bvandeusen/FabledCurator
1
0
Fork 0
Code Issues 1 Pull Requests Actions Packages Projects Releases 35 Wiki Activity

feat(fc2b): schema migration 0003 — ML pipeline tables

Browse Source 
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>
This commit is contained in:
Bryan Van Deusen
2026-05-15 07:35:22 -04:00
parent aa9705882f
commit 906804140c
9 changed files with 380 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/app/models/image_record.py
+2 -2
View File
@@ -56,8 +56,8 @@ class ImageRecord(Base):
)
# ML fields (populated by FC-2's ml-worker)
wd14_predictions: Mapped[dict | None] = mapped_column(JSON, nullable=True)
wd14_model_version: Mapped[str | None] = mapped_column(String(128), nullable=True)
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)