apunkt/SurfSense
1
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2026-04-26 09:16:22 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Implement KB sync after Notion page updates with block ID verification

Browse source 
- Add NotionKBSyncService for immediate KB updates after page changes
- Implement block ID verification to ensure content freshness
- Refactor duplicate block processing logic to shared utils
- Add user-friendly status messages
- Include debug logging for troubleshooting
This commit is contained in:
CREDO23 2026-02-17 20:30:12 +02:00
parent 2f65536c6d
commit 7d1bd1fab4
5 changed files with 150 additions and 58 deletions
Download patch file Download diff file Expand all files Collapse all files

48
surfsense_backend/app/tasks/connector_indexers/notion_indexer.py
View file

@ -24,6 +24,7 @@ from app.utils.document_converters import (
generate_document_summary,
generate_unique_identifier_hash,
)
from app.utils.notion_utils import process_blocks
from .base import (
build_document_metadata_string,
@ -280,53 +281,6 @@ async def index_notion_pages(
pages_to_process = [] # List of dicts with document and page data
new_documents_created = False
# Helper function to convert page content to markdown
def process_blocks(blocks, level=0):
result = ""
for block in blocks:
block_type = block.get("type")
block_content = block.get("content", "")
children = block.get("children", [])
# Add indentation based on level
indent = " " * level
# Format based on block type
if block_type in ["paragraph", "text"]:
result += f"{indent}{block_content}\n\n"
elif block_type in ["heading_1", "header"]:
result += f"{indent}# {block_content}\n\n"
elif block_type == "heading_2":
result += f"{indent}## {block_content}\n\n"
elif block_type == "heading_3":
result += f"{indent}### {block_content}\n\n"
elif block_type == "bulleted_list_item":
result += f"{indent}* {block_content}\n"
elif block_type == "numbered_list_item":
result += f"{indent}1. {block_content}\n"
elif block_type == "to_do":
result += f"{indent}- [ ] {block_content}\n"
elif block_type == "toggle":
result += f"{indent}> {block_content}\n"
elif block_type == "code":
result += f"{indent}```\n{block_content}\n```\n\n"
elif block_type == "quote":
result += f"{indent}> {block_content}\n\n"
elif block_type == "callout":
result += f"{indent}> **Note:** {block_content}\n\n"
elif block_type == "image":
result += f"{indent}![Image]({block_content})\n\n"
else:
# Default for other block types
if block_content:
result += f"{indent}{block_content}\n\n"
# Process children recursively
if children:
result += process_blocks(children, level + 1)
return result
for page in pages:
try:
page_id = page.get("page_id")