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>

runtime/ops/formatter/external_pdf_formatter/metadata.yml

@@ -1,7 +1,7 @@
-name: '外部PDF文本抽取'
+name: 'MinerU PDF文本抽取'
 name_en: 'External PDF Text Extraction'
-description: '基于外部API，抽取PDF中的文本。'
-description_en: 'Extracts text from PDF files based on external APIs.'
+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: 'ExternalPDFFormatter'

runtime/ops/formatter/external_pdf_formatter/process.py

@@ -2,7 +2,7 @@
 # -*- coding: utf-8 -*-
 
 """
-Description: 外部PDF文本抽取
+Description: MinerU PDF文本抽取
 Create: 2025/10/29 17:24
 """
 import json

runtime/ops/formatter/unstructured_formatter/metadata.yml

@@ -1,7 +1,7 @@
 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.'
+description: '抽取非结构化文件的文本，目前支持PowerPoint演示文稿、Word文档以及Excel工作簿。'
+description_en: 'Extracts text from Unstructured files, currently supporting PowerPoint presentations, Word documents and Excel spreadsheets files.'
 language: 'python'
 vendor: 'huawei'
 raw_id: 'UnstructuredFormatter'