I Have 1 Hour Free" A Walk Plan in 10 Seconds, Powered by Local AI

Описание и применение

Локальный ИИ‑агент преобразует свободное время в конкретный план прогулки, используя открытые данные и небольшие модели.

Задача

People with short free time often waste it scrolling instead of going outside.

Результат

The agent delivers a quick, accurate walk plan using only local models and free open data, enabling users to spend free time outdoors without external API costs or data privacy concerns.

Рабочий процесс

• User inputs free time duration and location into the Streamlit app.
• The tiny decision model (tev1:0.8b) selects required tools.
• The larger model (qwen2.5:3b) calls tools via LangChain to gather weather, daylight, and park data.
• Python safety logic calculates leave‑by, turn‑back, and home‑by times and warns about rain or sunset proximity.
• The agent outputs a short, friendly headline and a map of nearby parks.
• The user follows the plan and goes outside.
• The "how this answer was made" view shows all tool calls and results.

Доказательства

Free Time Walk Planner is a local AI agent that turns "I have 1 hour free" into a real plan for getting outside.

Источник

It picks a nearby park, tells you when to leave and when to turn back so you're home before sunset, and says what to carry based on the weather.

Источник

Two small local models on Ollama, each with one job: tev1:0.8b and qwen2.5:3b.

Источник

Open-Meteo: weather forecast; Nominatim (OpenStreetMap): place name → coordinates; Overpass API (OpenStreetMap): nearby parks, gardens and trails; OSRM: walking routes and distances; astral: sunrise, sunset and golden hour, calculated fully offline.

Источник

Leave‑by, turn‑back and home‑by times, plus warnings for rain, wind or a return close to sunset, are all calculated in code, so the numbers are always correct.

Источник