fix: refact logic

app/core/config.py

@@ -5,6 +5,7 @@ from pathlib import Path
 
 from pydantic_settings import BaseSettings, SettingsConfigDict
 import torch
+from typing import Optional
 
 
 class Settings(BaseSettings):
@@ -21,11 +22,10 @@ class Settings(BaseSettings):
     debug: bool = False
 
     # PaddleOCR-VL Settings
-    paddleocr_vl_url: str = "http://localhost:8080/v1"
+    paddleocr_vl_url: str = "http://127.0.0.1:8000/v1"
 
     # Model Paths
-    doclayout_model_path: str = "app/model/DocLayout/best.pt"
-    pp_doclayout_model_dir: str = "app/model/PP-DocLayout/PP-DocLayoutV2"
+    pp_doclayout_model_dir: Optional[str] = "/home/yoge/.cache/modelscope/hub/models/PaddlePaddle/PP-DocLayoutV2"
 
     # Image Processing
     max_image_size_mb: int = 10
@@ -37,11 +37,6 @@ class Settings(BaseSettings):
     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."""

app/core/dependencies.py

@@ -3,20 +3,20 @@
 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
+from app.services.converter import Converter
+from app.core.config import get_settings
 
 # Global instances (initialized on startup)
 _layout_detector: LayoutDetector | None = None
 
 
-def init_layout_detector(model_path: str) -> None:
+def init_layout_detector() -> None:
     """Initialize the global layout detector.
 
     Called during application startup.
     """
     global _layout_detector
-    _layout_detector = LayoutDetector(model_path=model_path)
-    _layout_detector.load_model()
+    _layout_detector = LayoutDetector()
 
 
 def get_layout_detector() -> LayoutDetector:
@@ -33,10 +33,15 @@ def get_image_processor() -> ImageProcessor:
 
 def get_ocr_service() -> OCRService:
     """Get an OCR service instance."""
-    return OCRService()
+    return OCRService(
+        vl_server_url=get_settings().paddleocr_vl_url,
+        layout_detector=get_layout_detector(),
+        image_processor=get_image_processor(),
+        converter=get_converter(),
+    )
 
 
-def get_docx_converter() -> DocxConverter:
+def get_converter() -> Converter:
     """Get a DOCX converter instance."""
-    return DocxConverter()
+    return Converter()