pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix: debug hierachical merging... (#10337)

Browse Source 
### What problem does this PR solve?


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
Kevin Hu
2025-09-29 09:29:33 +08:00
committed by GitHub
parent 664bc0b961
commit 71f69cdb75
13 changed files with 113 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
api/db/services/task_service.py
View File

@ -358,7 +358,7 @@ def queue_tasks(doc: dict, bucket: str, name: str, priority: int):
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 do_layout != "DeepDOC":
if doc["parser_id"] in ["one", "knowledge_graph"] or do_layout != "DeepDOC" or doc["parser_config"].get("toc", True):
page_size = 10 ** 9
page_ranges = doc["parser_config"].get("pages") or [(1, 10 ** 5)]
for s, e in page_ranges:
@ -505,7 +505,6 @@ def queue_dataflow(tenant_id:str, flow_id:str, task_id:str, doc_id:str=CANVAS_DE
task["kb_id"] = DocumentService.get_knowledgebase_id(doc_id)
task["tenant_id"] = tenant_id
task["task_type"] = "dataflow"
task["dataflow_id"] = flow_id
task["file"] = file