HTV

Chatbot Feature

A minimal, production-ready chatbot powered by Google's Gemini API with real-time streaming support.

Quick Start

1. Backend Setup:

   cd backend
   
   # Create .env file with your Gemini API key
   echo "GEMINI_API_KEY=your_key_here" > .env
   echo "GEMINI_MODEL=gemini-1.5-pro" >> .env
   
   # Option A: Local Python
   pip install -r requirements.txt
   uvicorn main:app --reload --port 8000
   
   # Option B: Docker
   docker-compose up --build

2. Frontend Setup:

   cd frontend
   npm install
   npm run dev

3. Open http://localhost:3000 and start chatting!

Documentation

See CHATBOT_SETUP.md for detailed documentation including:

• Architecture overview
• API reference
• Configuration options
• How to swap LLM providers
• Production deployment guide
• Troubleshooting

Features

✅ Real-time streaming responses (SSE)
✅ Clean, accessible UI with Tailwind CSS
✅ Generic LLM interface (easy to swap providers)
✅ Error handling and loading states
✅ Keyboard shortcuts (Enter to send, Shift+Enter for newline)
✅ Auto-scroll and focus management
✅ Request telemetry and logging

---

HTV Project

Minimal boilerplate for a Next.js frontend and FastAPI backend.

Frontend (Next.js)

Located in frontend/ directory.

Features

• Next.js with TypeScript
• Tailwind CSS
• App Router (no src directory)
• No ESLint

Setup

cd frontend
npm install
npm run dev

The frontend will run on http://localhost:3000

Backend (FastAPI)

Located in backend/ directory.

Features

• FastAPI with CORS enabled
• Domain-based structure in app/domains/
• Example domain included
• Docker support with hot reload

Setup (Local)

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

Setup (Docker)

cd backend
docker build -t backend .
docker run -p 8000:8000 -v $(pwd):/app backend

The backend will run on http://localhost:8000

• API docs: http://localhost:8000/docs
• Health check: http://localhost:8000/health

Features

Trellis 3D Generator

A proof of concept that demonstrates image-to-3D model generation:

• Upload an image via the web interface
• Generate 3D models using the Trellis API
• View and interact with the generated GLB model in real-time using Three.js
• Download the generated 3D model

Access at: http://localhost:3000/trellis

Project Structure

HTV/
├── frontend/              # Next.js application
│   ├── app/              # Next.js App Router
│   │   ├── trellis/      # Trellis 3D generator POC
│   │   └── ...
│   ├── lib/              # Utilities
│   ├── components/       # React components
│   └── public/           # Static assets
└── backend/              # FastAPI application
    ├── app/
    │   ├── endpoints/    # API endpoints
    │   │   ├── redis/    # Redis operations
    │   │   ├── trellis/  # Trellis 3D generation
    │   │   └── ...
    │   ├── integrations/ # Third-party API integrations
    │   │   └── trellis.py
    │   └── core/         # Core services (config, redis)
    ├── main.py           # FastAPI entry point
    ├── Dockerfile        # Docker configuration
    └── requirements.txt