Panathos AI

AI-powered search and research assistant built with Next.js, Supabase, and Gemini 2.5.

Features

• 🔍 Multi-Stage Search: 4 search modes from instant answers to deep research
• 🤖 AI-Powered: Gemini 2.5 Flash via LiteLLM for intelligent responses
• 📄 File Analysis: Upload and analyze PDFs, documents, and more
• 🔐 Secure Auth: Email, Google, and GitHub authentication via Supabase
• 📊 Usage Tracking: Monitor your searches and API usage
• 🎨 Beautiful UI: Modern design with dark/light mode support

Tech Stack

• Frontend: Next.js 14, React, TypeScript, Tailwind CSS
• Backend: Next.js API Routes, LiteLLM (Python FastAPI)
• Database: Supabase (PostgreSQL with pgvector)
• Auth: Supabase Auth
• Search: Tavily API
• AI: Google Gemini 2.5 Flash

Getting Started

Prerequisites

• Node.js 18+
• Python 3.11+
• Supabase account
• Tavily API key
• Google AI API key

Installation

1. Clone the repository:

   git clone https://github.com/yourusername/panathos-ai.git
   cd panathos-ai

2. Install dependencies:

   npm install

3. Set up environment variables:

   cp .env.example .env.local

   Fill in your API keys and configuration.

4. Start the development server:

   npm run dev

5. (Optional) Start the LiteLLM backend:

   cd backend
   pip install -r requirements.txt
   uvicorn main:app --reload --port 8000

Environment Variables

See .env.example for required environment variables.

Project Structure

├── app/                    # Next.js App Router
│   ├── api/               # API routes
│   ├── auth/              # Auth pages
│   ├── chat/              # Chat interface
│   ├── dashboard/         # Usage dashboard
│   ├── files/             # File management
│   ├── research/          # Research projects
│   └── settings/          # User settings
├── components/            # React components
│   ├── chat/              # Chat-specific components
│   ├── layout/            # Layout components
│   ├── providers/         # Context providers
│   └── ui/                # shadcn/ui components
├── lib/                   # Utility libraries
│   ├── context/           # Context management
│   ├── prompts/           # System prompts
│   ├── search/            # Tavily integration
│   ├── supabase/          # Supabase client
│   └── usage/             # Usage tracking
├── backend/               # LiteLLM Python service
└── docs/                  # Documentation

Search Modes

Mode	Time	Stages	Use Case
Instant	~2s	1	Quick facts and definitions
Fast	~10s	2-3	Simple research questions
Medium	~30s	4-6	Thorough analysis
Slow	~60s	6-8	Comprehensive research

Deployment

Vercel (Frontend)

1. Push to GitHub
2. Import project to Vercel
3. Add environment variables
4. Deploy

Backend (Railway/Fly.io)

1. Deploy the backend/ directory
2. Set environment variables
3. Update LITELLM_API_URL in Vercel

Contributing

Contributions are welcome! Please read our contributing guidelines first.

License

MIT License - see LICENSE for details.