feat(fc2b): add CentroidService — per-tag SigLIP centroids + similarity

recompute_for_tag (mean of member embeddings, eligible-kind + min-refs
gated, upsert), list_drifted (the delta-gate: member-count mismatch OR
missing OR wrong model version), find_similar_tags (pgvector cosine
distance, similarity = 1 - distance). Tests marked integration.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-15 07:37:53 -04:00
parent 03c6a61673
commit dfa67d6437
2 changed files with 260 additions and 0 deletions
+148
View File
@@ -0,0 +1,148 @@
"""Tag centroids: the mean SigLIP embedding of a tag's member images.
Powers centroid-augmented suggestions (a tag whose centroid is close to an
image's embedding becomes a suggestion even if Camie didn't predict it).
"""
from dataclasses import dataclass
import numpy as np
from sqlalchemy import func, select
from sqlalchemy.dialects.postgresql import insert
from sqlalchemy.ext.asyncio import AsyncSession
from ...models import (
ImageRecord,
MLSettings,
Tag,
TagKind,
TagReferenceEmbedding,
)
from ...models.tag import image_tag
from .embedder import MODEL_VERSION as SIGLIP_VERSION
ELIGIBLE_KINDS = {
TagKind.character,
TagKind.artist,
TagKind.fandom,
TagKind.general,
TagKind.series,
}
@dataclass(frozen=True)
class CentroidHit:
tag_id: int
similarity: float
class CentroidService:
def __init__(self, session: AsyncSession):
self.session = session
async def _min_reference_images(self) -> int:
return (
await self.session.execute(
select(MLSettings.min_reference_images).where(MLSettings.id == 1)
)
).scalar_one()
async def recompute_for_tag(self, tag_id: int) -> bool:
"""Recompute one tag's centroid. Returns True if a centroid was
written, False if skipped (ineligible kind or too few members)."""
tag = await self.session.get(Tag, tag_id)
if tag is None or tag.kind not in ELIGIBLE_KINDS:
return False
min_refs = await self._min_reference_images()
stmt = (
select(ImageRecord.siglip_embedding)
.join(image_tag, image_tag.c.image_record_id == ImageRecord.id)
.where(image_tag.c.tag_id == tag_id)
.where(ImageRecord.siglip_embedding.is_not(None))
)
embeddings = [
np.array(e, dtype=np.float32)
for e in (await self.session.execute(stmt)).scalars().all()
]
if len(embeddings) < min_refs:
return False
centroid = np.mean(np.stack(embeddings), axis=0).astype(np.float32)
stmt = insert(TagReferenceEmbedding).values(
tag_id=tag_id,
embedding=centroid.tolist(),
reference_count=len(embeddings),
model_version=SIGLIP_VERSION,
)
stmt = stmt.on_conflict_do_update(
index_elements=["tag_id"],
set_={
"embedding": centroid.tolist(),
"reference_count": len(embeddings),
"model_version": SIGLIP_VERSION,
"updated_at": func.now(),
},
)
await self.session.execute(stmt)
return True
async def list_drifted(self) -> list[int]:
"""Tag ids whose centroid is stale: member count != reference_count,
OR no centroid row, OR centroid built on a different SigLIP version.
Only considers eligible-kind tags with embeddings present."""
member_counts = (
select(
image_tag.c.tag_id.label("tag_id"),
func.count(image_tag.c.image_record_id).label("members"),
)
.join(ImageRecord, ImageRecord.id == image_tag.c.image_record_id)
.where(ImageRecord.siglip_embedding.is_not(None))
.group_by(image_tag.c.tag_id)
.subquery()
)
stmt = (
select(Tag.id)
.join(member_counts, member_counts.c.tag_id == Tag.id)
.outerjoin(
TagReferenceEmbedding,
TagReferenceEmbedding.tag_id == Tag.id,
)
.where(Tag.kind.in_(ELIGIBLE_KINDS))
.where(
(TagReferenceEmbedding.tag_id.is_(None))
| (
TagReferenceEmbedding.reference_count
!= member_counts.c.members
)
| (TagReferenceEmbedding.model_version != SIGLIP_VERSION)
)
)
return list((await self.session.execute(stmt)).scalars().all())
async def find_similar_tags(
self, image_id: int, limit: int = 20
) -> list[CentroidHit]:
"""Cosine similarity between an image's embedding and stored
centroids. Returns top-`limit` by similarity DESC. pgvector's
cosine_distance gives 1 - cosine_similarity."""
img = await self.session.get(ImageRecord, image_id)
if img is None or img.siglip_embedding is None:
return []
emb = img.siglip_embedding
distance = TagReferenceEmbedding.embedding.cosine_distance(emb)
stmt = (
select(
TagReferenceEmbedding.tag_id,
(1 - distance).label("similarity"),
)
.order_by(distance.asc())
.limit(limit)
)
rows = (await self.session.execute(stmt)).all()
return [
CentroidHit(tag_id=r.tag_id, similarity=float(r.similarity))
for r in rows
]
+112
View File
@@ -0,0 +1,112 @@
import numpy as np
import pytest
from backend.app.models import ImageRecord, TagKind
from backend.app.models.tag import image_tag
from backend.app.services.ml.centroids import CentroidService
from backend.app.services.tag_service import TagService
pytestmark = pytest.mark.integration
def _img(sha: str, embedding: list[float] | None) -> ImageRecord:
return ImageRecord(
path=f"/images/{sha}.jpg",
sha256=sha,
size_bytes=1,
mime="image/jpeg",
width=1,
height=1,
origin="imported_filesystem",
integrity_status="unknown",
siglip_embedding=embedding,
)
async def _attach(db, image_id: int, tag_id: int):
await db.execute(
image_tag.insert().values(
image_record_id=image_id, tag_id=tag_id, source="manual"
)
)
@pytest.mark.asyncio
async def test_recompute_skips_too_few_members(db):
tags = TagService(db)
tag = await tags.find_or_create("Lonely", TagKind.character)
img = _img("a" * 64, [0.1] * 1152)
db.add(img)
await db.flush()
await _attach(db, img.id, tag.id)
svc = CentroidService(db)
assert await svc.recompute_for_tag(tag.id) is False
@pytest.mark.asyncio
async def test_recompute_writes_centroid(db):
tags = TagService(db)
tag = await tags.find_or_create("Popular", TagKind.character)
for i in range(5):
img = _img(f"{i:064d}", [float(i)] * 1152)
db.add(img)
await db.flush()
await _attach(db, img.id, tag.id)
svc = CentroidService(db)
assert await svc.recompute_for_tag(tag.id) is True
from backend.app.models import TagReferenceEmbedding
cen = await db.get(TagReferenceEmbedding, tag.id)
assert cen is not None
assert cen.reference_count == 5
assert abs(np.array(cen.embedding)[0] - 2.0) < 1e-4
@pytest.mark.asyncio
async def test_recompute_skips_ineligible_kind(db):
tags = TagService(db)
tag = await tags.find_or_create("somearchive", TagKind.archive)
for i in range(5):
img = _img(f"arch{i:060d}", [1.0] * 1152)
db.add(img)
await db.flush()
await _attach(db, img.id, tag.id)
svc = CentroidService(db)
assert await svc.recompute_for_tag(tag.id) is False
@pytest.mark.asyncio
async def test_list_drifted_includes_uncomputed(db):
tags = TagService(db)
tag = await tags.find_or_create("Drifty", TagKind.character)
for i in range(5):
img = _img(f"d{i:063d}", [0.5] * 1152)
db.add(img)
await db.flush()
await _attach(db, img.id, tag.id)
svc = CentroidService(db)
drifted = await svc.list_drifted()
assert tag.id in drifted
@pytest.mark.asyncio
async def test_find_similar_tags(db):
tags = TagService(db)
tag = await tags.find_or_create("SimTag", TagKind.character)
for i in range(5):
img = _img(f"s{i:063d}", [1.0] * 1152)
db.add(img)
await db.flush()
await _attach(db, img.id, tag.id)
svc = CentroidService(db)
await svc.recompute_for_tag(tag.id)
query_img = _img("q" * 64, [1.0] * 1152)
db.add(query_img)
await db.flush()
hits = await svc.find_similar_tags(query_img.id, limit=10)
assert any(h.tag_id == tag.id for h in hits)
sim = next(h.similarity for h in hits if h.tag_id == tag.id)
assert sim > 0.99