myhloli 869cf0a609 Merge remote-tracking branch 'origin/dev' into dev пре 11 месеци
..
config 20438bd2b7 feat(language-detection): add YOLOv11 language detection model пре 11 месеци
data 3271cf75d3 refactor(langdetect): simplify language detection model and improve logging пре 11 месеци
dict2md 0a468eca6e feat(llm_aided): add title optimization feature пре 11 месеци
filter e1be7da644 refactor(magic_pdf): switch to pdfminer for invalid character detection пре 1 година
integrations b492c19c4c refactor: move some constants or enums defs to config folder пре 1 година
libs 29681c4f79 fix(language): enhance language detection and text processing пре 11 месеци
model bd1b76771e refactor(magic_pdf): update OCR engine selection in RapidTableModel пре 11 месеци
operators 52efe94da8 feat(api): simplify markdown and content list generation пре 11 месеци
post_proc 512adb6701 feat(model): add onnxruntime support for paddleocr on cpu пре 11 месеци
pre_proc 15e876677d refactor(pre_proc): improve character overlap handling in spans пре 11 месеци
resources a80ff05150 refactor(model): remove unused YOLO v11 language detection model пре 11 месеци
spark b492c19c4c refactor: move some constants or enums defs to config folder пре 1 година
tools f911a102ab feat(tools): add character bounding box drawing functionality пре 11 месеци
utils f6af67eb11 feat: support convert ppt/pptx/doc/docx пре 11 месеци
__init__.py d5dbed7325 目录重构 пре 1 година
pdf_parse_union_core_v2.py 3f93b895bc feat(pdf_parse): add internal block sorting for images and tables пре 11 месеци