A Python Flask-based internal wiki system with AI assistant capabilities, powered by Supabase.

• Wiki Management: Create, edit, and organize wiki pages in a hierarchy
• AI Assistant: Ask questions and get intelligent answers based on your wiki content
• Vector Search: Uses OpenAI embeddings with Supabase pgvector for semantic search
• Cloud Database: Powered by Supabase PostgreSQL with automatic scaling
• Responsive Design: Works on desktop and mobile devices
• Simple Setup: No local database installation required

• Python 3.8+
• Supabase account (free tier available)
• OpenAI API key

1. Clone and install dependencies:

   git clone <your-repo>
   cd atlasai-flask-supabase
   pip install -r requirements.txt
   

2. Create Supabase project:

   • Go to supabase.com
   • Create a new project
   • Note your project URL and API keys

3. Configure environment:

   cp .env.example .env
   # Edit .env with your Supabase and OpenAI credentials
   

4. Run the application:

   python app.py
   

5. Access AtlasAI: Open http://localhost:5000 in your browser

Create a .env file with:

# Supabase Configuration
SUPABASE_URL=https://your-project-id.supabase.co
SUPABASE_ANON_KEY=your-anon-key-here
SUPABASE_SERVICE_ROLE_KEY=your-service-role-key-here

# OpenAI Configuration
OPENAI_API_KEY=your-openai-api-key-here

# Flask Configuration
SECRET_KEY=your-secret-key-here

1. Go to your Supabase project dashboard
2. Navigate to the SQL Editor
3. Run the SQL script provided by python setup_supabase.py
4. This creates all necessary tables and the vector search function

• Create Pages: Click "Create Page" to add new wiki content
• Edit Pages: Click "Edit" on any page to modify content
• AI Assistant: Use the chat panel on the right to ask questions
• Search: Use the search box in the sidebar to find pages
• Organize: Set parent pages to create a hierarchy

• Hierarchical page organization
• Markdown content support
• Real-time search
• Page creation/editing/deletion
• Automatic slug generation

• Vector similarity search
• OpenAI GPT-4 responses
• Source citations
• Feedback collection
• Chat history logging

• Backend: Flask + Supabase Python client
• Database: Supabase PostgreSQL with pgvector
• AI: OpenAI embeddings and chat completion
• Frontend: Bootstrap + Vanilla JavaScript
• Deployment: Vercel/Heroku/Railway ready