Files
FabledCurator/alembic/versions/0069_default_siglip2.py
T
bvandeusen 6959e1220c Revert "db: collapse alembic 0001..0087 into one baseline"
This reverts 2529b51. Not a retreat — a reordering, on the operator's
call, and the better sequence.

The squash's acceptance test (run 4971) found ~130 places where the ORM
models do not describe the deployed schema (#3275), including a
unique=True the database never had and two UNIQUE indexes that exist
only in migrations. Collapsing now would have baked all of that into the
one file a public installer starts from.

So: fix the drift first as ordinary migrations on the intact chain, let
the operator deploy so their database moves to the corrected head, and
only then collapse. The baseline is then generated from reconciled
models and reproduces a schema worth reproducing.

Nothing is lost by reverting. The baseline was never deployed, and
regenerating it after the fixes is strictly better than patching this
copy — it will come out of autogenerate correct rather than needing the
same hand-finishing twice.
2026-08-30 14:34:28 -04:00

52 lines
1.7 KiB
Python

"""default the embedder to SigLIP 2 — for FRESH installs only (#1203)
Make SigLIP 2 (so400m, 512px; a 1152-d drop-in) the default embedder. New
installs start on it. An EXISTING library is NOT touched: flipping its stored
embedder version would mark every embedding stale (the scorer is version-gated)
and kill suggestions until a full re-embed+retrain — so an existing instance
switches deliberately via Settings → GPU agent → Embedding model → Re-embed →
Retrain. We detect "fresh" by the absence of any embedded image.
Revision ID: 0069
Revises: 0068
Create Date: 2026-06-30
"""
from typing import Sequence, Union
from alembic import op
revision: str = "0069"
down_revision: Union[str, None] = "0068"
branch_labels: Union[str, Sequence[str], None] = None
depends_on: Union[str, Sequence[str], None] = None
_NEW_NAME = "google/siglip2-so400m-patch16-512"
_NEW_VERSION = "siglip2-so400m-patch16-512"
_OLD_NAME = "google/siglip-so400m-patch14-384"
_OLD_VERSION = "siglip-so400m-patch14-384"
def upgrade() -> None:
# Fresh install (nothing embedded yet) → adopt SigLIP 2.
op.execute(
f"""
UPDATE ml_settings SET
embedder_model_name = '{_NEW_NAME}',
embedder_model_version = '{_NEW_VERSION}'
WHERE NOT EXISTS (
SELECT 1 FROM image_record WHERE siglip_embedding IS NOT NULL
)
"""
)
op.alter_column("ml_settings", "embedder_model_name", server_default=_NEW_NAME)
op.alter_column(
"ml_settings", "embedder_model_version", server_default=_NEW_VERSION
)
def downgrade() -> None:
op.alter_column("ml_settings", "embedder_model_name", server_default=_OLD_NAME)
op.alter_column(
"ml_settings", "embedder_model_version", server_default=_OLD_VERSION
)