MACHINE_LEARNING_MODEL_TTL=600 is a single global knob, so it unloads the CLIP textual (smart-search) encoder after idle exactly like OCR/face — immich has no per-model pin. This CronJob pings the textual encoder every 5 min (< the 600s TTL) via immich-ml /predict, so a search query never pays the ~1.5s cold-load, while idle OCR/face still free their VRAM on the shared T4. Textual-only (search = text->embedding->pgvector); the visual encoder is import-time and left to unload. curl baked into the image (no runtime install). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| agents | ||
| commands | ||
| reference | ||
| scripts | ||
| skills | ||
| calendar-query.py | ||
| CLAUDE.md | ||
| home-assistant-sofia.py | ||
| home-assistant.py | ||
| internet-mode-used_DO_NOT_REMOVE_MANUALLY_SECURITY_RISK | ||
| pfsense.py | ||
| settings.json | ||