AI Chat Assistant

Production-grade multimodal chat with Next.js 15, TypeScript, and Google Vertex AI
Live: chat.daza.ar • Repo: github.com/roofsonfire/chat

---

🚀 Quick Start

5-minute setup: docs/guides/QUICKSTART.md

git clone https://github.com/roofsonfire/chat.git
cd chat
npm install
cp .env.example .env.local
# Edit .env.local with your credentials
npm run dev

Full setup guide: docs/DEVELOPMENT.md

---

✨ Features

Core Capabilities

• 🤖 Multimodal AI Chat - Text + image inputs with Gemini 2.5
• ⚡ Real-time Streaming - Instant response streaming
• 🎨 Image Generation - AI-powered image creation
• 🔐 Secure Auth - Google OAuth + invite-only access
• 🛡️ Production-Ready - Rate limiting, security headers, error handling

Tech Stack

• Frontend: Next.js 15 (App Router), React 19, TypeScript 5, Tailwind CSS 4
• Backend: Next.js API Routes, Google Vertex AI, NextAuth.js
• Infrastructure: Google Cloud Run, Cloud Secret Manager
• Testing: Vitest, React Testing Library, Storybook

---

📂 Project Structure

chat/
├── src/
│   ├── app/              # Next.js App Router (pages, API routes)
│   ├── components/       # React components (ui/, chat/, auth/)
│   ├── lib/             # Core utilities (services/, hooks/, types/)
│   └── middleware.ts    # Auth, rate limiting, security
├── tests/               # Unit, integration, manual tests
├── docs/                # Comprehensive documentation
└── .github/
    ├── copilot-instructions.md   # AI pairing context
    ├── copilot-quick-reference.md # Fast reference card
    └── patterns/                  # Code pattern library

Full navigation: docs/PROJECT-NAVIGATION.md

---

📚 Documentation

Getting Started

• Quickstart Guide - 5-minute setup ⚡
• Development Guide - Local setup and workflows
• Project Navigation - Find what you need fast

Deployment

• Cloud Run Deployment - Production setup
• CI/CD Pipeline - GitHub Actions automation
• OAuth Setup - Google OAuth configuration

Architecture & Code

• API Reference - Endpoints and contracts
• Pattern Library - Reusable code patterns
• Model Selection - Dynamic AI models

Operations

• Project Status - Current state and roadmap
• Security Policy - Vulnerability reporting
• Contributing Guide - How to contribute

Complete index: docs/README.md

---

🧪 Testing

npm run test              # Run all tests
npm run test:coverage     # With coverage report
npm run test:ui           # Interactive test UI
npm run lint              # ESLint check
npm run format            # Prettier format

Test structure: Unit tests • Integration tests • Storybook tests • Manual smoke tests
Coverage target: >80% on critical paths

---

🔐 Security

• Authentication: NextAuth.js with Google OAuth (invite-only)
• Rate Limiting: 5 requests per 10 seconds per IP
• Input Validation: Zod schemas on all endpoints
• Security Headers: CSP, HSTS, X-Frame-Options, etc.
• Secrets Management: Google Cloud Secret Manager
• Password Hashing: bcrypt with 10 rounds

Security policy: docs/SECURITY.md

---

🤝 Contributing

We welcome contributions! Here's how to get started:

1. Fork the repository
2. Create a feature branch: git checkout -b feature/amazing-feature
3. Follow our patterns: See .github/patterns/
4. Write tests: Maintain >80% coverage
5. Submit a PR: Use our PR template

Guidelines: docs/CONTRIBUTING.md

---

🛠️ Development

Commands

npm run dev              # Development server (localhost:3000)
npm run build            # Production build
npm run start            # Start production server
npm run lint             # Lint code
npm run format           # Format code
npm run type-check       # TypeScript validation
npm run hash-password    # Generate password hash

Environment Variables

Required variables (see .env.example):

# NextAuth
NEXTAUTH_SECRET=          # openssl rand -base64 32
NEXTAUTH_URL=             # http://localhost:3000

# Google Cloud
GOOGLE_PROJECT_ID=        # Your GCP project ID
GOOGLE_CLIENT_ID=         # OAuth client ID
GOOGLE_CLIENT_SECRET=     # OAuth client secret

# Auth User
AUTH_USER_EMAIL=          # Authorized email
AUTH_USER_PASSWORD_HASH=  # bcrypt hash

Complete setup: docs/DEVELOPMENT.md

---

📊 Performance

• Server Components by default for reduced JavaScript
• Streaming responses for real-time AI chat
• Automatic code splitting with Next.js
• Image optimization with next/image
• Turbopack for faster development builds
• Edge middleware for rate limiting

Metrics: docs/PERFORMANCE.md

---

🌍 Deployment

Production: chat.daza.ar (Google Cloud Run, us-central1)
Branch strategy: develop (testing) → main (production)

Deploy to Cloud Run

# One-command deploy
./scripts/deployment/deploy-production.sh

# Or manual deploy
gcloud run deploy chat-production \
  --source . \
  --region us-central1 \
  --platform managed

Full guide: docs/deployment/CLOUD-RUN-DEPLOYMENT.md

---

💰 Cost Estimation

Google Cloud Run (Monthly)

• Low usage (~1K requests): $2-5
• Medium usage (~10K requests): $10-20
• High usage (~50K requests): $30-50

Vertex AI

• Text generation: ~$0.0001 per request
• Image generation: ~$0.001 per request

---

🆘 Support

• 🐛 Report Issues - Bug reports & feature requests
• 💬 Discussions - Questions & ideas
• 📚 Documentation - Comprehensive guides
• 🛡️ Security - Security policy & vulnerability reporting

---

📄 License

MIT License - see LICENSE file for details.

---

🙏 Acknowledgments

Built with Next.js, Google Vertex AI, shadcn/ui, and ❤️ by the community.

---

⭐ Star us on GitHub if this project helps you!

🏠 Home • 📚 Docs • 🌐 Demo • 💬 Discuss