myhloli
|
790691d63c
update:update config json
|
1 year ago |
myhloli
|
644085760b
fix(ocr_mkcontent): expand para_to_standard_format_v2 to handle list and index blocks
|
1 year ago |
Xiaomeng Zhao
|
e4904cd6d3
Merge pull request #765 from myhloli/add-list-group
|
1 year ago |
myhloli
|
8cc76c4921
refactor(para): improve paragraph splitting algorithm
|
1 year ago |
myhloli
|
fc49f5c446
refactor(magic_pdf): remove unused parameters and simplify functions
|
1 year ago |
Xiaomeng Zhao
|
fe21eebd8c
Merge pull request #753 from myhloli/dev
|
1 year ago |
myhloli
|
011a1b973b
refactor(ocr):Increase the dilation factor in OCR to address the issue of word concatenation.
|
1 year ago |
Xiaomeng Zhao
|
2a40984596
Merge pull request #747 from myhloli/dev
|
1 year ago |
myhloli
|
cf377ce4a1
update example files
|
1 year ago |
myhloli
|
ab3d2d1781
Merge remote-tracking branch 'origin/dev' into dev
|
1 year ago |
myhloli
|
237c062de4
docs: enhance document parsing capabilities
|
1 year ago |
Xiaomeng Zhao
|
f50bc87be6
Merge pull request #744 from myhloli/para-split-v3
|
1 year ago |
myhloli
|
81b9fd7bdb
refactor(para_split_v3): refine list block detection in paragraph splitting
|
1 year ago |
Xiaomeng Zhao
|
0d83fb77dd
Merge pull request #743 from myhloli/para-split-v3
|
1 year ago |
myhloli
|
244b868443
fix(split_v3): Fix the rule adaptation for some special list samples.
|
1 year ago |
myhloli
|
7e301b849b
refactor(pdf): adjust span filling threshold in block construction
|
1 year ago |
myhloli
|
fdcb49d327
refactor(para_split_v3): merge list and index block detection
|
1 year ago |
myhloli
|
0a9a6d3e53
fix(magic_pdf): include List and Index block types in processing
|
1 year ago |
Xiaomeng Zhao
|
702b6ac92c
Merge pull request #740 from myhloli/para-split-v3
|
1 year ago |
myhloli
|
1f1dd3538d
feat(list&index block): detect and merge list and index blocks
|
1 year ago |
icecraft
|
c479245e7a
feat: manager docs with sphinx (#737)
|
1 year ago |
Xiaomeng Zhao
|
b9631f30a9
Merge pull request #718 from myhloli/para-split-v3
|
1 year ago |
myhloli
|
7b42d5a0c4
fix: Solving the Grouping Anomaly Issue with Multiple Consecutive Non-Text Blocks
|
1 year ago |
Xiaomeng Zhao
|
964715b26c
Merge pull request #717 from myhloli/dev
|
1 year ago |
Xiaomeng Zhao
|
d1c9c7dd89
Merge branch 'opendatalab:dev' into dev
|
1 year ago |
Xiaomeng Zhao
|
ea7bc620f3
Merge pull request #716 from myhloli/para-split-v3
|
1 year ago |
myhloli
|
6f63e70e94
feat(pdf_parse_union_core_v2): reintegrate para_split_v3 and add page range support
|
1 year ago |
Xiaomeng Zhao
|
7f9d80fc0d
Update how_to_download_models_zh_cn.md
|
1 year ago |
Xiaomeng Zhao
|
675f8e66f4
Merge pull request #706 from myhloli/dev
|
1 year ago |
Xiaomeng Zhao
|
4e58bf8f5a
Update README_Windows_CUDA_Acceleration_en_US.md
|
1 year ago |