67 Commit (667c5812d0369d0b4687d55b30a399381e4cbd66)

Autore SHA1 Messaggio Data
  Stephen Hu 667c5812d0
Fix:Repeated images when parsing markdown files with images (#9196) 3 mesi fa
  Kevin Hu d9fe279dde
Feat: Redesign and refactor agent module (#9113) 3 mesi fa
  Yongteng Lei dbc2a8689a
Fix: no chunks parsed out for Law (#8842) 3 mesi fa
  Stephen Hu f569401398
Fix: better_handle_different_types (#8775) 3 mesi fa
  Stephen Hu 00c954755e
Fix:use the same logic to handle pos in tokenize_chunks_with_images (#8732) 3 mesi fa
  Yongteng Lei b705ff08fe
Refa: improve GraphRAG similarity sensitivity to numeric differences (#8479) 4 mesi fa
  Kevin Hu 93f5df716f
Fix: order chunks from docx by positions. (#7979) 5 mesi fa
  Yongteng Lei bd4678bca6
Fix: Unnecessary truncation in markdown parser (#7972) 5 mesi fa
  Yongteng Lei 46963ab1ca
Fix: add advanced delimiter detection for naive merge (#7941) 5 mesi fa
  Stephen Hu db4371c745
Fix: Improve First Chunk Size (#7806) 5 mesi fa
  Emmanuel Ferdman d4a123d6dd
Fix: resolve regex library warnings (#7782) 5 mesi fa
  Kevin Hu 321a280031
Feat: add image preview to retrieval test. (#7610) 5 mesi fa
  Stephen Hu 1662c7eda3
Feat: Markdown add image (#7124) 6 mesi fa
  Kevin Hu a087d13ccb
Feat: text file support position retaining. (#6231) 7 mesi fa
  Kevin Hu e05cdc2f9c
Fix: encode detect error. (#6006) 7 mesi fa
  Kevin Hu daddfc9e1b
Remove dup gb2312, solve currupt error. (#5326) 8 mesi fa
  Kevin Hu 3444cb15e3
Refine search query. (#5235) 8 mesi fa
  Kevin Hu 7b3d700d5f
Apply agentic searching. (#5196) 8 mesi fa
  Kevin Hu f374dd38b6
Fix divided by zero issue. (#4784) 8 mesi fa
  Luo Pan 68d46b2a1e
Fix bug in hierarchical_merge function (#4006) 10 mesi fa
  Zhichang Yu 03f00c9e6f
Rename page_num_list, top_list, position_list (#3940) 10 mesi fa
  Zhichang Yu 7a6bf4326e
Fixed log not displaying (#3946) 10 mesi fa
  Zhichang Yu 0d68a6cd1b
Fix errors detected by Ruff (#3918) 11 mesi fa
  Jin Hai 6657ca7cde
Change default error message to English (#3838) 11 mesi fa
  Zhichang Yu bc701d7b4c
Edit chunk shall update instead of insert it (#3709) 11 mesi fa
  liuhua 5c59651bda
Fix the bug causing garbled text (#3640) 11 mesi fa
  Zhichang Yu 30f6421760
Use consistent log file names, introduced initLogger (#3403) 11 mesi fa
  Zhichang Yu a2a5631da4
Rework logging (#3358) 11 mesi fa
  Zhichang Yu f4c52371ab
Integration with Infinity (#2894) 11 mesi fa
  Kevin Hu 226bdd6e99
add auto keywords and auto-question (#2965) 1 anno fa
  Kevin Hu 190eea7097
trival (#2808) 1 anno fa
  Kevin Hu 2d1c83da59
fix LIGHTEN issue (#2806) 1 anno fa
  Kevin Hu 9d4bb5767c
make highlight friendly to English (#2417) 1 anno fa
  Jin Hai 6b3a40be5c
Format file format from Windows/dos to Unix (#1949) 1 anno fa
  Kevin Hu 2452c5624f
remove duplicated key in mind map (#1809) 1 anno fa
  Kevin Hu 152072f900
Add graphrag (#1793) 1 anno fa
  H 79c873344b
Fix docs parser (#1714) 1 anno fa
  Kevin Hu c92d334b29
fix bug of regx (#1703) 1 anno fa
  KevinHuSh 7c9ea5cad9
add interpreter to graph (#1347) 1 anno fa
  KevinHuSh 92e9320657
upgrade laws parser of docx (#1332) 1 anno fa
  Zhedong Cen fc7cc1d36c
Optimize docx handle method in laws parser (#1302) 1 anno fa
  Zhedong Cen 38bd02f402
Support displaying images in the chunks of docx files when using general parser (#1253) 1 anno fa
  Wang Baoling 18f4a6b35c
feat: support json file (#1217) 1 anno fa
  Zhedong Cen 3c1444ab19
Add docx support for manual parser (#1227) 1 anno fa
  Zhedong Cen 90975460af
Add pdf support for QA parser (#1155) 1 anno fa
  Jin Hai 9ed0e50f6b
Update info (#1005) 1 anno fa
  KevinHuSh c6b6c748ae
fix file encoding detection bug (#653) 1 anno fa
  KevinHuSh 8c07992b6c
refine code (#595) 1 anno fa
  KevinHuSh ed6081845a
Fit a lot of encodings for text file. (#458) 1 anno fa
  KevinHuSh 24c15daaed
fix es exception (#298) 1 anno fa