You've already forked DataMate
ab4523b556
* fix(session): enhance database connection settings with pool pre-ping and recycle options * feat(metadata): add export type settings and enhance metadata structure * fix(base_op): improve sample handling by introducing target_type key and consolidating text/data retrieval logic * feat(metadata): add export type settings and enhance metadata structure * feat(metadata): add export type settings and enhance metadata structure
29 lines
726 B
YAML
29 lines
726 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:
|
|
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'
|