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

@@ -1,19 +1,13 @@
"""
Unified search service — hybrid FTS + semantic (RRF) search.
Phase 1 (PR4): semantic-only via pgvector cosine similarity.
Phase 2 (PR5): adds FTS via tsvector, enables RRF fusion.
FTS search over photos.search_vector with optional tag/date filters.
"""
import logging
from typing import Optional
import numpy as np
from sqlalchemy import select, text, func
from sqlalchemy import select, text
from sqlalchemy.ext.asyncio import AsyncSession
from app.models import Photo
from app.models.embeddings import Embedding
from app.config import settings
logger = logging.getLogger(__name__)
@@ -27,135 +21,57 @@ async def hybrid_search(
limit: int = 50,
offset: int = 0,
) -> list[dict]:
"""Run hybrid search (FTS + semantic) with RRF fusion.
Currently semantic-only; FTS leg added in PR5.
"""
model_name = settings.vision.embedder.name
results = {}
# ── Semantic search (CLIP text → pgvector cosine) ─────────────────
"""Full-text search using photos.search_vector. No embeddings, no OCR."""
if q:
try:
from app.services.vision.registry import registry
embedder = registry.get_embedder()
query_vec = embedder.embed_text(q)
# pgvector cosine distance: <=> returns distance (lower = closer).
# Join photos so we can filter out discarded / hidden rows
# inside the same query — otherwise a hidden-folder photo
# can take a top-N rank and starve the visible results.
vec_str = "[" + ",".join(str(float(v)) for v in query_vec) + "]"
stmt = text("""
SELECT e.photo_id,
(e.vector <=> :qvec::vector) AS distance
FROM embeddings e
JOIN photos p ON p.id = e.photo_id
WHERE e.model = :model
AND p.is_trashed = false
AND p.is_hidden = false
ORDER BY e.vector <=> :qvec::vector
LIMIT 200
""")
rows = (await db.execute(stmt, {"qvec": vec_str, "model": model_name})).fetchall()
for rank, (photo_id, distance) in enumerate(rows):
if photo_id not in results:
results[photo_id] = {"semantic_rank": rank, "fts_rank": None}
else:
results[photo_id]["semantic_rank"] = rank
except Exception as e:
logger.warning("Semantic search failed (models may not be loaded): %s", e)
# ── FTS search (photos.search_vector + ocr_text) ────────────────
if q:
try:
# Same discarded/hidden filter as the semantic leg.
# The OCR branch joins photos (through photo_id) so we can
# filter there too; otherwise OCR hits in hidden folders
# would leak into results.
fts_stmt = text("""
SELECT id, ts_rank(search_vector, plainto_tsquery('english', :q)) AS rank
FROM photos
WHERE search_vector @@ plainto_tsquery('english', :q)
AND is_trashed = false
AND is_hidden = false
UNION
SELECT o.photo_id AS id,
MAX(o.confidence) AS rank
FROM ocr_text o
JOIN photos p ON p.id = o.photo_id
WHERE to_tsvector('english', o.text) @@ plainto_tsquery('english', :q)
AND p.is_trashed = false
AND p.is_hidden = false
GROUP BY o.photo_id
ORDER BY rank DESC
LIMIT 200
LIMIT 500
""")
fts_rows = (await db.execute(fts_stmt, {"q": q})).fetchall()
for rank, (photo_id, score) in enumerate(fts_rows):
if photo_id not in results:
results[photo_id] = {"semantic_rank": None, "fts_rank": rank}
else:
results[photo_id]["fts_rank"] = rank
rows = (await db.execute(fts_stmt, {"q": q})).fetchall()
except Exception as e:
logger.warning("FTS search failed: %s", e)
rows = []
# ── RRF fusion ────────────────────────────────────────────────────
k = 60
scored = []
for photo_id, ranks in results.items():
score = 0.0
if ranks["semantic_rank"] is not None:
score += 1.0 / (k + ranks["semantic_rank"])
if ranks.get("fts_rank") is not None:
score += 1.0 / (k + ranks["fts_rank"])
scored.append((photo_id, score))
scored = [(pid, float(rank)) for pid, rank in rows]
scored.sort(key=lambda x: -x[1])
# If no text query, fall back to recent photos. Always filter out
# discarded + hidden here — this path backs the "Tags" and "People"
# browse views, which should honor the folder hide flag.
if not q:
if tag_ids:
from app.models.tags import photo_tags
# Subquery to get distinct photo_ids matching the tag filter
sub = select(photo_tags.c.photo_id).where(
photo_tags.c.tag_id.in_(tag_ids)
).distinct().subquery()
stmt = select(Photo.id).join(sub, Photo.id == sub.c.photo_id)
else:
stmt = select(Photo.id)
stmt = stmt.where(
Photo.is_discarded.is_(False),
Photo.is_hidden.is_(False),
)
stmt = stmt.order_by(Photo.added_at.desc())
if date_from:
stmt = stmt.where(Photo.taken_at >= date_from)
if date_to:
stmt = stmt.where(Photo.taken_at <= date_to)
stmt = stmt.offset(offset).limit(limit)
rows = (await db.execute(stmt)).fetchall()
return [{"photo_id": row[0], "score": 0.0} for row in rows]
photo_ids = [pid for pid, _ in scored]
if not photo_ids:
return []
stmt = select(photo_tags.c.photo_id).where(
photo_tags.c.photo_id.in_(photo_ids),
photo_tags.c.tag_id.in_(tag_ids),
).distinct()
valid = {row[0] for row in (await db.execute(stmt)).fetchall()}
scored = [(pid, s) for pid, s in scored if pid in valid]
# Apply filters to scored results
photo_ids = [pid for pid, _ in scored]
if not photo_ids:
return []
page = scored[offset : offset + limit]
return [{"photo_id": pid, "score": s} for pid, s in page]
# Filter by tags if requested
# No text query — recent photos with tag/date filters.
if tag_ids:
from app.models.tags import photo_tags
stmt = select(photo_tags.c.photo_id).where(
photo_tags.c.photo_id.in_(photo_ids),
photo_tags.c.tag_id.in_(tag_ids),
).distinct()
valid_ids = {row[0] for row in (await db.execute(stmt)).fetchall()}
scored = [(pid, s) for pid, s in scored if pid in valid_ids]
# Paginate
page = scored[offset : offset + limit]
return [{"photo_id": pid, "score": score} for pid, score in page]
sub = select(photo_tags.c.photo_id).where(
photo_tags.c.tag_id.in_(tag_ids)
).distinct().subquery()
stmt = select(Photo.id).join(sub, Photo.id == sub.c.photo_id)
else:
stmt = select(Photo.id)
stmt = stmt.where(
Photo.is_discarded.is_(False),
Photo.is_hidden.is_(False),
)
if date_from:
stmt = stmt.where(Photo.taken_at >= date_from)
if date_to:
stmt = stmt.where(Photo.taken_at <= date_to)
stmt = stmt.order_by(Photo.added_at.desc()).offset(offset).limit(limit)
rows = (await db.execute(stmt)).fetchall()
return [{"photo_id": row[0], "score": 0.0} for row in rows]