feat: 支持运行data-juicer算子 (#215)

* feature: 增加data-juicer算子

* feat: 支持运行data-juicer算子

* feat: 支持data-juicer任务下发

* feat: 支持data-juicer结果数据集归档

* feat: 支持data-juicer结果数据集归档
This commit is contained in:
hhhhsc701
2025-12-31 09:20:41 +08:00
committed by GitHub
parent 63f4e3e447
commit 6a1eb85e8e
26 changed files with 709 additions and 120 deletions

View File

@@ -6,7 +6,7 @@ authors = [
{ name = "Huawei datamate team" }
]
license = { text = "Apache-2.0" }
requires-python = ">=3.10"
requires-python = ">=3.10, <=3.12"
urls = { repository = "https://github.com/ModelEngine-Group/datamate" }
classifiers = [
"License :: OSI Approved :: Apache Software License",
@@ -20,7 +20,7 @@ dependencies = [
"jsonargparse>=4.44.0",
"loguru>=0.7.3",
"opencv-python-headless>=4.12.0.88",
"ray[data,default]==2.52.1",
"ray[data,default]>=2.52.1",
"unstructured[csv,docx,pptx,xlsx,pdf,md]==0.18.15",
"uvicorn[standard]>=0.38.0",
]