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 admin initialization (#75)

Browse Source
This commit is contained in:
KevinHuSh
2024-02-27 14:57:34 +08:00
committed by GitHub
parent d1c600d5d3
commit 4568a4b2cb
13 changed files with 91 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
deepdoc/vision/layout_recognizer.py
View File

@ -37,7 +37,7 @@ class LayoutRecognizer(Recognizer):
super().__init__(self.labels, domain,
os.path.join(get_project_base_directory(), "rag/res/deepdoc/"))
def __call__(self, image_list, ocr_res, scale_factor=3, thr=0.7, batch_size=16):
def __call__(self, image_list, ocr_res, scale_factor=3, thr=0.2, batch_size=16):
def __is_garbage(b):
patt = [r"^•+$", r"(版权归©|免责条款|地址[:：])", r"\.{3,}", "^[0-9]{1,2} / ?[0-9]{1,2}$",
r"^[0-9]{1,2} of [0-9]{1,2}$", "^http://[^ ]{12,}",