Update file_conversion.py

file_conversion.py

@@ -1,4 +1,4 @@
-from fastapi import APIRouter, UploadFile, File, HTTPException
+from fastapi import APIRouter, UploadFile, File, HTTPException, BackgroundTasks
 from fastapi.responses import FileResponse
 from pdf2docx import Converter
 import os
@@ -14,8 +14,13 @@ logger = logging.getLogger(__name__)
 # Define the temp directory
 TEMP_DIR = "/.tempfiles"
 
+def remove_file(path: str):
+    if os.path.exists(path):
+        os.unlink(path)
+        logger.info(f"Removed temporary file: {path}")
+
 @router.post("/convert/pdf_to_docx")
-async def convert_pdf_to_docx(file: UploadFile = File(...)):
+async def convert_pdf_to_docx(file: UploadFile = File(...), background_tasks: BackgroundTasks):
     if not file.filename.endswith('.pdf'):
         raise HTTPException(status_code=400, detail="File must be a PDF")
 
@@ -43,6 +48,10 @@ async def convert_pdf_to_docx(file: UploadFile = File(...)):
         if not os.path.exists(docx_temp_path):
             raise FileNotFoundError(f"Converted file not found: {docx_temp_path}")
 
+        # Schedule file removal after response is sent
+        background_tasks.add_task(remove_file, pdf_temp_path)
+        background_tasks.add_task(remove_file, docx_temp_path)
+
         # Return the DOCX file
         return FileResponse(
             docx_temp_path,
@@ -51,10 +60,7 @@ async def convert_pdf_to_docx(file: UploadFile = File(...)):
         )
     except Exception as e:
         logger.error(f"Conversion failed: {str(e)}")
-        raise HTTPException(status_code=500, detail=f"Conversion failed: {str(e)}")
-    finally:
-        # Clean up temporary files
-        if os.path.exists(pdf_temp_path):
-            os.unlink(pdf_temp_path)
-        if os.path.exists(docx_temp_path):
-            os.unlink(docx_temp_path)
+        # Clean up files in case of an error
+        remove_file(pdf_temp_path)
+        remove_file(docx_temp_path)
+        raise HTTPException(status_code=500, detail=f"Conversion failed: {str(e)}")