"""Application configuration for imageO_v3.""" from __future__ import annotations import os from typing import Optional from pydantic import Field from pydantic_settings import BaseSettings, SettingsConfigDict # Cache defaults are set only when they are not already configured. os.environ.setdefault("XDG_CACHE_HOME", "/app/.cache") os.environ.setdefault("HF_HOME", "/app/.cache/huggingface") os.environ.setdefault("NUMBA_DISABLE_CACHE", "1") class Settings(BaseSettings): """Typed settings loaded from environment variables.""" model_config = SettingsConfigDict( env_file=".env", env_file_encoding="utf-8", extra="ignore", ) app_env: str = Field(default="development", description="Runtime environment") log_level: str = Field(default="INFO", description="Logger minimum level") model_version: str = Field(default="v3.2.0", description="Service model version") redis_url: str = Field(default="", description="Redis connection URL") hf_token: str = Field(default="", description="Hugging Face token for gated model access") replay_attack_ttl_s: int = Field(default=60, description="HMAC timestamp TTL") prediction_cache_ttl_s: int = Field(default=300, description="Prediction cache TTL") max_image_size_mb: int = Field(default=3, description="Maximum upload size in MB") model_checkpoint_path: str = Field( default="", alias="MODEL_CHECKPOINT_PATH", description="Local path to ABMIL .pt when ABMIL_HF_REPO_ID is unset; ignored when Hub repo id is set", ) abmil_hf_repo_id: Optional[str] = Field( default="iamSubha16/milk_adulteration_abmil_prod", description="Hugging Face Hub repo id (e.g. org/private-repo). If set, ABMIL checkpoint is fetched via hf_hub_download.", ) abmil_hf_filename: str = Field( default="production_model_v3.pt", description=( "Checkpoint filename inside the Hub repo. This code targets the scale-aware hybrid-LSE " "ABMIL, so point this at the RETRAINED checkpoint; the old plain-attention _v2 file will " "not load under strict=True. Override via ABMIL_HF_FILENAME." ), ) abmil_hf_revision: Optional[str] = Field( default="main", description="Optional Hub revision: branch, tag, or commit SHA (pin in production)", ) abmil_hf_subfolder: Optional[str] = Field( default="", description="Optional folder inside the repo containing ABMIL_HF_FILENAME", ) abmil_hf_local_files_only: bool = Field( default=False, description="If true, Hub resolution uses only local HF cache (no network)", ) dinov3_model_id: str = Field( default="facebook/dinov3-vits16plus-pretrain-lvd1689m", description="Hugging Face model id for DINOv3 backbone", ) embedding_batch_size: int = Field( default=256, description="Batch size for tile embedding" ) embedding_device: Optional[str] = Field( default="cpu", description="Optional device override (cpu/cuda)", ) embedding_dtype: Optional[str] = Field( default="float32", description="Optional dtype for DINO model loading (auto/float16/float32/bfloat16)", ) dinov3_local_files_only: bool = Field( default=False, description="If true, do not fetch model files from Hugging Face", ) # --- Tiling / preprocessing (multi-scale; must match training extraction config) --- tile_sizes_raw: str = Field( default="", alias="TILE_SIZES", description="Comma-separated or JSON tile sizes, e.g. '128,64'. Empty falls back to TILE_SIZE, then [128, 64].", ) tile_size_legacy: str = Field( default="", alias="TILE_SIZE", description="Legacy single tile size; used only when TILE_SIZES is unset.", ) tile_overlap_ratio: float = Field(default=0.25, description="Preprocessing tile overlap ratio") tile_shrink_factor: float = Field(default=0.85, description="ROI shrink factor") tile_min_mask_coverage: float = Field( default=0.8, ge=0.0, le=1.0, description="Minimum fraction of tile pixels inside ROI mask to accept the tile", ) # ROI Hough-circle detection knobs (defaults match milk_adulteration_mil ROIConfig). roi_dp: float = Field(default=1.2, description="HoughCircles inverse accumulator resolution") roi_param1: float = Field(default=60.0, description="HoughCircles Canny high threshold") roi_param2: float = Field(default=35.0, description="HoughCircles accumulator threshold") roi_min_radius_frac: float = Field(default=0.25, description="Min circle radius as fraction of min(h, w)") roi_max_radius_frac: float = Field(default=0.75, description="Max circle radius as fraction of min(h, w)") roi_median_blur_ksize: int = Field(default=7, description="Median blur kernel size before Hough transform") roi_fallback_margin_frac: float = Field( default=0.10, description="Center-crop margin fraction used when no circle is detected", ) # Optional tile-quality gates (DISABLED by default to match current training extraction). tile_variance_gate_enabled: bool = Field( default=False, description="If true, reject tiles whose grayscale variance < tile_min_variance", ) tile_min_variance: float = Field(default=50.0, description="Min grayscale variance when variance gate enabled") tile_highlight_gate_enabled: bool = Field( default=False, description="If true, reject tiles whose specular-highlight fraction > tile_max_highlight_frac", ) tile_highlight_thresh: int = Field(default=235, description="Grayscale value above which a pixel is a highlight") tile_max_highlight_frac: float = Field( default=0.40, description="Max fraction of highlight pixels when highlight gate enabled", ) abmil_attn_dim: int = Field(default=256, description="Fallback ABMIL attention dimension") abmil_classifier_hidden: int = Field( default=256, description="Fallback ABMIL classifier hidden size", ) abmil_attn_hidden: int = Field(default=128, description="Fallback gated attention hidden size") abmil_dropout: float = Field(default=0.40, description="Fallback ABMIL dropout") abmil_threshold: float = Field(default=0.35, description="Fallback positive class threshold") abmil_scale_embed_dim: int = Field( default=16, description="Scale-embedding dim for MultiScaleEmbeddingProjector (0 disables); inferred from checkpoint when possible", ) abmil_num_scales: int = Field( default=3, description="Number of tile-scale buckets in the scale-embedding table; inferred from checkpoint when possible", ) abmil_lse_r: float = Field( default=5.0, description="LSE pooling sharpness r; not stored in the checkpoint, so must match the training default", ) @property def tile_sizes(self) -> list[int]: """Resolved multi-scale tile sizes (TILE_SIZES wins, then legacy TILE_SIZE, then [128, 64]).""" raw = (self.tile_sizes_raw or "").strip() if raw: if raw.startswith("["): import json return [int(x) for x in json.loads(raw)] return [int(x.strip()) for x in raw.split(",") if x.strip()] legacy = (self.tile_size_legacy or "").strip() if legacy: return [int(legacy)] return [128, 64] settings = Settings()