| .. |
|
config
|
20438bd2b7
feat(language-detection): add YOLOv11 language detection model
|
11 månader sedan |
|
data
|
cd11ddcd6b
docs: make sure the generate process of docs work properly
|
11 månader sedan |
|
dict2md
|
0a468eca6e
feat(llm_aided): add title optimization feature
|
11 månader sedan |
|
filter
|
e1be7da644
refactor(magic_pdf): switch to pdfminer for invalid character detection
|
11 månader sedan |
|
integrations
|
b492c19c4c
refactor: move some constants or enums defs to config folder
|
1 år sedan |
|
libs
|
2684e7753b
fix(npu): correct module name for NPU operations
|
11 månader sedan |
|
model
|
88b909e20e
refactor(magic_pdf): comment out npu-related code
|
11 månader sedan |
|
operators
|
489f70e91d
refactor(magic_pdf): move model config variables
|
11 månader sedan |
|
pipe
|
b2887ca0aa
refactor: refactor code
|
11 månader sedan |
|
post_proc
|
192047a1e8
refactor(magic_pdf): remove unnecessary logging statements
|
11 månader sedan |
|
pre_proc
|
15e876677d
refactor(pre_proc): improve character overlap handling in spans
|
11 månader sedan |
|
resources
|
20438bd2b7
feat(language-detection): add YOLOv11 language detection model
|
11 månader sedan |
|
rw
|
2db3c26374
refactor(libs): remove unused imports and functions
|
1 år sedan |
|
spark
|
b492c19c4c
refactor: move some constants or enums defs to config folder
|
1 år sedan |
|
tools
|
bf2ff5a241
feat(gradio-app): improve PDF conversion and UI functionalities
|
11 månader sedan |
|
utils
|
f6af67eb11
feat: support convert ppt/pptx/doc/docx
|
11 månader sedan |
|
__init__.py
|
d5dbed7325
目录重构
|
1 år sedan |
|
pdf_parse_by_ocr.py
|
a3a720ea87
refactor: isolate inference and pipeline
|
1 år sedan |
|
pdf_parse_by_txt.py
|
a3a720ea87
refactor: isolate inference and pipeline
|
1 år sedan |
|
pdf_parse_union_core_v2.py
|
7c5cdcd4d7
refactor(pdf_parse): improve character spacing handling in PDF text extraction
|
11 månader sedan |
|
user_api.py
|
87af738ab1
fix: 1. ocr txt mode error 2. lose pdf_parse_type field
|
1 år sedan |
myhloli
7c5cdcd4d7
refactor(pdf_parse): improve character spacing handling in PDF text extraction