zlei6/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2026-06-29 15:31:05 +08:00
Code Issues Packages Projects Releases Wiki Activity

Revert "fix: paginate non-DeepDOC PDF parsing tasks to prevent OOM" (#16104)

Browse Source 
Reverts infiniflow/ragflow#15951
This commit is contained in:
Wang Qi
2026-06-16 20:11:45 +08:00
committed by GitHub
parent 1e4796da9d
commit 17e3aad7ae
1 changed files with 3 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
api/db/services/task_service.py
View File

@@ -390,14 +390,15 @@ def queue_tasks(doc: dict, bucket: str, name: str, priority: int):
if doc["type"] == FileType.PDF.value:
file_bin = settings.STORAGE_IMPL.get(bucket, name)
do_layout = doc["parser_config"].get("layout_recognize", "DeepDOC")
pages = PdfParser.total_page_number(doc["name"], file_bin)
if pages is None:
pages = 0
page_size = doc["parser_config"].get("task_page_size") or 12
if doc["parser_id"] == "paper":
page_size = doc["parser_config"].get("task_page_size") or 22
if doc["parser_id"] in ["one", "knowledge_graph"] or doc["parser_config"].get("toc_extraction", False):
page_size = doc["parser_config"].get("task_page_size") or 30
if doc["parser_id"] in ["one", "knowledge_graph"] or do_layout != "DeepDOC" or doc["parser_config"].get("toc_extraction", False):
page_size = MAXIMUM_TASK_PAGE_NUMBER
page_ranges = doc["parser_config"].get("pages") or [(1, MAXIMUM_PAGE_NUMBER)]
for s, e in page_ranges:
s -= 1