Commit Graph

7 Commits

Author SHA1 Message Date
hhhhsc701
f78475e29f Develop hsc (#58)
feature: 优化镜像构建/部署
2025-11-06 17:14:54 +08:00
hhhhsc701
05b26a2981 feature: 更新算子名称;增加创建任务、模板校验 (#57)
* feature: 更新算子名称;增加创建任务、模板校验

* feature: 镜像构建增加缓存
2025-11-05 17:38:03 +08:00
Startalker
a600c1d793 feature: modify UnstructuredFormatter and ExternalPDFFormatter description (#44)
* feature: add UnstructuredFormatter

* feature: add UnstructuredFormatter in db

* feature: add unstructured[docx]==0.18.15

* feature: support doc

* feature: add mineru

* feature: add external pdf extract operator by using mineru

* feature: mineru docker install bugfix

* feature: add unstructured xlsx/xls/csv/pptx/ppt

* feature: modify UnstructuredFormatter and ExternalPDFFormatter description

---------

Co-authored-by: Startalker <438747480@qq.com>
2025-10-31 10:32:14 +08:00
Startalker
06b05a65a9 feature: add unstructured xlsx/xls/csv/pptx/ppt (#41)
* feature: add UnstructuredFormatter

* feature: add UnstructuredFormatter in db

* feature: add unstructured[docx]==0.18.15

* feature: support doc

* feature: add mineru

* feature: add external pdf extract operator by using mineru

* feature: mineru docker install bugfix

* feature: add unstructured xlsx/xls/csv/pptx/ppt

---------

Co-authored-by: Startalker <438747480@qq.com>
2025-10-30 20:21:12 +08:00
Startalker
155603b1ca feature: add external pdf extract operator by using mineru (#36)
* feature: add UnstructuredFormatter

* feature: add UnstructuredFormatter in db

* feature: add unstructured[docx]==0.18.15

* feature: support doc

* feature: add mineru

* feature: add external pdf extract operator by using mineru

* feature: mineru docker install bugfix

---------

Co-authored-by: Startalker <438747480@qq.com>
2025-10-30 15:55:10 +08:00
Startalker
f86d4fae25 feature: add unstructured formatter operator for doc/docx (#17)
* feature: add UnstructuredFormatter

* feature: add UnstructuredFormatter in db

* feature: add unstructured[docx]==0.18.15

* feature: support doc

---------

Co-authored-by: Startalker <438747480@qq.com>
2025-10-23 16:49:03 +08:00
Dallas98
1c97afed7d init datamate 2025-10-21 23:00:48 +08:00