How jhn07/ai-floor-analysis works
Project type and purpose
• This is a full-stack Next.js 13 application (“app” directory, React components, built-in API routes) that lets users upload floor plans, run AI-powered analysis, chat about them, and even generate TTS responses.
File structure
• Top-level “app” directory: contains your React pages and built-in API routes (analyze, chat, tts).
• “components”: reusable UI pieces divided into analysis cards, chat UI, and generic UI elements.
• “hooks”: client-side React hooks for file uploads, chat state, and scrolling.
• “services”: a service layer that abstracts calls to your backend routes (api.service.ts) and to external AI providers (ai-analyzer.service.ts, ai-chat.service.ts).
• “lib/utils.ts” and “types”: application utilities and TypeScript typings.
README for additional insights
• Uses Next.js 13 with the App Router, React, and Vercel deployment.
• No dedicated database layer—AI requests go out at runtime via the API routes.
Elements
– Blue for frontend/UI
– Green for backend/API routes & services
– Orange for external systems (AI/TTS)
• Annotations for TypeScript types, utility modules, and the public asset directory if relevant.