diff --git a/manifest.yaml b/manifest.yaml
index 213909f..7bbef81 100644
--- a/manifest.yaml
+++ b/manifest.yaml
@@ -1,17 +1,17 @@
-version: 1.2.1
+version: 1.2.2
 type: plugin
 author: intsig-textin
 name: xparse
 label:
-  en_US: xParse
-  ja_JP: xParse
-  zh_Hans: xParse
-  pt_BR: xParse
+  en_US: Document OCR - TextIn
+  ja_JP: ドキュメント解析 OCR - TextIn
+  zh_Hans: 文档解析 OCR - TextIn
+  pt_BR: OCR de Documentos - TextIn
 description:
-  en_US: Parse complex documents into Markdown, structured elements, tables, and images for RAG pipelines and agent workflows.
-  ja_JP: 複雑なドキュメントを Markdown、構造化要素、テーブル、画像に解析し、RAG パイプラインやエージェントワークフローに活用します。
-  zh_Hans: 将复杂文档解析为 Markdown、结构化元素、表格和图片，服务于 RAG 管线和 Agent 工作流。
-  pt_BR: Analise documentos complexos em Markdown, elementos estruturados, tabelas e imagens para pipelines RAG e fluxos de trabalho de agentes.
+  en_US: xParse is designed for LLM downstream tasks, accurately recognizes content in PDF/Word/Excel/images and converts to standard formats (markdown, json). Excels at complex document understanding and restoration. Free 1000 pages/day for developers.
+  ja_JP: xParse はLLM下流タスク向けに設計。PDF/Word/Excel/画像のコンテンツを正確に認識し、標準フォーマット（markdown、json）に変換します。複雑なドキュメントの理解と復元に優れ、開発者に毎日1000ページの無料枠を提供します。
+  zh_Hans: xParse 专为LLM下游任务设计，能精准识别PDF/Word/Excel/图片中的内容并转成标准格式（markdown、json），尤其擅长复杂文档的理解和还原，免费为开发者提供1000页/天额度。
+  pt_BR: xParse é projetado para tarefas downstream de LLM, reconhece com precisão o conteúdo em PDF/Word/Excel/imagens e converte para formatos padrão (markdown, json). Excelente na compreensão e restauração de documentos complexos. 1000 páginas/dia grátis para desenvolvedores.
 icon: icon.svg
 icon_dark: icon-dark.svg
 resource:
@@ -30,7 +30,7 @@ plugins:
   tools:
     - provider/xparse.yaml
 meta:
-  version: 1.2.1
+  version: 1.2.2
   arch:
     - amd64
     - arm64
diff --git a/provider/xparse.yaml b/provider/xparse.yaml
index 7ee5777..98619a6 100644
--- a/provider/xparse.yaml
+++ b/provider/xparse.yaml
@@ -1,17 +1,17 @@
 identity:
   author: "intsig-textin"
   name: "xparse"
-  version: "1.2.1"
+  version: "1.2.2"
   label:
-    en_US: "xParse"
-    zh_Hans: "xParse"
-    pt_BR: "xParse"
-    ja_JP: "xParse"
+    en_US: "Document OCR - TextIn"
+    zh_Hans: "文档解析 OCR - TextIn"
+    pt_BR: "OCR de Documentos - TextIn"
+    ja_JP: "ドキュメント解析 OCR - TextIn"
   description:
-    en_US: "Parse complex documents into Markdown, structured elements, tables, and images for RAG pipelines and agent workflows."
-    zh_Hans: "将复杂文档解析为 Markdown、结构化元素、表格和图片，服务于 RAG 管线和 Agent 工作流。"
-    pt_BR: "Analise documentos complexos em Markdown, elementos estruturados, tabelas e imagens para pipelines RAG e fluxos de trabalho de agentes."
-    ja_JP: "複雑なドキュメントを Markdown、構造化要素、テーブル、画像に解析し、RAG パイプラインやエージェントワークフローに活用します。"
+    en_US: "xParse is designed for LLM downstream tasks, accurately recognizes content in PDF/Word/Excel/images and converts to standard formats (markdown, json). Excels at complex document understanding and restoration. Free 1000 pages/day for developers."
+    zh_Hans: "xParse 专为LLM下游任务设计，能精准识别PDF/Word/Excel/图片中的内容并转成标准格式（markdown、json），尤其擅长复杂文档的理解和还原，免费为开发者提供1000页/天额度。"
+    pt_BR: "xParse é projetado para tarefas downstream de LLM, reconhece com precisão o conteúdo em PDF/Word/Excel/imagens e converte para formatos padrão (markdown, json). Excelente na compreensão e restauração de documentos complexos. 1000 páginas/dia grátis para desenvolvedores."
+    ja_JP: "xParse はLLM下流タスク向けに設計。PDF/Word/Excel/画像のコンテンツを正確に認識し、標準フォーマット（markdown、json）に変換します。複雑なドキュメントの理解と復元に優れ、開発者に毎日1000ページの無料枠を提供します。"
   icon: "icon.svg"
   tags: ['rag', 'utilities']
 
diff --git a/requirements.txt b/requirements.txt
index 32e3147..c8a7909 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,2 +1,2 @@
-dify_plugin>=0.4.0,<=0.7.1
+dify_plugin>=0.9.0
 requests>=2.31.0
diff --git a/xparse.difypkg b/xparse.difypkg
index e8aa916..d3a2245 100644
Binary files a/xparse.difypkg and b/xparse.difypkg differ