bvandeusen
906804140c
Renames image_record.wd14_* -> tagger_* (we're on Camie now, not WD14). Adds tag_allowlist (auto-apply opt-in, per-tag confidence), tag_suggestion_rejection (per-image dismissals), tag_alias (composite (string, category) -> canonical tag, resolved at read time), tag_reference_embedding (per-tag SigLIP centroids), and the ml_settings singleton (per-category + centroid thresholds, model version pins). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
78 lines
2.9 KiB
Python
78 lines
2.9 KiB
Python
"""ImageRecord — the gallery's primary entity, ported from ImageRepo.
|
|
|
|
ML fields and thumbnails are declared now (in FC-1) so FC-2 can populate them
|
|
without a schema migration. The SigLIP embedding column uses pgvector's Vector
|
|
type — pgvector extension is enabled in the initial migration.
|
|
"""
|
|
|
|
from datetime import datetime
|
|
|
|
from pgvector.sqlalchemy import Vector
|
|
from sqlalchemy import (
|
|
JSON,
|
|
BigInteger,
|
|
DateTime,
|
|
Enum,
|
|
ForeignKey,
|
|
Integer,
|
|
String,
|
|
Text,
|
|
func,
|
|
)
|
|
from sqlalchemy.orm import Mapped, mapped_column
|
|
|
|
from .base import Base
|
|
|
|
ORIGIN_CHOICES = ("downloaded", "imported_filesystem", "uploaded")
|
|
|
|
|
|
class ImageRecord(Base):
|
|
__tablename__ = "image_record"
|
|
|
|
id: Mapped[int] = mapped_column(Integer, primary_key=True)
|
|
|
|
# On-disk identity
|
|
path: Mapped[str] = mapped_column(Text, nullable=False, unique=True)
|
|
sha256: Mapped[str] = mapped_column(String(64), nullable=False, unique=True, index=True)
|
|
phash: Mapped[str | None] = mapped_column(String(32), nullable=True, index=True)
|
|
size_bytes: Mapped[int] = mapped_column(BigInteger, nullable=False)
|
|
mime: Mapped[str] = mapped_column(String(64), nullable=False)
|
|
width: Mapped[int | None] = mapped_column(Integer, nullable=True)
|
|
height: Mapped[int | None] = mapped_column(Integer, nullable=True)
|
|
|
|
# Integrity verification status. FC-2e populates this; FC-2a leaves rows at 'unknown'.
|
|
# Values: 'unknown' (default), 'ok', 'corrupt', 'failed_verification'.
|
|
integrity_status: Mapped[str] = mapped_column(
|
|
String(24), nullable=False, default="unknown", index=True
|
|
)
|
|
|
|
# Thumbnail (populated by FC-2)
|
|
thumbnail_path: Mapped[str | None] = mapped_column(Text, nullable=True)
|
|
|
|
# Origin / provenance pointers
|
|
origin: Mapped[str] = mapped_column(Enum(*ORIGIN_CHOICES, name="origin_enum"), nullable=False)
|
|
primary_post_id: Mapped[int | None] = mapped_column(
|
|
ForeignKey("post.id", ondelete="SET NULL"), nullable=True, index=True
|
|
)
|
|
|
|
# ML fields (populated by FC-2's ml-worker)
|
|
tagger_predictions: Mapped[dict | None] = mapped_column(JSON, nullable=True)
|
|
tagger_model_version: Mapped[str | None] = mapped_column(String(128), nullable=True)
|
|
# 1152 = SigLIP-so400m embedding dim. Swapping models in FC-2 may require
|
|
# a column-width migration.
|
|
siglip_embedding: Mapped[list[float] | None] = mapped_column(Vector(1152), nullable=True)
|
|
siglip_model_version: Mapped[str | None] = mapped_column(String(128), nullable=True)
|
|
|
|
# Centroid score cache (populated post-tagging)
|
|
centroid_scores: Mapped[dict | None] = mapped_column(JSON, nullable=True)
|
|
|
|
created_at: Mapped[datetime] = mapped_column(
|
|
DateTime(timezone=True), nullable=False, server_default=func.now()
|
|
)
|
|
updated_at: Mapped[datetime] = mapped_column(
|
|
DateTime(timezone=True),
|
|
nullable=False,
|
|
server_default=func.now(),
|
|
onupdate=func.now(),
|
|
)
|