src/config/config.py

from typing import Optional
# from pydantic import BaseSettings
from pydantic_settings import BaseSettings
import os
from dotenv import load_dotenv

# Load environment variables from .env file
load_dotenv()


class Settings(BaseSettings):
    """Configuration settings for the application."""
    
    # API Keys - will be loaded from environment variables
    groq_api_key: str = os.getenv("GROQ_API_KEY")
    groq_base_url: str = os.getenv("GROQ_BASE_URL", "https://api.groq.com/openai/v1")
    
    huggingface_api_key: str = os.getenv("HUGGINGFACE_API_KEY")
    huggingface_provider: str = os.getenv("HUGGINGFACE_PROVIDER", "novita")
    
    # Model configurations
    llm_model: str = os.getenv("LLM_MODEL", "llama-3.1-8b-instant")
    
    # OCR and processing settings
    y_threshold: float = float(os.getenv("Y_THRESHOLD", "3.0"))
    gap_threshold: int = int(os.getenv("GAP_THRESHOLD", "10"))
    gap_threshold_ratio: float = float(os.getenv("GAP_THRESHOLD_RATIO", "0.1"))
    
    # File processing settings
    temp_file_name: str = os.getenv("TEMP_FILE_NAME", "/app/temp/temp.pdf")
    dpi: int = int(os.getenv("DPI", "300"))
    
    # spaCy model settings
    spacy_model_name: str = os.getenv("SPACY_MODEL_NAME", "en_core_web_sm")
    
    # Device settings
    force_cpu: bool = os.getenv("FORCE_CPU", "false").lower() == "true"
    
    class Config:
        env_file = ".env"
        env_file_encoding = "utf-8"
        case_sensitive = False


# Global settings instance
settings = Settings()