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>
This commit is contained in:
Startalker
2025-10-23 16:49:03 +08:00
committed by GitHub
parent c52702b073
commit f86d4fae25
7 changed files with 63 additions and 3 deletions

View File

@@ -0,0 +1,16 @@
name: '非结构化文本抽取'
name_en: 'Unstructured Text Extraction'
description: '抽取非结构化文件的文本,目前支持word文档'
description_en: 'Extracts text from Unstructured files, currently supporting Word documents.'
language: 'python'
vendor: 'huawei'
raw_id: 'UnstructuredFormatter'
version: '1.0.0'
types:
- 'collect'
modal: 'text'
effect:
before: ''
after: ''
inputs: 'text'
outputs: 'text'