| .. |
|
config
|
20438bd2b7
feat(language-detection): add YOLOv11 language detection model
|
преди 11 месеца |
|
data
|
3271cf75d3
refactor(langdetect): simplify language detection model and improve logging
|
преди 11 месеца |
|
dict2md
|
0a468eca6e
feat(llm_aided): add title optimization feature
|
преди 11 месеца |
|
filter
|
e1be7da644
refactor(magic_pdf): switch to pdfminer for invalid character detection
|
преди 1 година |
|
integrations
|
b492c19c4c
refactor: move some constants or enums defs to config folder
|
преди 1 година |
|
libs
|
c38060d5b9
fix(boxbase): handle cases where bounding box area is zero
|
преди 10 месеца |
|
model
|
b6710b9988
fix(magic_pdf): correct batch ratio conditions for GPU memory
|
преди 10 месеца |
|
operators
|
52efe94da8
feat(api): simplify markdown and content list generation
|
преди 11 месеца |
|
post_proc
|
d986e39313
feat(llm_aided): add reasonability check and fine-tuning guidelines
|
преди 10 месеца |
|
pre_proc
|
f37b14bc83
refactor(pre_proc): adjust IOU threshold for character overlap detection
|
преди 10 месеца |
|
resources
|
2a3a006f4d
fix(models): update unimernet_small model path
|
преди 10 месеца |
|
spark
|
b492c19c4c
refactor: move some constants or enums defs to config folder
|
преди 1 година |
|
tools
|
f911a102ab
feat(tools): add character bounding box drawing functionality
|
преди 11 месеца |
|
utils
|
f6af67eb11
feat: support convert ppt/pptx/doc/docx
|
преди 1 година |
|
__init__.py
|
d5dbed7325
目录重构
|
преди 1 година |
|
pdf_parse_union_core_v2.py
|
10e848b39d
feat(pdf_parse_union_core_v2): add timing log for LLM aided processes
|
преди 10 месеца |
myhloli
10e848b39d
feat(pdf_parse_union_core_v2): add timing log for LLM aided processes