 pluto
|
2df137ee2a
|
feat: add recognition engine with CLIP matching and Ollama vision LLM
- OllamaClient: analyze_image, compare_images, is_available
- Recognition pipeline: CLIP embedding -> cosine similarity -> threshold
routing (known >0.85, unknown <0.60, ambiguous -> Ollama fallback)
- Vision dispatcher: get_description() supports haiku/ollama/both backends
- 9 embedding serialization tests
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
|
2026-03-07 17:17:49 -06:00 |
|
 Jeremy Hobbs
|
6086ed3cc0
|
Initial commit: frigate-notify application
AI-powered video alert service that bridges Frigate NVR events to Matrix.
Listens to MQTT, uses Claude Haiku vision to analyze snapshots, and posts
annotated alerts to a Matrix room.
- app/main.py: MQTT subscriber and event orchestration loop
- app/vision.py: Claude Haiku vision analysis wrapper
- app/matrix_client.py: Matrix HTTP client for sending messages/images
- app/requirements.txt: Python dependencies
- Dockerfile: container image build definition
- docker-compose.yml: deployment configuration (host network, NAS mounts)
- .env.example: required environment variable template (copy to .env)
|
2026-03-07 14:30:57 -06:00 |
|