Spot-Undoo: Privacy-First AI Kerala Micro-Travel Planner & Layover Explorer

Описание и применение

Spot-Undoo – локальный, приватный планировщик путешествий в Керале, использующий локально хостинг ИИ и MongoDB Atlas для генерации маршрутов в реальном времени, учитывая ограничения времени и бюджета.

Задача

Travel apps funnel users to overcrowded tourist traps, missing local culture and leaving transit commuters with no curated routes within time and budget constraints.

Результат

Spot-Undoo delivers privacy‑first, locally hosted itineraries that expose authentic Kerala spots, support transit commuters with safe return guarantees, and enable community contributions via MongoDB Atlas.

Рабочий процесс

• 1. Open app – GPS auto‑snaps to nearest Kerala railway hub.
• 2. AI model (Qwen 2.5 3B fine‑tuned via Ollama) generates 3 plan archetypes based on user constraints.
• 3. Planner displays itineraries on Neo‑Brutalist vector canvas or Live OpenStreetMap.
• 4. User selects itinerary; app ensures safe return before train departure.
• 5. Community can upload new spots; MongoDB Atlas stores data with geospatial duplicate guard.

Доказательства

Spot-Undoo solves this by pairing locally hosted open-weight AI models (fine-tuned Qwen 2.5:3B on Ollama) with MongoDB Atlas and a Native Android build to generate constraint-guaranteed itineraries on the fly.

Источник

Runs locally using Ollama (spot-undo-qwen). ~71.4 tokens/second on an RTX 3050 mobile GPU (warm latency: 2.39 seconds).

Источник

Built-in Geospatial Duplicate Guard (rejects identical spots within a ±0.00001 coordinate tolerance).

Источник

Native Android APK & Responsive Mobile Web: Packaged with Capacitor 6 for native Android deployment (5.2 MB footprint).

Источник