Files
FabledCurator/backend/app/api/gallery.py
T
bvandeusen 79cd1234e2
CI / lint (push) Successful in 2s
CI / backend-lint-and-test (push) Successful in 11s
CI / frontend-build (push) Successful in 28s
CI / integration (push) Successful in 2m57s
feat(gallery): visual 'more like this' search (Phase 3 backend)
GalleryService.similar() ranks images by pgvector cosine distance to a source
image's precomputed SigLIP embedding — no query-time ML inference. Composes
with the Phase-1/2 scope filters (AND) but replaces the date sort (always
nearest-first, bounded top-N, no cursor). Returns None for a missing source
(→404), [] for a source with no embedding (video / pending ML); excludes self
and NULL-embedding rows. New GET /api/gallery/similar?similar_to=<id>&limit=N.
Image-detail payload gains has_embedding so the UI can hide the surface.

Alembic 0036 adds an HNSW vector_cosine_ops index on siglip_embedding (1152<2000
dims) so the search is sub-50ms ANN instead of a full scan; one-time ~30-60s
build over existing embeddings on deploy. Shared _gallery_images/_image_json
helpers de-dup the scroll/similar builders.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-04 08:47:43 -04:00

201 lines
7.1 KiB
Python

"""Gallery API: cursor scroll, timeline, jump, image detail, facets."""
from datetime import UTC, datetime, timedelta
from quart import Blueprint, jsonify, request
from ..extensions import get_session
from ..services.gallery_service import GalleryService
gallery_bp = Blueprint("gallery", __name__, url_prefix="/api/gallery")
def _image_json(i):
"""Serialize a GalleryImage for the scroll/similar list responses."""
return {
"id": i.id,
"sha256": i.sha256,
"mime": i.mime,
"width": i.width,
"height": i.height,
"created_at": i.created_at.isoformat(),
"posted_at": i.posted_at.isoformat() if i.posted_at else None,
"thumbnail_url": i.thumbnail_url,
"artist": i.artist,
}
def _parse_date(raw):
"""Parse a YYYY-MM-DD query value to a UTC midnight datetime, or None.
Raises ValueError (→ 400) on a malformed value."""
if not raw:
return None
return datetime.strptime(raw, "%Y-%m-%d").replace(tzinfo=UTC)
def _parse_filters():
"""Parse the composable gallery filters from query args, returning
``(filters_dict, sort)``. Raises ValueError (→ 400) on malformed ids/dates.
`tag_id` accepts a single id or a comma-separated list (AND); `media` is
image|video; `sort` is newest|oldest; `platform` selects one platform
(or the UNSOURCED_PLATFORM sentinel); `untagged`/`no_artist` are boolean
flags; `date_from`/`date_to` are inclusive calendar-day bounds (date_to is
widened by a day so the whole day is covered by the service's half-open
`< date_to`)."""
tag_raw = request.args.get("tag_id")
tag_ids = (
[int(x) for x in tag_raw.split(",") if x.strip()] if tag_raw else None
) or None
post_id_raw = request.args.get("post_id")
post_id = int(post_id_raw) if post_id_raw else None
artist_id_raw = request.args.get("artist_id")
artist_id = int(artist_id_raw) if artist_id_raw else None
media = request.args.get("media")
media_type = media if media in ("image", "video") else None
sort = request.args.get("sort")
sort = sort if sort in ("newest", "oldest") else "newest"
platform = request.args.get("platform") or None
untagged = request.args.get("untagged") in ("1", "true", "yes")
no_artist = request.args.get("no_artist") in ("1", "true", "yes")
date_from = _parse_date(request.args.get("date_from"))
date_to = _parse_date(request.args.get("date_to"))
if date_to is not None:
date_to += timedelta(days=1) # inclusive of the date_to calendar day
filters = {
"tag_ids": tag_ids, "post_id": post_id, "artist_id": artist_id,
"media_type": media_type, "platform": platform,
"untagged": untagged, "no_artist": no_artist,
"date_from": date_from, "date_to": date_to,
}
return filters, sort
@gallery_bp.route("/scroll", methods=["GET"])
async def scroll():
cursor = request.args.get("cursor") or None
try:
limit = int(request.args.get("limit", "50"))
filters, sort = _parse_filters()
except ValueError:
return jsonify({"error": "invalid filter or limit parameter"}), 400
async with get_session() as session:
svc = GalleryService(session)
try:
page = await svc.scroll(
cursor=cursor, limit=limit, sort=sort, **filters,
)
except ValueError as exc:
return jsonify({"error": str(exc)}), 400
return jsonify(
{
"images": [_image_json(i) for i in page.images],
"next_cursor": page.next_cursor,
"date_groups": [
{"year": y, "month": m, "image_ids": ids} for y, m, ids in page.date_groups
],
}
)
@gallery_bp.route("/similar", methods=["GET"])
async def similar():
"""Visual "more like this": images ranked by cosine distance to the
`similar_to` image's embedding. Composes with the scope filters (AND) but
ignores post_id and sort. Bounded top-N, no cursor."""
try:
similar_to = int(request.args["similar_to"])
limit = int(request.args.get("limit", "100"))
filters, _sort = _parse_filters()
except (KeyError, ValueError):
return jsonify({"error": "similar_to query param required"}), 400
# post_id is the exclusive post-detail view — not a similarity scope.
scope = {k: v for k, v in filters.items() if k != "post_id"}
async with get_session() as session:
svc = GalleryService(session)
try:
images = await svc.similar(image_id=similar_to, limit=limit, **scope)
except ValueError as exc:
return jsonify({"error": str(exc)}), 400
if images is None:
return jsonify({"error": "not found"}), 404
return jsonify(
{
"images": [_image_json(i) for i in images],
"next_cursor": None,
"date_groups": [],
}
)
@gallery_bp.route("/timeline", methods=["GET"])
async def timeline():
try:
filters, _sort = _parse_filters()
except ValueError:
return jsonify({"error": "invalid filter parameter"}), 400
async with get_session() as session:
svc = GalleryService(session)
try:
buckets = await svc.timeline(**filters)
except ValueError as exc:
return jsonify({"error": str(exc)}), 400
return jsonify(
[{"year": b.year, "month": b.month, "count": b.count} for b in buckets]
)
@gallery_bp.route("/facets", methods=["GET"])
async def facets():
try:
filters, _sort = _parse_filters()
except ValueError:
return jsonify({"error": "invalid filter parameter"}), 400
async with get_session() as session:
svc = GalleryService(session)
try:
f = await svc.facets(**filters)
except ValueError as exc:
return jsonify({"error": str(exc)}), 400
return jsonify(
{
"total": f.total,
"platforms": f.platforms,
"untagged": f.untagged,
"no_artist": f.no_artist,
"date_min": f.date_min.isoformat() if f.date_min else None,
"date_max": f.date_max.isoformat() if f.date_max else None,
}
)
@gallery_bp.route("/jump", methods=["GET"])
async def jump():
try:
year = int(request.args["year"])
month = int(request.args["month"])
filters, sort = _parse_filters()
except (KeyError, ValueError):
return jsonify({"error": "year and month query params required"}), 400
async with get_session() as session:
svc = GalleryService(session)
try:
cursor = await svc.jump_cursor(
year=year, month=month, sort=sort, **filters,
)
except ValueError as exc:
return jsonify({"error": str(exc)}), 400
return jsonify({"cursor": cursor})
@gallery_bp.route("/image/<int:image_id>", methods=["GET"])
async def image_detail(image_id: int):
async with get_session() as session:
svc = GalleryService(session)
payload = await svc.get_image_with_tags(image_id)
if payload is None:
return jsonify({"error": "not found"}), 404
return jsonify(payload)