feat：在docker中集成mineru，并且修正下载文件名不正确的问题

backend/Dockerfile

@@ -6,14 +6,21 @@ WORKDIR /app
 RUN apt-get update && apt-get install -y \
     build-essential \
     libreoffice \
+    wget \
     && rm -rf /var/lib/apt/lists/*
 
 
 # Copy requirements first to leverage Docker cache
 COPY requirements.txt .
+RUN pip install huggingface_hub
+RUN wget https://github.com/opendatalab/MinerU/raw/master/scripts/download_models_hf.py -O download_models_hf.py
+RUN python download_models_hf.py
+
+
 RUN pip install --no-cache-dir -r requirements.txt
 RUN pip install -U magic-pdf[full]
 
+
 # Copy the rest of the application
 COPY . .
 

backend/app/api/endpoints/files.py

@@ -10,6 +10,7 @@ from ...services.file_service import process_file
 from ...schemas.file import FileResponse as FileResponseSchema, FileList
 import asyncio
 from fastapi import WebSocketDisconnect
+import uuid
 
 router = APIRouter()
 
@@ -27,14 +28,20 @@ async def upload_file(
             detail=f"File type not allowed. Allowed types: {', '.join(settings.ALLOWED_EXTENSIONS)}"
         )
     
-    # Save file
-    file_path = settings.UPLOAD_FOLDER / file.filename
+    # Generate unique file ID
+    file_id = str(uuid.uuid4())
+    file_extension = os.path.splitext(file.filename)[1]
+    unique_filename = f"{file_id}{file_extension}"
+    
+    # Save file with unique name
+    file_path = settings.UPLOAD_FOLDER / unique_filename
     with open(file_path, "wb") as buffer:
         content = await file.read()
         buffer.write(content)
     
     # Create database entry
     db_file = FileModel(
+        id=file_id,
         filename=file.filename,
         original_path=str(file_path),
         status=FileStatus.NOT_STARTED

backend/app/services/file_service.py

@@ -31,9 +31,8 @@ def process_file(file_id: str):
             # Process the file using your existing masking system
             process_service = DocumentService()
             
-            # Determine output path
-            input_path = Path(file.original_path)
-            output_filename = f"processed_{input_path.name}"
+            # Determine output path using file_id with .md extension
+            output_filename = f"{file_id}.md"
             output_path = str(settings.PROCESSED_FOLDER / output_filename)
             
             # Process document with both input and output paths