35 lines
978 B
YAML
35 lines
978 B
YAML
name: 'MinerU PDF文本抽取'
|
|
name_en: 'MinerU PDF Text Extraction'
|
|
description: '基于MinerU API，抽取PDF中的文本。'
|
|
description_en: 'Extracts text from PDF files based on MinerU API.'
|
|
language: 'python'
|
|
vendor: 'huawei'
|
|
raw_id: 'MineruFormatter'
|
|
version: '1.0.0'
|
|
types:
|
|
- 'collect'
|
|
modal: 'text'
|
|
effect:
|
|
before: ''
|
|
after: ''
|
|
inputs: 'text'
|
|
outputs: 'text'
|
|
settings:
|
|
mineruApi:
|
|
name: 'Mineru Api地址'
|
|
description: '指定mineru服务的api地址，默认为本地同一集群内地址。'
|
|
type: 'input'
|
|
defaultVal: 'http://deepdata-mineru:8000'
|
|
required: false
|
|
exportType:
|
|
name: '导出类型'
|
|
description: '指定清洗结果文件类型。若指定为md且后续存在其他清洗算子，可能导致文件格式错乱。'
|
|
type: 'select'
|
|
defaultVal: 'markdown'
|
|
required: false
|
|
options:
|
|
- label: 'markdown'
|
|
value: 'md'
|
|
- label: 'txt'
|
|
value: 'txt'
|