From 931fafa4032aeb9c0a74e3038cd8d196dfe20858 Mon Sep 17 00:00:00 2001
From: "MSI\\ModSetter" <vermarohanfinal@gmail.com>
Date: Mon, 21 Jul 2025 06:19:37 -0700
Subject: [PATCH] refactor: Remove deprecated document processing services and
 update imports

- Deleted the document_processing module and its associated docling_service.
- Updated imports in documents_routes.py and background_tasks.py to reflect the new service structure.
- Ensured compatibility with the task logging system by adjusting type hints for log entries.
---
 surfsense_backend/app/routes/documents_routes.py       | 10 ++++++----
 .../{document_processing => }/docling_service.py       |  0
 .../app/services/document_processing/__init__.py       |  1 -
 surfsense_backend/app/tasks/background_tasks.py        |  2 +-
 4 files changed, 7 insertions(+), 6 deletions(-)
 rename surfsense_backend/app/services/{document_processing => }/docling_service.py (100%)
 delete mode 100644 surfsense_backend/app/services/document_processing/__init__.py

diff --git a/surfsense_backend/app/routes/documents_routes.py b/surfsense_backend/app/routes/documents_routes.py
index 5c2a0a0..4d3e852 100644
--- a/surfsense_backend/app/routes/documents_routes.py
+++ b/surfsense_backend/app/routes/documents_routes.py
@@ -3,7 +3,7 @@ from fastapi import APIRouter, Depends, BackgroundTasks, UploadFile, Form, HTTPE
 from sqlalchemy.ext.asyncio import AsyncSession
 from sqlalchemy.future import select
 from typing import List
-from app.db import get_async_session, User, SearchSpace, Document, DocumentType
+from app.db import Log, get_async_session, User, SearchSpace, Document, DocumentType
 from app.schemas import DocumentsCreate, DocumentUpdate, DocumentRead
 from app.users import current_active_user
 from app.utils.check_ownership import check_ownership
@@ -11,6 +11,8 @@ from app.tasks.background_tasks import add_received_markdown_file_document, add_
 from app.config import config as app_config
 # Force asyncio to use standard event loop before unstructured imports
 import asyncio
+
+from surfsense_backend.app.services.task_logging_service import TaskLoggingService
 try:
     asyncio.set_event_loop_policy(asyncio.DefaultEventLoopPolicy())
 except RuntimeError:
@@ -136,8 +138,8 @@ async def process_file_in_background(
     search_space_id: int,
     user_id: str,
     session: AsyncSession,
-    task_logger: 'TaskLoggingService',
-    log_entry: 'Log'
+    task_logger: TaskLoggingService,
+    log_entry: Log
 ):
     try:
         # Check if the file is a markdown or text file
@@ -383,7 +385,7 @@ async def process_file_in_background(
                 )
                 
                 # Use Docling service for document processing
-                from app.services.document_processing.docling_service import create_docling_service
+                from app.services.docling_service import create_docling_service
                 
                 # Create Docling service
                 docling_service = create_docling_service()
diff --git a/surfsense_backend/app/services/document_processing/docling_service.py b/surfsense_backend/app/services/docling_service.py
similarity index 100%
rename from surfsense_backend/app/services/document_processing/docling_service.py
rename to surfsense_backend/app/services/docling_service.py
diff --git a/surfsense_backend/app/services/document_processing/__init__.py b/surfsense_backend/app/services/document_processing/__init__.py
deleted file mode 100644
index 0c86000..0000000
--- a/surfsense_backend/app/services/document_processing/__init__.py
+++ /dev/null
@@ -1 +0,0 @@
-# Document processing services for SurfSense
\ No newline at end of file
diff --git a/surfsense_backend/app/tasks/background_tasks.py b/surfsense_backend/app/tasks/background_tasks.py
index d405861..9599619 100644
--- a/surfsense_backend/app/tasks/background_tasks.py
+++ b/surfsense_backend/app/tasks/background_tasks.py
@@ -682,7 +682,7 @@ async def add_received_file_document_using_docling(
             raise RuntimeError(f"No long context LLM configured for user {user_id}")
 
         # Generate summary using chunked processing for large documents
-        from app.services.document_processing.docling_service import create_docling_service
+        from app.services.docling_service import create_docling_service
         docling_service = create_docling_service()
         
         summary_content = await docling_service.process_large_document_summary(