app/config.py

from functools import lru_cache
from os import getenv


DEFAULT_MODEL_NAME = "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2"
DEFAULT_DIMENSION = 384


def _read_int(name: str, default: int, minimum: int, maximum: int) -> int:
    raw_value = getenv(name)
    if raw_value is None or raw_value.strip() == "":
        return default

    try:
        value = int(raw_value)
    except ValueError as exc:
        raise RuntimeError(f"{name} must be an integer") from exc

    if value < minimum or value > maximum:
        raise RuntimeError(f"{name} must be between {minimum} and {maximum}")

    return value


class Settings:
    def __init__(self) -> None:
        self.model_name = getenv("MODEL_NAME", DEFAULT_MODEL_NAME)
        self.api_key = getenv("EMBEDDING_API_KEY")
        self.max_text_length = _read_int("MAX_TEXT_LENGTH", 3000, 1, 100_000)
        self.max_batch_size = _read_int("MAX_BATCH_SIZE", 64, 1, 512)
        self.dimension = DEFAULT_DIMENSION


@lru_cache
def get_settings() -> Settings:
    return Settings()