myhloli 044780951a perf(model): add threading lock for OCR model initialization 11 månader sedan
..
config b492c19c4c refactor: move some constants or enums defs to config folder 1 år sedan
data b0529b6fbd fix: reduce maximum image size 1 år sedan
dict2md b80befe9cf refactor(mkcontent): optimize paragraph text merging and language detection 1 år sedan
filter ac88815620 refactor(pdf_check): improve character detection using PyMuPDF 1 år sedan
integrations b492c19c4c refactor: move some constants or enums defs to config folder 1 år sedan
libs b9f3435cb7 Update version.py with new version 1 år sedan
model 044780951a perf(model): add threading lock for OCR model initialization 11 månader sedan
para 41545a13c6 refactor(para): adjust line height multiplier for block splitting 1 år sedan
pipe b492c19c4c refactor: move some constants or enums defs to config folder 1 år sedan
pre_proc 7f8dc353b0 fix(pre_proc): prevent errors when imageWriter is None 1 år sedan
resources 240fe99e3c feat(table): integrate RapidTable model for table recognition 1 år 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 9c8d995ed2 Merge pull request #1045 from myhloli/dev 1 år sedan
utils 9cda7051c6 add init to magic_pdf.utils 1 år sedan
__init__.py d5dbed7325 目录重构 1 år sedan
pdf_parse_by_ocr.py 309be741e8 refactor(txt_parse): improve text extraction accuracy with new algorithm 1 år sedan
pdf_parse_by_txt.py 309be741e8 refactor(txt_parse): improve text extraction accuracy with new algorithm 1 år sedan
pdf_parse_union_core_v2.py d4345b6e39 refactor(pdf_parse): adjust character-axis alignment algorithm 1 år sedan
user_api.py 309be741e8 refactor(txt_parse): improve text extraction accuracy with new algorithm 1 år sedan