feat(backend): 更新核心模块和文件处理

- 更新配置模块 (config.py)
- 更新数据库连接 (database.py)
- 更新主应用入口 (main.py)
- 更新数据模型 (models.py)
- 更新基础 Schema (base.py)
- 更新文件处理器 (docx, excel, pdf)
- 更新 Dockerfile

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

backend/app/services/file_processor/pdf_processor.py

@@ -1,8 +1,9 @@
 """
 PDF Text Extractor
 """
+import asyncio
+from typing import Dict, List
 import pdfplumber
-from typing import Dict, List, Optional
 
 
 class PDFProcessor:
@@ -20,6 +21,12 @@ class PDFProcessor:
 
         return "\n\n".join(text_parts)
 
+    async def extract_text_async(self, file_path: str) -> str:
+        """Extract all text from PDF asynchronously"""
+        return await asyncio.get_event_loop().run_in_executor(
+            None, self.extract_text, file_path
+        )
+
     def extract_pages(self, file_path: str) -> List[Dict]:
         """Extract text page by page with metadata"""
         pages = []
@@ -36,6 +43,12 @@ class PDFProcessor:
 
         return pages
 
+    async def extract_pages_async(self, file_path: str) -> List[Dict]:
+        """Extract pages asynchronously"""
+        return await asyncio.get_event_loop().run_in_executor(
+            None, self.extract_pages, file_path
+        )
+
     def extract_with_metadata(self, file_path: str) -> Dict:
         """Extract text with PDF metadata"""
         result = {
@@ -58,8 +71,14 @@ class PDFProcessor:
 
         return result
 
+    async def extract_with_metadata_async(self, file_path: str) -> Dict:
+        """Extract with metadata asynchronously"""
+        return await asyncio.get_event_loop().run_in_executor(
+            None, self.extract_with_metadata, file_path
+        )
 
-def process_pdf(file_path: str) -> str:
+
+async def process_pdf(file_path: str) -> str:
     """Process PDF file and return text"""
     processor = PDFProcessor()
-    return processor.extract_with_metadata(file_path)["text"]
+    return await processor.extract_with_metadata_async(file_path)