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>

backend/app/models/__init__.py

@@ -6,9 +6,6 @@ from app.models.photos import Photo
 from app.models.folders import Folder, SourceRoot
 from app.models.tags import Tag, PhotoTag
 from app.models.heaps import Heap, HeapPhoto
-from app.models.embeddings import Embedding
-from app.models.ocr_text import OCRText
-from app.models.face_embedding import FaceEmbedding
 from app.models.sharing import HeapShare, FolderShare
 
 __all__ = [
@@ -20,9 +17,6 @@ __all__ = [
     'PhotoTag',
     'Heap',
     'HeapPhoto',
-    'Embedding',
-    'OCRText',
-    'FaceEmbedding',
     'HeapShare',
     'FolderShare',
-]
+]

backend/app/models/embeddings.py

@@ -1,24 +0,0 @@
-"""
-Embedding model — stores CLIP/SigLIP image embeddings via pgvector.
-
-Composite PK (photo_id, model) allows re-embedding with newer models
-without clobbering old vectors.
-
-Vector dimension is 768 to support SigLIP2 ViT-B/16 (the default).
-OpenCLIP ViT-B/32 (512-d) embeddings are zero-padded on insert so
-both models coexist in the same column. The padding is invisible to
-cosine similarity (zeros don't affect the angle).
-"""
-from sqlalchemy import Column, String, ForeignKey, DateTime, func
-from pgvector.sqlalchemy import Vector
-
-from app.database import Base
-
-
-class Embedding(Base):
-    __tablename__ = 'embeddings'
-
-    photo_id = Column(String, ForeignKey('photos.id', ondelete='CASCADE'), primary_key=True)
-    model = Column(String(64), primary_key=True)  # e.g. 'siglip2_vitb16'
-    vector = Column(Vector(512))                   # OpenCLIP ViT-B/32 → 512-d
-    created_at = Column(DateTime(timezone=True), server_default=func.now())

backend/app/models/face_embedding.py

@@ -1,24 +0,0 @@
-"""
-Face embedding model — stores per-face detection + recognition vectors.
-
-cluster_id FKs to tags.id where kind='face_cluster'. Null means
-unclustered (will be assigned by recluster_faces).
-"""
-from sqlalchemy import Column, String, Float, ForeignKey, DateTime, func
-from sqlalchemy.dialects.postgresql import JSONB
-from pgvector.sqlalchemy import Vector
-import uuid
-
-from app.database import Base
-
-
-class FaceEmbedding(Base):
-    __tablename__ = 'face_embeddings'
-
-    id = Column(String, primary_key=True, default=lambda: str(uuid.uuid4()))
-    photo_id = Column(String, ForeignKey('photos.id', ondelete='CASCADE'), nullable=False, index=True)
-    bbox = Column(JSONB)           # [x1, y1, x2, y2] normalized 0-1
-    vector = Column(Vector(512))   # ArcFace → 512-d
-    cluster_id = Column(String, ForeignKey('tags.id', ondelete='SET NULL'), nullable=True, index=True)
-    quality = Column(Float)
-    created_at = Column(DateTime(timezone=True), server_default=func.now())

backend/app/models/ocr_text.py

@@ -1,20 +0,0 @@
-"""
-OCR text model — stores text regions extracted from photos via rapidocr.
-"""
-from sqlalchemy import Column, String, Float, ForeignKey, Text, DateTime, func
-from sqlalchemy.dialects.postgresql import JSONB
-import uuid
-
-from app.database import Base
-
-
-class OCRText(Base):
-    __tablename__ = 'ocr_text'
-
-    id = Column(String, primary_key=True, default=lambda: str(uuid.uuid4()))
-    photo_id = Column(String, ForeignKey('photos.id', ondelete='CASCADE'), nullable=False, index=True)
-    text = Column(Text, nullable=False)
-    language = Column(String(8), default='')
-    confidence = Column(Float)
-    bbox = Column(JSONB)  # [x1, y1, x2, y2] normalized 0-1
-    created_at = Column(DateTime(timezone=True), server_default=func.now())

backend/app/models/photos.py

@@ -50,6 +50,11 @@ class Photo(Base):
     # rows, and POST /folders/{id}/hide recomputes it on toggle.
     is_hidden = Column(Boolean, nullable=False, default=False, server_default='false', index=True)
 
+    # "Needs review" — set by the content classifier when a photo is
+    # classified as 'other' (screenshot, document, meme, scan, etc.) so
+    # the user can page through non-photographs in the UI and triage them.
+    needs_review = Column(Boolean, nullable=False, default=False, server_default='false', index=True)
+
     # "Capture date is probably wrong" — denormalized from the folder/filename
     # date-guesser. Set at scan time and recomputed on every taken_at edit so
     # the filter bar can query it directly. See services/date_guess.py for
@@ -118,4 +123,5 @@ class Photo(Base):
         Index('ix_photos_media_type', 'media_type'),
         Index('ix_photos_processing_status', 'processing_status'),
         Index('ix_photos_lat_lon', 'latitude', 'longitude'),
+        Index('ix_photos_needs_review', 'needs_review'),
     )

backend/app/models/tags.py

@@ -6,7 +6,7 @@ labels, and face clusters via the `kind` column. The `photo_tags`
 association carries per-photo ML metadata (confidence, bounding box,
 source model).
 """
-from sqlalchemy import Column, String, Float, ForeignKey, Table, Index, UniqueConstraint
+from sqlalchemy import Column, String, Float, ForeignKey, Table, Index, UniqueConstraint  # noqa: F401
 from sqlalchemy.orm import relationship
 from sqlalchemy.dialects.postgresql import JSONB
 import uuid
@@ -22,7 +22,7 @@ photo_tags = Table(
     # ML metadata — null for user-applied tags
     Column('confidence', Float, nullable=True),
     Column('bbox', JSONB, nullable=True),       # [x1, y1, x2, y2] normalized 0-1
-    Column('source', String, nullable=True),     # e.g. "vision:yolov8n", "vision:sface"
+    Column('source', String, nullable=True),     # e.g. "vision:clip_classifier"
     Index('ix_photo_tags_photo_id', 'photo_id'),
     Index('ix_photo_tags_tag_id', 'tag_id'),
 )
@@ -42,16 +42,11 @@ class Tag(Base):
 
     # Tag classification
     kind = Column(String, nullable=False, default='user', index=True)
-    # kind values: 'user' | 'object' | 'scene' | 'face_cluster'
+    # kind values: 'user' | 'content_type'
 
     # Which model produced this tag (null for user-created)
     source = Column(String, nullable=True)
-    # e.g. "vision:yolov8n", "vision:sface", null
-
-    # For face clusters: the photo used as the cluster representative thumbnail
-    representative_photo_id = Column(
-        String, ForeignKey('photos.id', ondelete='SET NULL'), nullable=True
-    )
+    # e.g. "vision:clip_classifier", null
 
     # Relationships
     photos = relationship("Photo", secondary=photo_tags, backref="tags")