settings.py

# settings.py
import os

# Basic settings
SNAPSHOT_PATH = os.getenv("SNAPSHOT_PATH", "snapshot.json")
PERSIST_CONTENT = os.getenv("PERSIST_CONTENT", "false").lower() == "true"

# Healthcare-specific settings
HEALTHCARE_SETTINGS = {
    "phi_detection_enabled": True,
    "min_facility_count_for_aggregation": 10,
    "default_occupancy_threshold": 85.0,
    "bed_change_significance_threshold": 5.0,
    "supported_file_types": [".csv", ".xlsx", ".xls", ".json", ".parquet", ".pdf", ".docx", ".txt"],
    "healthcare_keywords": [
        "hospital", "patient", "bed", "care", "health", "medical", "clinical",
        "facility", "nursing", "residential", "ambulatory", "healthcare", "occupancy",
        "capacity", "staff", "zone", "province", "alberta", "cihi", "odhf",
        "respiratory", "virus", "flu", "surge", "acute", "long-term", "ltc"
    ],
    # Dynamic column patterns for detection
    "column_patterns": {
        "facility_name": ["facility", "name", "hospital", "site", "location"],
        "facility_type": ["type", "category", "class", "facility_type", "odhf_facility_type"],
        "beds_current": ["current", "2023", "2024", "beds_current", "staffed_beds", "capacity"],
        "beds_prev": ["prev", "previous", "2022", "beds_prev", "previous_beds"],
        "zone": ["zone", "region", "area", "district"],
        "province": ["province", "state", "territory"],
        "city": ["city", "municipality", "town"],
        "teaching_status": ["teaching", "status", "type", "hospital_type"]
    }
}

# Model settings
MODEL_SETTINGS = {
    "max_new_tokens": 2048,
    "temperature": 0.3,
    "top_p": 0.9,
    "repetition_penalty": 1.15
}

# Debug settings
DEBUG = os.getenv("DEBUG", "false").lower() == "true"