2df137ee2a101138f4070eed3641e877b2546f71
- 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>
Description
AI-powered Frigate NVR video alert service: MQTT -> Claude Vision -> Matrix
Languages
Python
75.3%
JavaScript
16.7%
CSS
5.9%
HTML
1.6%
Dockerfile
0.5%