feat: add OCR text extraction and Postgres full-text search

- Create ocr_text table for storing per-region OCR results
- Add tsvector search_vector column to photos with GIN index and
  auto-update trigger on filename/user_title/user_notes
- Implement ocr_photo Celery task using rapidocr-onnxruntime
- Add FTS leg to hybrid search: queries photos.search_vector and
  ocr_text via UNION, fused with semantic results via RRF (k=60)

Migration 0004 backfills search_vector for existing rows.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-04-10 09:10:14 +02:00
parent 649437dc85
commit 842a4fc864
5 changed files with 167 additions and 6 deletions

View File

@@ -62,9 +62,30 @@ async def hybrid_search(
except Exception as e:
logger.warning("Semantic search failed (models may not be loaded): %s", e)
# ── FTS search (placeholder for PR5) ──────────────────────────────
# Will be: tsvector @@ plainto_tsquery(q), ranked by ts_rank.
# For now, skip.
# ── FTS search (photos.search_vector + ocr_text) ────────────────
if q:
try:
fts_stmt = text("""
SELECT id, ts_rank(search_vector, plainto_tsquery('english', :q)) AS rank
FROM photos
WHERE search_vector @@ plainto_tsquery('english', :q)
UNION
SELECT o.photo_id AS id,
MAX(o.confidence) AS rank
FROM ocr_text o
WHERE to_tsvector('english', o.text) @@ plainto_tsquery('english', :q)
GROUP BY o.photo_id
ORDER BY rank DESC
LIMIT 200
""")
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
except Exception as e:
logger.warning("FTS search failed: %s", e)
# ── RRF fusion ────────────────────────────────────────────────────
k = 60