f090a809a9
Addresses 16 robustness, transparency, and performance issues across the Celery media processing pipeline: Critical: - Singleton DB engine in vision tasks (was leaking one per task call) - acks_late + task_reject_on_worker_lost so crashed workers don't lose tasks - Global soft/hard time limits (5/10 min) to prevent hung worker slots - Thumbnail copy-before-resize (in-place mutation degraded larger sizes) - backfill_vision now checks each task type independently (OCR, faces, etc.) - Parameterized LIMIT in backfill_vision (was f-string SQL injection) High: - try/except + retry(max=3) on all vision inference tasks - extract_metadata writes processing_error on exiftool failure - PIL Image handles closed in _load_thumb/_load_original - Scan progress Redis keys auto-expire after 1 hour - Watcher lock renewal is wall-clock based (30s) not event-count based - worker_process_init signal warms up vision models on startup Medium: - Explicit task_routes for every task name (wildcards never matched) - app.services.metadata added to Celery include list - POST /maintenance/recover-stuck endpoint for photos stuck in processing - Docker healthchecks for worker-light, worker-vision, and Redis - Task ID in vision log lines for distributed tracing - Bare except:pass narrowed to specific exceptions Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
120 lines
3.9 KiB
Python
120 lines
3.9 KiB
Python
"""
|
|
Download vision model weights on first worker boot.
|
|
|
|
Run as: python -m app.services.vision.bootstrap_models
|
|
|
|
Or called from the vision worker entrypoint before Celery starts.
|
|
Downloads are idempotent — existing files are skipped.
|
|
|
|
For models that require export (OpenCLIP, YOLOv8n), see export_models.py.
|
|
Those must be exported once on any machine with pip, then placed in
|
|
the models volume before the worker starts.
|
|
"""
|
|
import logging
|
|
import os
|
|
from pathlib import Path
|
|
from urllib.request import urlretrieve
|
|
|
|
from app.config import settings
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
# (relative_path, url, description)
|
|
# Models with url=None must be pre-exported via export_models.py.
|
|
# InsightFace (RetinaFace + ArcFace) auto-downloads via the insightface
|
|
# package on first use — no manual download entries needed.
|
|
DOWNLOADS = []
|
|
|
|
# Models that need manual export via export_models.py
|
|
EXPORTS = [
|
|
("embed/visual.onnx", "OpenCLIP ViT-B/32 visual encoder"),
|
|
("embed/textual.onnx", "OpenCLIP ViT-B/32 textual encoder"),
|
|
("detect/yolov8n.onnx", "YOLOv8n object detector"),
|
|
]
|
|
|
|
|
|
def bootstrap(models_dir: str | None = None):
|
|
"""Ensure all model files are present. Download what we can, warn about
|
|
files that need manual export."""
|
|
base = Path(models_dir or settings.vision.models_dir)
|
|
base.mkdir(parents=True, exist_ok=True)
|
|
|
|
# Download auto-downloadable models
|
|
for rel_path, url, desc in DOWNLOADS:
|
|
dest = base / rel_path
|
|
dest.parent.mkdir(parents=True, exist_ok=True)
|
|
|
|
if dest.exists():
|
|
logger.debug("Already exists: %s (%s)", dest, desc)
|
|
continue
|
|
|
|
logger.info("Downloading %s → %s", desc, dest)
|
|
try:
|
|
urlretrieve(url, str(dest))
|
|
size_kb = dest.stat().st_size / 1024
|
|
logger.info("Downloaded %s (%.0f KB)", desc, size_kb)
|
|
except Exception as e:
|
|
logger.error("Failed to download %s: %s", desc, e)
|
|
if dest.exists():
|
|
dest.unlink()
|
|
|
|
# Check for manually-exported models
|
|
missing = []
|
|
for rel_path, desc in EXPORTS:
|
|
dest = base / rel_path
|
|
if not dest.exists():
|
|
missing.append((rel_path, desc))
|
|
|
|
if missing:
|
|
logger.warning(
|
|
"Missing %d model file(s); attempting automatic export:",
|
|
len(missing),
|
|
)
|
|
for rel_path, desc in missing:
|
|
logger.warning(" %s — %s", base / rel_path, desc)
|
|
|
|
try:
|
|
from app.services.vision import export_models
|
|
|
|
export_models.export_openclip(base)
|
|
export_models.export_siglip2(base)
|
|
export_models.export_yolov8n(base)
|
|
except Exception as e:
|
|
logger.error(
|
|
"Automatic export failed: %s. "
|
|
"Run `python -m app.services.vision.export_models "
|
|
"--models-dir %s` manually before starting the worker.",
|
|
e,
|
|
base,
|
|
)
|
|
return
|
|
|
|
# Re-check what's still missing after the export pass.
|
|
still_missing = [
|
|
(rel_path, desc)
|
|
for rel_path, desc in EXPORTS
|
|
if not (base / rel_path).exists()
|
|
]
|
|
if still_missing:
|
|
for rel_path, desc in still_missing:
|
|
logger.error(" still missing: %s — %s", base / rel_path, desc)
|
|
else:
|
|
logger.info("All model files present in %s", base)
|
|
else:
|
|
logger.info("All model files present in %s", base)
|
|
|
|
# Signal readiness via Redis so the scan pipeline knows the vision
|
|
# worker can accept tasks.
|
|
try:
|
|
import redis as _redis
|
|
r = _redis.from_url(settings.redis_url)
|
|
r.set("mulita:vision:ready", "1")
|
|
logger.info("Set mulita:vision:ready in Redis")
|
|
except Exception as e:
|
|
logger.warning("Could not set vision readiness flag in Redis: %s", e)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
logging.basicConfig(level=logging.INFO)
|
|
bootstrap()
|