refactor: strip AI pipeline to binary photo/other classifier

Drops face recognition, OCR, object detection, and semantic embeddings.
The sole remaining vision task is a CLIP-based binary classifier
(photography vs other); photos in "other" get needs_review=true so
screenshots, documents, memes and scans can be triaged from a new
filter pill in the UI.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-04-14 22:27:17 +02:00
parent 5c531f11da
commit 574d71371f
50 changed files with 700 additions and 3068 deletions

View File

@@ -1,124 +1,46 @@
"""
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.
Ensure the OpenCLIP ViT-B/32 visual encoder is present on worker boot.
Exported via export_models.py if missing.
"""
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 = [
REQUIRED = [
("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))
missing = [(rel, desc) for rel, desc in REQUIRED if not (base / rel).exists()]
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)
logger.warning("Missing %d model file(s); attempting automatic export", len(missing))
try:
from app.services.vision import export_models
export_models.export_openclip_visual(base)
except Exception as e:
logger.error(
"Export failed: %s. Run `python -m app.services.vision.export_models "
"--models-dir %s` manually to retry.",
e, base,
)
from app.services.vision import export_models
missing_paths = {rel for rel, _ in missing}
# Only run the export functions whose outputs are actually missing.
# Each function is mapped to the file(s) it produces.
export_map = [
(export_models.export_openclip, ["embed/visual.onnx", "embed/textual.onnx"]),
(export_models.export_siglip2, ["embed_siglip2/visual.onnx", "embed_siglip2/textual.onnx"]),
(export_models.export_yolov8n, ["detect/yolov8n.onnx"]),
]
for export_fn, outputs in export_map:
if not any(o in missing_paths for o in outputs):
continue
try:
export_fn(base)
except Exception as e:
logger.error(
"Export step %s failed: %s. "
"Run `python -m app.services.vision.export_models "
"--models-dir %s` manually to retry.",
export_fn.__name__,
e,
base,
)
# 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)
still_missing = [(r, d) for r, d in REQUIRED if not (base / r).exists()]
if still_missing:
for rel, desc in still_missing:
logger.error(" still missing: %s%s", base / rel, desc)
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")
_redis.from_url(settings.redis_url).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)