TerraGuard: Teaching a Local Gemma 4 to Read a Hillside
Описание и применение
Прототип TerraGuard объединяет датчики ESP32, FastAPI, локальный Gemma 4 12B и React для автономного мониторинга склонов, оценки рисков и оповещений без внешних LLM‑API.
Задача
Integrating multimodal sensor data with a local LLM to provide structured risk assessments and alerts for hillside monitoring without relying on external APIs.
Результат
A working prototype demonstrates end‑to‑end hillside monitoring, local LLM assessment, alerting, investigation, and daily reporting, all without external LLM APIs.
Рабочий процесс
- 1. Observe: ESP32 reads sensors and records data quality flags.
- 2. Interpret: FastAPI builds an evidence packet with current readings, history, deltas, and flags, then calls local Gemma 4 12B via Ollama.
- 3. Validate: Backend checks JSON schema, risk labels, and applies fallback rules.
- 4. Alert: Severity states (SAFE→WATCH→WARNING→CRITICAL) trigger overlays and sirens.
- 5. Investigate: Operators query past events; answers are grounded in stored records.
- 6. Report: Daily evidence‑based report with timeline, stats, narrative, and PDF is generated.
Доказательства
A physical ESP32 sensor node feeds a FastAPI backend, and the backend hands an evidence packet to Gemma 4 12B running locally through Ollama.
Gemma 4 12B is central, not decorative. We run gemma4:12b, the 12B Unified model. Per Google's official model card, it is an open‑weight model under Apache 2.0 that accepts text, image and audio input and documents a context window of up to 256K tokens.
The backend controls which evidence the model sees. Gemma has no access to the sensors, the database or the browser.
We report a working physical prototype where the monitoring, Gemma assessment, alert, report and preparedness workflows run in the current project configuration.
- Дата записи: 2026-10-26T10:11:18.709Z