Commit Graph
8 Commits
Author SHA1 Message Date
icecraft 6a481320ea fix: using new data api replace old rw api 2024-11-18 17:03:53 +08:00
b72d4ebd94 Feat/support rag (#510)
* Create requirements-docker.txt

* feat: update deps to support rag

* feat: add support to rag, add rag_data_reader api for rag integration

* feat: let user retrieve the filename of the processed file

* feat: add projects demo for rag integrations

---------

Co-authored-by: Xiaomeng Zhao <moe@myhloli.com>
Co-authored-by: icecraft <xurui1@pjlab.org.cn>
2024-08-30 16:46:44 +08:00
icecraftandicecraft f0a8886c7b fix: remove the default value of output option in tools/cli.py and tools/cli_dev.py (#494)
Co-authored-by: icecraft <xurui1@pjlab.org.cn>
2024-08-28 11:13:00 +08:00
c9a51491a4 feat: rename the file generated by command line tools (#401)
* feat: rename the file generated by command line tools

* feat: add pdf filename as prefix to {span,layout,model}.pdf

---------

Co-authored-by: icecraft <tmortred@gmail.com>
Co-authored-by: icecraft <xurui1@pjlab.org.cn>
2024-08-20 14:13:25 +08:00
myhloli c90ee891d6 feat(draw_bbox): add model bbox drawing functionality
Implement the feature to draw bounding boxes for model elements in the PDF. This includes
adding new drawing functions and modifying existing ones to accommodate the new feature.
Also, updates are made to CLI tools and common utilities to support the model bbox drawing.
2024-08-09 20:09:53 +08:00
icecraftandshenguanlin ad5596fcc4 fix: #366 the broken chain after the refractor of AbsReaderWriter lead to wrong api invoke (#371)
Co-authored-by: shenguanlin <shenguanlin@pjlab.org.cn>
2024-08-09 10:48:48 +08:00
icecraftandshenguanlin e155d32212 feat: remove dummpy code, magic_pdf/cli, magic_pdf/train_utils (#291)
* feat: remove dummpy code, magic_pdf/cli, magic_pdf/train_utils

* feat: expose version in command line

---------

Co-authored-by: shenguanlin <shenguanlin@pjlab.org.cn>
2024-08-01 19:59:43 +08:00
icecraftandshenguanlin 40e0827e60 Feat/impl cli (#264)
* feat: refractor cli command

* feat: add docs to describe the output files of cli

* feat: resove review comments

* feat: updat docs about middle.json

---------

Co-authored-by: shenguanlin <shenguanlin@pjlab.org.cn>
2024-08-01 19:21:15 +08:00