mirror of
https://github.com/MODSetter/SurfSense.git
synced 2026-06-26 21:39:43 +02:00
chore: linting
This commit is contained in:
parent
0a012dbc79
commit
ce952d2ad1
127 changed files with 821 additions and 517 deletions
|
|
@ -9,8 +9,8 @@ from uuid import UUID
|
|||
|
||||
from app.celery_app import celery_app
|
||||
from app.config import config
|
||||
from app.observability import metrics as ot_metrics
|
||||
from app.notifications.service import NotificationService
|
||||
from app.observability import metrics as ot_metrics
|
||||
from app.services.task_logging_service import TaskLoggingService
|
||||
from app.tasks.celery_tasks import get_celery_session_maker, run_async_celery_task
|
||||
from app.tasks.connector_indexers.local_folder_indexer import (
|
||||
|
|
@ -1335,7 +1335,7 @@ async def _index_local_folder_async(
|
|||
exclude_patterns=exclude_patterns,
|
||||
file_extensions=file_extensions,
|
||||
root_folder_id=root_folder_id,
|
||||
target_file_paths=target_file_paths,
|
||||
target_file_paths=target_file_paths,
|
||||
on_heartbeat_callback=_heartbeat_progress
|
||||
if (is_batch or is_full_scan)
|
||||
else None,
|
||||
|
|
@ -1463,7 +1463,7 @@ async def _index_uploaded_folder_files_async(
|
|||
user_id=user_id,
|
||||
folder_name=folder_name,
|
||||
root_folder_id=root_folder_id,
|
||||
file_mappings=file_mappings,
|
||||
file_mappings=file_mappings,
|
||||
on_heartbeat_callback=_heartbeat_progress,
|
||||
use_vision_llm=use_vision_llm,
|
||||
processing_mode=processing_mode,
|
||||
|
|
|
|||
|
|
@ -46,7 +46,8 @@ def reconcile_inbox_task() -> None:
|
|||
result = await session.execute(
|
||||
update(ExternalChatInboundEvent)
|
||||
.where(
|
||||
ExternalChatInboundEvent.status == ExternalChatEventStatus.PROCESSING,
|
||||
ExternalChatInboundEvent.status
|
||||
== ExternalChatEventStatus.PROCESSING,
|
||||
ExternalChatInboundEvent.received_at < stale_threshold,
|
||||
)
|
||||
.values(
|
||||
|
|
@ -163,4 +164,3 @@ async def enqueue_telegram_update(account_id: int, raw_update: dict) -> int | No
|
|||
)
|
||||
await session.commit()
|
||||
return inbox_id
|
||||
|
||||
|
|
|
|||
|
|
@ -260,7 +260,7 @@ async def index_confluence_pages(
|
|||
connector_id=connector_id,
|
||||
search_space_id=search_space_id,
|
||||
user_id=user_id,
|
||||
)
|
||||
)
|
||||
|
||||
with session.no_autoflush:
|
||||
duplicate_by_content = await check_duplicate_document_by_hash(
|
||||
|
|
|
|||
|
|
@ -414,7 +414,7 @@ async def index_google_calendar_events(
|
|||
connector_id=connector_id,
|
||||
search_space_id=search_space_id,
|
||||
user_id=user_id,
|
||||
)
|
||||
)
|
||||
|
||||
with session.no_autoflush:
|
||||
duplicate = await check_duplicate_document_by_hash(
|
||||
|
|
|
|||
|
|
@ -552,7 +552,7 @@ async def _process_single_file(
|
|||
connector_id=connector_id,
|
||||
search_space_id=search_space_id,
|
||||
user_id=user_id,
|
||||
)
|
||||
)
|
||||
|
||||
pipeline = IndexingPipelineService(session)
|
||||
documents = await pipeline.prepare_for_indexing([doc])
|
||||
|
|
|
|||
|
|
@ -444,7 +444,7 @@ async def index_google_gmail_messages(
|
|||
connector_id=connector_id,
|
||||
search_space_id=search_space_id,
|
||||
user_id=user_id,
|
||||
)
|
||||
)
|
||||
|
||||
with session.no_autoflush:
|
||||
duplicate = await check_duplicate_document_by_hash(
|
||||
|
|
|
|||
|
|
@ -268,7 +268,7 @@ async def index_linear_issues(
|
|||
connector_id=connector_id,
|
||||
search_space_id=search_space_id,
|
||||
user_id=user_id,
|
||||
)
|
||||
)
|
||||
|
||||
with session.no_autoflush:
|
||||
duplicate = await check_duplicate_document_by_hash(
|
||||
|
|
|
|||
|
|
@ -568,7 +568,7 @@ async def index_local_folder(
|
|||
folder_path=folder_path,
|
||||
folder_name=folder_name,
|
||||
target_file_path=target_file_paths[0],
|
||||
root_folder_id=root_folder_id,
|
||||
root_folder_id=root_folder_id,
|
||||
task_logger=task_logger,
|
||||
log_entry=log_entry,
|
||||
)
|
||||
|
|
@ -580,7 +580,7 @@ async def index_local_folder(
|
|||
folder_path=folder_path,
|
||||
folder_name=folder_name,
|
||||
target_file_paths=target_file_paths,
|
||||
root_folder_id=root_folder_id,
|
||||
root_folder_id=root_folder_id,
|
||||
on_progress_callback=on_heartbeat_callback,
|
||||
)
|
||||
if err:
|
||||
|
|
@ -766,7 +766,7 @@ async def index_local_folder(
|
|||
folder_name=folder_name,
|
||||
search_space_id=search_space_id,
|
||||
user_id=user_id,
|
||||
)
|
||||
)
|
||||
connector_docs.append(doc)
|
||||
file_meta_map[unique_identifier] = {
|
||||
"relative_path": relative_path,
|
||||
|
|
@ -983,7 +983,7 @@ async def _index_batch_files(
|
|||
folder_path=folder_path,
|
||||
folder_name=folder_name,
|
||||
target_file_path=file_path,
|
||||
root_folder_id=root_folder_id,
|
||||
root_folder_id=root_folder_id,
|
||||
task_logger=task_logger,
|
||||
log_entry=log_entry,
|
||||
)
|
||||
|
|
@ -1111,7 +1111,7 @@ async def _index_single_file(
|
|||
folder_name=folder_name,
|
||||
search_space_id=search_space_id,
|
||||
user_id=user_id,
|
||||
)
|
||||
)
|
||||
|
||||
if root_folder_id:
|
||||
connector_doc.folder_id = await _resolve_folder_for_file(
|
||||
|
|
@ -1396,7 +1396,7 @@ async def index_uploaded_files(
|
|||
folder_name=folder_name,
|
||||
search_space_id=search_space_id,
|
||||
user_id=user_id,
|
||||
)
|
||||
)
|
||||
|
||||
connector_doc.folder_id = await _resolve_folder_for_file(
|
||||
session,
|
||||
|
|
|
|||
|
|
@ -440,9 +440,7 @@ async def index_luma_events(
|
|||
summary_content = (
|
||||
f"Luma Event: {item['event_name']}\n\n{item['event_markdown']}"
|
||||
)
|
||||
summary_embedding = await asyncio.to_thread(
|
||||
embed_text, summary_content
|
||||
)
|
||||
summary_embedding = await asyncio.to_thread(embed_text, summary_content)
|
||||
|
||||
chunks = await create_document_chunks(item["event_markdown"])
|
||||
|
||||
|
|
|
|||
|
|
@ -308,7 +308,7 @@ async def index_notion_pages(
|
|||
connector_id=connector_id,
|
||||
search_space_id=search_space_id,
|
||||
user_id=user_id,
|
||||
)
|
||||
)
|
||||
|
||||
with session.no_autoflush:
|
||||
duplicate = await check_duplicate_document_by_hash(
|
||||
|
|
|
|||
|
|
@ -318,9 +318,7 @@ async def index_crawled_urls(
|
|||
continue
|
||||
|
||||
# Format content as structured document for summary generation
|
||||
structured_document = crawler.format_to_structured_document(
|
||||
crawl_result
|
||||
)
|
||||
crawler.format_to_structured_document(crawl_result)
|
||||
|
||||
# Generate content hash using a version WITHOUT metadata
|
||||
structured_document_for_hash = crawler.format_to_structured_document(
|
||||
|
|
@ -332,8 +330,8 @@ async def index_crawled_urls(
|
|||
|
||||
# Extract useful metadata
|
||||
title = metadata.get("title", url)
|
||||
description = metadata.get("description", "")
|
||||
language = metadata.get("language", "")
|
||||
metadata.get("description", "")
|
||||
metadata.get("language", "")
|
||||
|
||||
# Update title immediately for better UX
|
||||
document.title = title
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue