dtoro 1ebc4bfe73 feat: add YOLO object detection writing to unified Tag model ...

Implement detect_objects Celery task:
- Runs YOLOv8n on 640px thumbnail via ONNX Runtime
- Creates Tag(kind=object) rows for each COCO class detected
- Writes photo_tags associations with confidence, bbox, and source
- Wipes previous detections per source model on re-run

No new tables/migrations — uses the unified Tag model from PR3.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-10 09:11:26 +02:00

..

alembic

feat: add OCR text extraction and Postgres full-text search

2026-04-10 09:10:14 +02:00

app

feat: add YOLO object detection writing to unified Tag model

2026-04-10 09:11:26 +02:00

alembic.ini

feat: migrate to Postgres + pgvector with Alembic scaffolding

2026-04-10 08:46:20 +02:00

Dockerfile

feat: add vision pipeline scaffolding with ONNX backend

2026-04-10 09:00:06 +02:00

requirements.txt

feat: add vision pipeline scaffolding with ONNX backend

2026-04-10 09:00:06 +02:00