bvandeusen
625336b6b4
Live data showed the v1 flat 0.75 cosine over-fired — ~64% of matched images got
3-10 character guesses dominated by the most-referenced characters (a 27-ref
character clears a low bar on many images). A sweep showed 0.85 collapses the
noise (noisy multi-matches 47→3) while keeping the confident single-character
matches.
- ml_settings.ccip_match_threshold (migration 0063, default 0.85); match_image
reads it (override still accepted). DEFAULT_SIM_THRESHOLD fallback 0.75→0.85.
- Exposed in GET/PATCH /api/ml/settings (validated 0.5–0.999).
- Slider in the GPU agent card ("Character-match strictness") — tune live, no
redeploy, same observe-and-tune loop as auto-apply.
Test: a ~0.9-cosine figure matches at 0.85, dropped at 0.95.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa
104 lines
4.7 KiB
Python
104 lines
4.7 KiB
Python
"""MLSettings — single-row table holding ML pipeline tunables."""
|
||
|
||
from datetime import datetime
|
||
|
||
from sqlalchemy import (
|
||
Boolean,
|
||
CheckConstraint,
|
||
DateTime,
|
||
Float,
|
||
Integer,
|
||
String,
|
||
func,
|
||
)
|
||
from sqlalchemy.orm import Mapped, mapped_column
|
||
|
||
from .base import Base
|
||
|
||
|
||
class MLSettings(Base):
|
||
__tablename__ = "ml_settings"
|
||
# Bare name — Base.metadata's naming convention prepends ck_<table>_,
|
||
# producing the final ck_ml_settings_singleton (matches migration 0003).
|
||
__table_args__ = (CheckConstraint("id = 1", name="singleton"),)
|
||
|
||
id: Mapped[int] = mapped_column(Integer, primary_key=True)
|
||
suggestion_threshold_character: Mapped[float] = mapped_column(
|
||
Float, nullable=False, default=0.70
|
||
)
|
||
# Default raised 0.50 → 0.70 on 2026-06-02 — operator-flagged 0.50
|
||
# surfaced too many low-confidence picks; 0.70 keeps the rail
|
||
# signal-rich while still surfacing more than the original 0.95
|
||
# which hid almost everything. Operator-tunable via Settings → ML.
|
||
suggestion_threshold_general: Mapped[float] = mapped_column(
|
||
Float, nullable=False, default=0.70
|
||
)
|
||
centroid_similarity_threshold: Mapped[float] = mapped_column(
|
||
Float, nullable=False, default=0.55
|
||
)
|
||
# Ingest floor: tagger predictions below this confidence are not stored
|
||
# (tagger.Tagger.infer). Default 0.70 — the suggestion path already
|
||
# filters at 0.70 and the centroid/learned path covers low-confidence
|
||
# preferred tags, so the sub-0.70 tail is redundant weight (it had
|
||
# bloated image_record's TOAST to ~100 GB; plan-task #764). Operator-
|
||
# tunable via Settings → ML; must stay ≤ the suggestion thresholds.
|
||
tagger_store_floor: Mapped[float] = mapped_column(
|
||
Float, nullable=False, default=0.70
|
||
)
|
||
min_reference_images: Mapped[int] = mapped_column(
|
||
Integer, nullable=False, default=5
|
||
)
|
||
# Video tagging (#747). Sample one frame every N seconds (fixed CADENCE, not a
|
||
# fixed count) so a tag's frame-presence reflects real screen time regardless
|
||
# of video length; cap the total so a long video can't explode into hundreds
|
||
# of inferences (the cadence stretches past the cap). A tag is kept only if it
|
||
# appears in >= video_min_tag_frames sampled frames (≈ that many × interval
|
||
# seconds on screen) — duration-independent noise rejection. Operator-tunable.
|
||
video_frame_interval_seconds: Mapped[float] = mapped_column(
|
||
Float, nullable=False, default=4.0
|
||
)
|
||
video_max_frames: Mapped[int] = mapped_column(
|
||
Integer, nullable=False, default=64
|
||
)
|
||
video_min_tag_frames: Mapped[int] = mapped_column(
|
||
Integer, nullable=False, default=3
|
||
)
|
||
# Tagging-v2 head training (#114). The head is the suggestion source that
|
||
# LEARNS from the operator's tags (replacing Camie + centroid). A concept
|
||
# needs >= head_min_positives labelled images before a head is trained;
|
||
# head_auto_apply_precision is the precision bar a head must clear (at some
|
||
# operating point) to "graduate" into earned auto-apply. Operator-tunable.
|
||
head_min_positives: Mapped[int] = mapped_column(
|
||
Integer, nullable=False, default=8
|
||
)
|
||
head_auto_apply_precision: Mapped[float] = mapped_column(
|
||
Float, nullable=False, default=0.97
|
||
)
|
||
# Earned auto-apply (#114). A graduated head fires (tags images without a
|
||
# human) when this master switch is on AND the head has at least
|
||
# head_auto_apply_min_positives clean labels — so a precise-looking but
|
||
# under-supported low-N head can't spray tags across the library. ON by
|
||
# default (operator-asked 2026-06-29: opt-OUT, not opt-in); the support +
|
||
# measured-precision gates keep it safe, and every auto-tag is reversible.
|
||
head_auto_apply_enabled: Mapped[bool] = mapped_column(
|
||
Boolean, nullable=False, default=True
|
||
)
|
||
head_auto_apply_min_positives: Mapped[int] = mapped_column(
|
||
Integer, nullable=False, default=30
|
||
)
|
||
# CCIP character-match cosine cut (#114). 0.85 default — the v1 flat 0.75
|
||
# over-fired (high-reference characters matched a scatter of images); 0.85
|
||
# keeps the confident single-character matches. Tunable from the agent card.
|
||
ccip_match_threshold: Mapped[float] = mapped_column(
|
||
Float, nullable=False, default=0.85
|
||
)
|
||
tagger_model_version: Mapped[str] = mapped_column(
|
||
String(128), nullable=False, default="camie-tagger-v2"
|
||
)
|
||
embedder_model_version: Mapped[str] = mapped_column(
|
||
String(128), nullable=False, default="siglip-so400m-patch14-384"
|
||
)
|
||
updated_at: Mapped[datetime] = mapped_column(
|
||
DateTime(timezone=True), nullable=False, server_default=func.now()
|
||
)
|