20 Commits (ed6081845ac8bbee43269db163feb3f97d81282d)

Author SHA1 Message Date
  KevinHuSh ed6081845a
Fit a lot of encodings for text file. (#458) 1 year ago
  KevinHuSh 572e5b1ff1
Let task continue dispaching while meeting unexpected doc formats (#199) 1 year ago
  KevinHuSh fd7fcb5baf
apply pep8 formalize (#155) 1 year ago
  KevinHuSh da21320b88
fix plainPdf bugs (#152) 1 year ago
  KevinHuSh 71fe314955
refine page ranges (#147) 1 year ago
  KevinHuSh f6aee7f230
add use layout or not option (#145) 1 year ago
  KevinHuSh 6c6b144de2
refine manual parser (#140) 1 year ago
  KevinHuSh 5875c8ba08
Add 'One' chunk method (#137) 1 year ago
  KevinHuSh 6999598101
refine for English corpus (#135) 1 year ago
  KevinHuSh 0feb085c88
refine table parser (#120) 1 year ago
  KevinHuSh f1f09df901
add local llm implementation (#119) 1 year ago
  KevinHuSh 8a57f2afd5
change callback strategy, add timezone to docker (#96) 1 year ago
  KevinHuSh 7bfaf0df29
fix position extraction bug (#93) 1 year ago
  KevinHuSh 8a726fb04b
solve task execution issues (#90) 1 year ago
  KevinHuSh d32322c081
rename vision, add layour and tsr recognizer (#70) 1 year ago
  KevinHuSh cacd36c5e1
use onnx models, new deepdoc (#68) 1 year ago
  KevinHuSh c5ea37cd30 Add resume parser and fix bugs (#59) 1 year ago
  KevinHuSh 407b2523b6 remove unused codes, seperate layout detection out as a new api. Add new rag methed 'table' (#55) 1 year ago
  KevinHuSh e6acaf6738 Add Q&A and Book, fix task running bugs (#50) 1 year ago
  KevinHuSh 6224edcd1b Add task moduel, and pipline the task and every parser (#49) 1 year ago