dtoro/mule-image
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor: strip AI pipeline to binary photo/other classifier

Browse Source 
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:
authentik Default Admin
2026-04-14 22:27:17 +02:00
parent 5c531f11da
commit 574d71371f
50 changed files with 700 additions and 3068 deletions
Download Patch File Download Diff File Expand all files Collapse all files

95
backend/app/routers/library.py
View File

@@ -89,6 +89,12 @@ async def get_library_stats(
)
).scalar() or 0
needs_review_count = (
await db.execute(
select(func.count(Photo.id)).where(visible, Photo.needs_review.is_(True))
)
).scalar() or 0
# Legacy split (kept for the existing /stats consumers).
photo_count = (
await db.execute(
@@ -120,6 +126,7 @@ async def get_library_stats(
"with_gps": with_gps_count,
"duplicates": duplicates_count,
"discarded": discarded_count,
"needs_review": needs_review_count,
"total_photos": photo_count,
"total_videos": video_count,
"total_size": size,
@@ -437,10 +444,7 @@ async def get_worker_status(
r = _redis.Redis.from_url(settings.redis_url, socket_timeout=1.0)
r.ping()
broker_ok = True
# `vision` is the big one — embed / classify / detect / ocr /
# extract_faces all land here, so it's where backlogs actually
# pile up. Leaving it off the dashboard made it look like the
# queue was always empty while the worker was clearly busy.
# `vision` runs the content classifier — the only heavy queue.
for q in ('default', 'high', 'low', 'vision'):
try:
queue_depths[q] = int(r.llen(q) or 0)
@@ -525,8 +529,6 @@ async def get_pipeline_stats(
Keep the shape flat + serialisable; the frontend turns it straight
into a list of rows without needing to know about the models.
"""
from app.config import settings as _settings
from app.models import Embedding, FaceEmbedding, OCRText
from app.models.tags import photo_tags # association Table, not a model
owner = _owner_filter(current_user, scope)
@@ -572,45 +574,15 @@ async def get_pipeline_stats(
)
)
# Embeddings: count distinct photos that have a row for the currently
# configured embedder model. A photo can have multiple model rows
# (historical re-embeds) so COUNT(DISTINCT) is the right thing here.
embedder_model = _settings.vision.embedder.name
embeddings_done = await scalar_count(
select(func.count(func.distinct(Embedding.photo_id)))
.select_from(Embedding)
.join(Photo, Photo.id == Embedding.photo_id)
.where(not_discarded, Embedding.model == embedder_model)
)
tagged_photos = await scalar_count(
# Classified: distinct photos with a content_type tag.
classified_done = await scalar_count(
select(func.count(func.distinct(photo_tags.c.photo_id)))
.select_from(photo_tags)
.join(Photo, Photo.id == photo_tags.c.photo_id)
.where(not_discarded)
.where(not_discarded, photo_tags.c.source == 'vision:clip_classifier')
)
ocr_done = await scalar_count(
select(func.count(func.distinct(OCRText.photo_id)))
.select_from(OCRText)
.join(Photo, Photo.id == OCRText.photo_id)
.where(not_discarded)
)
# Faces: photos that have at least one face_embeddings row. A photo
# with no faces legitimately finishes face extraction with zero rows,
# so this undercounts by exactly "images with no visible people". We
# surface the photo-with-faces count rather than "images scanned for
# faces" because the latter isn't tracked anywhere.
faces_photos = await scalar_count(
select(func.count(func.distinct(FaceEmbedding.photo_id)))
.select_from(FaceEmbedding)
.join(Photo, Photo.id == FaceEmbedding.photo_id)
.where(not_discarded)
)
face_rows = await scalar_count(select(func.count(FaceEmbedding.id)))
face_clusters = await scalar_count(
select(func.count(func.distinct(FaceEmbedding.cluster_id)))
.where(FaceEmbedding.cluster_id.is_not(None))
needs_review_count = await scalar_count(
select(func.count(Photo.id)).where(not_discarded, Photo.needs_review.is_(True))
)
duplicate_groups = await scalar_count(
@@ -657,43 +629,11 @@ async def get_pipeline_stats(
"hint": "Feeds duplicate detection.",
},
{
"key": "embeddings",
"label": f"Embeddings ({embedder_model})",
"done": embeddings_done,
"key": "classification",
"label": "Content classification (photo vs other)",
"done": classified_done,
"total": total_images,
"hint": "Semantic search + content classification.",
},
{
"key": "tags",
"label": "Object tags (YOLO)",
"done": tagged_photos,
"total": total_images,
"hint": "Auto-generated object labels. Not every photo has a detectable object.",
"partial": True,
},
{
"key": "ocr",
"label": "OCR text",
"done": ocr_done,
"total": total_images,
"hint": "Extracted text from screenshots / documents. Many photos have none.",
"partial": True,
},
{
"key": "faces",
"label": "Face detection",
"done": faces_photos,
"total": total_images,
"hint": f"{face_rows} face rows detected across {faces_photos} photos.",
"partial": True,
},
{
"key": "face_clusters",
"label": "Face clusters",
"done": face_clusters,
"total": face_clusters, # no meaningful "total" — it's just the current count
"hint": "Built by recluster_faces. Run it after backfill to populate the People view.",
"standalone": True,
"hint": f"{needs_review_count} photos flagged for review.",
},
{
"key": "duplicates",
@@ -708,7 +648,6 @@ async def get_pipeline_stats(
return {
"total_photos": total_photos,
"total_images": total_images,
"embedder_model": embedder_model,
"stages": stages,
}