Start new conversation
• DELETE /conversation/:id - Delete conversation
• GET /system_prompts - Get available system prompts
• GET /health - Health check

Example API Usage

// Send a message
const response = await fetch('/send_message', {
    method: 'POST',
    headers: { 'Content-Type': 'application/json' },
    body: JSON.stringify({
        conversation_id: 1,
        content: 'Hello AI!',
        model_type: 'gpt-4',
        system_prompt: 'You are a helpful assistant.'
    })
});

// Create new conversation
const newConv = await fetch('/new_conversation', {
    method: 'POST',
    headers: { 'Content-Type': 'application/json' },
    body: JSON.stringify({
        model_type: 'gpt-3.5-turbo',
        system_prompt: 'You are a coding assistant.'
    })
});

Project Structure

PatChat/
├── app.py                 # Main Flask application
├── requirements.txt       # Python dependencies
├── Dockerfile            # Docker configuration
├── env.example           # Environment variables template
├── templates/            # HTML templates
│   ├── base.html         # Base template
│   ├── chat.html         # Chat interface
│   └── history.html      # Conversation history
└── README.md             # This file

Database Schema

Conversations Table

CREATE TABLE conversations (
    id SERIAL PRIMARY KEY,
    title VARCHAR(255) DEFAULT 'New Conversation',
    model_type VARCHAR(50) DEFAULT 'gpt-3.5-turbo',
    system_prompt TEXT DEFAULT 'You are a helpful AI assistant.',
    created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
    updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
);

Messages Table

CREATE TABLE messages (
    id SERIAL PRIMARY KEY,
    conversation_id INTEGER REFERENCES conversations(id) ON DELETE CASCADE,
    content TEXT NOT NULL,
    role VARCHAR(20) NOT NULL, -- 'user' or 'assistant'
    model_type VARCHAR(50),
    created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
);

Configuration

Environment Variables

Variable	Description	Default
OPENAI_API_KEY	Your OpenAI API key	Required
DATABASE_URL	Database connection string	sqlite:///patchat.db
SECRET_KEY	Flask secret key	dev-secret-key
PORT	Server port	5000

Supported AI Models

Model	Description	Max Tokens	Cost per 1K tokens
gpt-3.5-turbo	Fast and cost-effective for most tasks	4,096	$0.0015
gpt-4	More capable but slower than GPT-3.5	8,192	$0.03
gpt-4-turbo	Latest GPT-4 model with improved performance	128,000	$0.01
gpt-4o	Latest multimodal model with vision capabilities	128,000	$0.005
gpt-4o-mini	Faster and more cost-effective than GPT-4o	128,000	$0.00015
gpt-4o-mini-high	Higher quality responses than GPT-4o Mini	128,000	$0.0006
gpt-4o3	Latest and most capable model (if available)	128,000	$0.02

Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests if applicable
5. Submit a pull request

License

This project is open source and available under the MIT License.

Support

If you encounter any issues or have questions:

1. Check the Issues page
2. Create a new issue with detailed information
3. Include your environment details and error messages

Roadmap

• User authentication
• Conversation sharing
• Export conversations
• Voice input/output
• Multiple AI providers
• Advanced prompt templates
• Conversation search
• Mobile app

---

Made with ❤️ for the AI community