doc_processer/app/core/config.py

"""Application configuration using Pydantic Settings."""

from functools import lru_cache
from pathlib import Path

from pydantic_settings import BaseSettings, SettingsConfigDict
import torch
from typing import Optional


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

    model_config = SettingsConfigDict(
        env_file=".env",
        env_file_encoding="utf-8",
        case_sensitive=False,
    )

    # API Settings
    api_prefix: str = "/doc_process/v1"
    debug: bool = False

    # PaddleOCR-VL Settings
    paddleocr_vl_url: str = "http://127.0.0.1:8000/v1"
    
    # MinerOCR Settings
    miner_ocr_api_url: str = "http://127.0.0.1:8000/file_parse"

    # Model Paths
    pp_doclayout_model_dir: Optional[str] = "/home/yoge/.cache/modelscope/hub/models/PaddlePaddle/PP-DocLayoutV2"

    # Image Processing
    max_image_size_mb: int = 10
    image_padding_ratio: float = 0.15  # 15% on each side = 30% total expansion

    device: torch.device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")  # cuda:0 or cpu

    # Server Settings
    host: str = "0.0.0.0"
    port: int = 8053

    @property
    def pp_doclayout_dir(self) -> Path:
        """Get the PP-DocLayout model directory path."""
        return Path(self.pp_doclayout_model_dir)


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