Files
mule-image/backend/app/services/vision/bootstrap_models.py
dtoro fbeefb24a0 fix: vision tasks inherit user_id, admin owns mount root
- detect_objects, classify_content, recluster_faces now look up the
  photo's user_id and set it on created Tag rows — fixes tags being
  invisible to the owning user due to NULL user_id
- Initial admin setup creates source root at the mount root (/photos)
  instead of a subdirectory, since the admin owns the entire library
- Revert to OpenCLIP ViT-B/32 (512-d) as default embedder — SigLIP
  requires transformers version alignment not yet available in the
  Docker image. SigLIP2 code remains for future enablement.
- Add transformers to requirements for future SigLIP support

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-13 00:01:28 +02:00

110 lines
3.5 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)
if __name__ == "__main__":
logging.basicConfig(level=logging.INFO)
bootstrap()