dtoro
649437dc85
Wire the full embedding flow: - Rewrite Embedding model to use pgvector Vector(512) with HNSW index - Add embed_photo, vision_fanout, backfill_vision Celery tasks on dedicated `vision` queue - Hook vision_fanout into generate_thumbnails completion - Add POST /api/v1/photos/search with hybrid RRF ranking (semantic-only for now; FTS leg added in PR5) - Stub ocr_photo, detect_objects, extract_faces tasks for later PRs Migration 0003 drops/recreates the embeddings table (was never populated). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
75 lines
2.1 KiB
Python
75 lines
2.1 KiB
Python
"""
|
|
Search API router — unified hybrid search endpoint.
|
|
"""
|
|
from typing import Optional
|
|
from fastapi import APIRouter, Depends
|
|
from pydantic import BaseModel
|
|
from sqlalchemy.ext.asyncio import AsyncSession
|
|
from sqlalchemy import select
|
|
|
|
from app.database import get_db
|
|
from app.models import Photo
|
|
from app.services.search import hybrid_search
|
|
|
|
router = APIRouter()
|
|
|
|
|
|
class SearchRequest(BaseModel):
|
|
q: Optional[str] = None
|
|
filters: Optional[dict] = None
|
|
limit: int = 50
|
|
offset: int = 0
|
|
|
|
|
|
@router.post("")
|
|
async def search_photos(body: SearchRequest, db: AsyncSession = Depends(get_db)):
|
|
"""Unified search endpoint. Every query runs hybrid (FTS + semantic)
|
|
by default — the user never picks a mode.
|
|
|
|
Filters:
|
|
- tag_ids: list of tag IDs (any kind: user, object, face_cluster)
|
|
- date_from / date_to: ISO date strings
|
|
"""
|
|
filters = body.filters or {}
|
|
|
|
results = await hybrid_search(
|
|
db=db,
|
|
q=body.q,
|
|
tag_ids=filters.get("tag_ids"),
|
|
date_from=filters.get("date_from"),
|
|
date_to=filters.get("date_to"),
|
|
limit=body.limit,
|
|
offset=body.offset,
|
|
)
|
|
|
|
if not results:
|
|
return {"results": [], "total": 0}
|
|
|
|
# Hydrate with photo data
|
|
photo_ids = [r["photo_id"] for r in results]
|
|
stmt = select(Photo).where(Photo.id.in_(photo_ids))
|
|
rows = (await db.execute(stmt)).scalars().all()
|
|
photo_map = {p.id: p for p in rows}
|
|
|
|
hydrated = []
|
|
for r in results:
|
|
photo = photo_map.get(r["photo_id"])
|
|
if not photo:
|
|
continue
|
|
hydrated.append({
|
|
"id": photo.id,
|
|
"filename": photo.filename,
|
|
"filepath": photo.filepath,
|
|
"media_type": photo.media_type,
|
|
"width": photo.width,
|
|
"height": photo.height,
|
|
"taken_at": photo.taken_at.isoformat() if photo.taken_at else None,
|
|
"rating": photo.rating,
|
|
"color_label": photo.color_label,
|
|
"thumb_small": photo.thumb_small,
|
|
"thumb_medium": photo.thumb_medium,
|
|
"score": r["score"],
|
|
})
|
|
|
|
return {"results": hydrated, "total": len(hydrated)}
|