myhloli 1a549a0e4b fix(language): remove invalid UTF-16 surrogate pairs from input text 10 kuukautta sitten
..
config 20438bd2b7 feat(language-detection): add YOLOv11 language detection model 11 kuukautta sitten
data 3271cf75d3 refactor(langdetect): simplify language detection model and improve logging 11 kuukautta sitten
dict2md 0a468eca6e feat(llm_aided): add title optimization feature 11 kuukautta sitten
filter e1be7da644 refactor(magic_pdf): switch to pdfminer for invalid character detection 11 kuukautta sitten
integrations b492c19c4c refactor: move some constants or enums defs to config folder 1 vuosi sitten
libs 1a549a0e4b fix(language): remove invalid UTF-16 surrogate pairs from input text 10 kuukautta sitten
model 902dcd2cee refactor(BatchAnalyze): comment out image rotation logic in doclayout_yolo 10 kuukautta sitten
operators 52efe94da8 feat(api): simplify markdown and content list generation 11 kuukautta sitten
post_proc 916ced9f4d docs(magic_pdf): update llm_aided.py prompt for title list optimization 10 kuukautta sitten
pre_proc f37b14bc83 refactor(pre_proc): adjust IOU threshold for character overlap detection 10 kuukautta sitten
resources c20e9a1e84 feat(layout): improve title block handling and layout detection 10 kuukautta sitten
spark b492c19c4c refactor: move some constants or enums defs to config folder 1 vuosi sitten
tools f911a102ab feat(tools): add character bounding box drawing functionality 11 kuukautta sitten
utils f6af67eb11 feat: support convert ppt/pptx/doc/docx 11 kuukautta sitten
__init__.py d5dbed7325 目录重构 1 vuosi sitten
pdf_parse_union_core_v2.py 206fcb3900 Merge pull request #1537 from myhloli/doclayoutyolo-fix 10 kuukautta sitten