init repo

app/core/config.py

@@ -0,0 +1,52 @@
+"""Application configuration using Pydantic Settings."""
+
+from functools import lru_cache
+from pathlib import Path
+
+from pydantic_settings import BaseSettings, SettingsConfigDict
+
+
+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://localhost:8080/v1"
+
+    # Model Paths
+    doclayout_model_path: str = "app/model/DocLayout"
+    pp_doclayout_model_dir: str = "app/model/PP-DocLayout"
+
+    # Image Processing
+    max_image_size_mb: int = 10
+    image_padding_ratio: float = 0.15  # 15% on each side = 30% total expansion
+
+    # Server Settings
+    host: str = "0.0.0.0"
+    port: int = 8053
+
+    @property
+    def doclayout_model_file(self) -> Path:
+        """Get the DocLayout model file path."""
+        return Path(self.doclayout_model_path)
+
+    @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()
+

app/core/dependencies.py

@@ -0,0 +1,42 @@
+"""Application dependencies."""
+
+from app.services.image_processor import ImageProcessor
+from app.services.layout_detector import LayoutDetector
+from app.services.ocr_service import OCRService
+from app.services.docx_converter import DocxConverter
+
+# Global instances (initialized on startup)
+_layout_detector: LayoutDetector | None = None
+
+
+def init_layout_detector(model_path: str) -> None:
+    """Initialize the global layout detector.
+
+    Called during application startup.
+    """
+    global _layout_detector
+    _layout_detector = LayoutDetector(model_path=model_path)
+    _layout_detector.load_model()
+
+
+def get_layout_detector() -> LayoutDetector:
+    """Get the global layout detector instance."""
+    if _layout_detector is None:
+        raise RuntimeError("Layout detector not initialized. Call init_layout_detector() first.")
+    return _layout_detector
+
+
+def get_image_processor() -> ImageProcessor:
+    """Get an image processor instance."""
+    return ImageProcessor()
+
+
+def get_ocr_service() -> OCRService:
+    """Get an OCR service instance."""
+    return OCRService()
+
+
+def get_docx_converter() -> DocxConverter:
+    """Get a DOCX converter instance."""
+    return DocxConverter()
+