| .. |
|
config
|
565ef479fa
feat: Implement universal document parser with enhanced processing capabilities
|
2 hete |
|
core
|
ccde49c2d2
refactor: Update import path for merger components in pipeline_manager_v2.py
|
1 hete |
|
models
|
565ef479fa
feat: Implement universal document parser with enhanced processing capabilities
|
2 hete |
|
tests
|
565ef479fa
feat: Implement universal document parser with enhanced processing capabilities
|
2 hete |
|
utils
|
565ef479fa
feat: Implement universal document parser with enhanced processing capabilities
|
2 hete |
|
Layout后处理-文本转表格.md
|
565ef479fa
feat: Implement universal document parser with enhanced processing capabilities
|
2 hete |
|
OCR识别差异分析与改进方案.md
|
565ef479fa
feat: Implement universal document parser with enhanced processing capabilities
|
2 hete |
|
VLM服务地址.md
|
565ef479fa
feat: Implement universal document parser with enhanced processing capabilities
|
2 hete |
|
__init__.py
|
565ef479fa
feat: Implement universal document parser with enhanced processing capabilities
|
2 hete |
|
main_v2.py
|
b2eafd4378
fix: Update page range in universal_doc_parser to process first 2 pages
|
1 hete |
|
unclip_ratio参数说明.md
|
565ef479fa
feat: Implement universal document parser with enhanced processing capabilities
|
2 hete |
|
模型统一框架.md
|
565ef479fa
feat: Implement universal document parser with enhanced processing capabilities
|
2 hete |
|
流式处理模式说明.md
|
565ef479fa
feat: Implement universal document parser with enhanced processing capabilities
|
2 hete |
zhch158_admin
b2eafd4378
fix: Update page range in universal_doc_parser to process first 2 pages