app/config.py

"""Configuration settings for the inference API."""

from functools import lru_cache

from pydantic_settings import BaseSettings


class Settings(BaseSettings):
    """Application settings loaded from environment variables."""

    model_name: str = "distilbert-base-uncased-finetuned-sst-2-english"
    task: str = "text-classification"
    host: str = "0.0.0.0"
    port: int = 8000
    max_batch_size: int = 32
    device: str = "cpu"

    # HF Inference API settings
    use_api: bool = True  # True = use HF API, False = load model locally
    api_token: str | None = None  # HF API token (required if use_api=True)

    class Config:
        env_file = ".env"
        env_prefix = "HF_"


@lru_cache
def get_settings() -> Settings:
    """Get cached settings instance."""
    return Settings()