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

refine manual parser (#140)

Browse Source
This commit is contained in:
KevinHuSh
2024-03-21 18:17:32 +08:00
committed by GitHub
parent f4ec7cfa76
commit 6c6b144de2
11 changed files with 77 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
rag/svr/task_broker.py
View File

@ -82,8 +82,8 @@ def dispatch():
tsks = []
if r["type"] == FileType.PDF.value:
pages = PdfParser.total_page_number(r["name"], MINIO.get(r["kb_id"], r["location"]))
page_size = 5
if r["parser_id"] == "paper": page_size = 12
page_size = 12
if r["parser_id"] == "paper": page_size = 22
if r["parser_id"] == "one": page_size = 1000000000
for s,e in r["parser_config"].get("pages", [(0,100000)]):
e = min(e, pages)