✨ add support for new filetypes

Author: yzAiden

backend/database/attachment_db.py

@@ -272,6 +272,7 @@ def get_content_type(file_path: str) -> str:
                   '.html': 'text/html',
                   '.htm': 'text/html',
                   '.json': 'application/json',
+                  '.epub': 'application/epuub',
                   '.xml': 'application/xml',
                   '.zip': 'application/zip',
                   '.rar': 'application/x-rar-compressed',

doc/docs/en/sdk/data-process.md

@@ -43,10 +43,10 @@ def file_process(self,
 
 ## 📁 Supported File Formats
 
-- **Text files**: .txt, .md, .csv
-- **Documents**: .pdf, .docx, .pptx
+- **Text files**: .txt, .md, .csv, .json
+- **Documents**: .pdf, .docx, .pptx, .epub
 - **Images**: .jpg, .png, .gif (with OCR)
-- **Web content**: HTML, URLs
+- **Web content**: HTML, URLs, XML
 - **Archives**: .zip, .tar
 
 ## 💡 Usage Examples

doc/docs/en/user-guide/knowledge-base.md

@@ -26,12 +26,14 @@ Create and manage knowledge bases, upload documents, and generate summaries. Kno
 ### Supported File Formats
 
 Nexent supports multiple file formats, including:
-- **Text:** .txt, .md
+- **Text:** .txt, .md, .csv, .json
 - **PDF:** .pdf
 - **Word:** .docx
 - **PowerPoint:** .pptx
+- **EPUB:** .epub
 - **Excel:** .xlsx
 - **Data files:** .csv
+- **Web content:** .html, .xml
 
 ## 📊 Knowledge Base Summary
 

doc/docs/en/user-guide/start-chat.md

@@ -79,8 +79,8 @@ You can upload files during a chat so the agent can reason over their content:
    - Or drag files directly into the chat area
 
 2. **Supported File Formats**
-   - **Documents:** PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx)
-   - **Text:** Markdown (.md), Plain text (.txt)
+   - **Documents:** PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx), EPUB (.epub), HTML (.html), XML (.xml)
+   - **Text & Data:** Markdown (.md), Plain text (.txt), JSON (.json), CSV (.csv)
    - **Images:** JPG, PNG, GIF, and other common formats
 
 3. **File Processing Flow**

doc/docs/zh/sdk/data-process.md

@@ -98,6 +98,9 @@ def file_process(self,
 - `.odt` - OpenDocument文本
 - `.pptx` - PowerPoint 2007及更高版本
 - `.ppt` - PowerPoint 97-2003版本
+- `.xml` - XML数据文件
+- `.json` - JSON数据文件
+- `.csv` - 逗号分隔值文件
 
 ## 💡 使用示例
 

doc/docs/zh/user-guide/knowledge-base.md

@@ -26,12 +26,14 @@
 
 Nexent支持多种文件格式，包括：
 
-- **文本**: .txt, .md文件
+- **文本**: .txt, .md, .json文件
 - **PDF**: .pdf文件
 - **Word**: .docx文件
 - **PowerPoint**: .pptx文件
 - **Excel**: .xlsx文件
+- **EPUB** .epub文件
 - **数据文件**: .csv文件
+- **Web content**: .html, .xml文件
 
 ## 📊 知识库总结
 

doc/docs/zh/user-guide/start-chat.md

@@ -79,8 +79,8 @@ Nexent支持语音输入功能，让您可以通过语音与智能体交互。
    - 或直接将文件拖拽到对话区域
 
 2. **支持的文件格式**
-   - **文档类**：PDF、Word (.docx)、PowerPoint (.pptx)、Excel (.xlsx)
-   - **文本类**：Markdown (.md)、纯文本 (.txt)
+   - **文档类**：PDF、Word (.docx)、PowerPoint (.pptx)、Excel (.xlsx), EPUB (.epub), HTML (.html), XML (.xml)
+   - **文本类**：Markdown (.md)、纯文本 (.txt), JSON (.json), CSV (.csv)
    - **图片类**：JPG、PNG、GIF 等常见图片格式
 
 3. **文件处理流程**

frontend/app/[locale]/knowledges/components/upload/UploadArea.tsx

@@ -233,7 +233,7 @@ const UploadArea = forwardRef<UploadAreaRef, UploadAreaProps>(
       fileList,
       onChange: handleChange,
       customRequest: handleCustomRequest,
-      accept: ".pdf,.docx,.pptx,.xlsx,.md,.txt,.csv",
+      accept: ".pdf,.docx,.pptx,.xlsx,.md,.txt,.csv,.json,.epub,.xml,.html",
       showUploadList: true,
       disabled: disabled,
       progress: {

frontend/const/chatConfig.ts

@@ -9,6 +9,7 @@ export const chatConfig = {
     "application/json",
     "application/xml",
     "text/markdown",
+    "text/csv",
   ],
 
   // Supported text file extensions
@@ -36,10 +37,10 @@ export const chatConfig = {
   imageExtensions: ["jpg", "jpeg", "png", "gif", "webp", "svg", "bmp"],
 
   // Supported document file extensions
-  documentExtensions: ["pdf", "doc", "docx", "xls", "xlsx", "ppt", "pptx"],
+  documentExtensions: ["pdf", "doc", "docx", "xls", "xlsx", "ppt", "pptx", "epub", "html", "xml"],
 
   // Supported text document extensions
-  supportedTextExtensions: ["md", "markdown", "txt"],
+  supportedTextExtensions: ["md", "markdown", "txt", "csv", "json"],
 
   // File icon mapping configuration
   fileIcons: {
@@ -50,7 +51,7 @@ export const chatConfig = {
     word: ["doc", "docx"],
 
     // Plain text files
-    text: ["txt"],
+    text: ["txt", "epub"],
 
     // Markdown files
     markdown: ["md"],
@@ -62,7 +63,7 @@ export const chatConfig = {
     powerpoint: ["ppt", "pptx"],
 
     // HTML files
-    html: ["html", "htm"],
+    html: ["html", "htm", "xml"],
 
     // Code files
     code: ["css", "js", "ts", "jsx", "tsx", "php", "py", "java", "c", "cpp", "cs"],

frontend/const/knowledgeBase.ts

@@ -120,7 +120,12 @@ export const FILE_EXTENSIONS = {
   PPT: 'ppt',
   PPTX: 'pptx',
   TXT: 'txt',
-  MD: 'md'
+  MD: 'md',
+  EPUB: 'epub',
+  CSV: 'csv',
+  HTML: 'html',
+  XML: 'xml',
+  JSON: 'json'
 } as const;
 
 // File type constants
@@ -131,6 +136,11 @@ export const FILE_TYPES = {
   POWERPOINT: 'PowerPoint',
   TEXT: 'Text',
   MARKDOWN: 'Markdown',
+  EPUB: 'EPUB',
+  CSV: 'CSV',
+  JSON: 'JSON',
+  HTML: 'HTML',
+  XML: 'XML',
   UNKNOWN: 'Unknown'
 } as const;
 
@@ -144,5 +154,10 @@ export const EXTENSION_TO_TYPE_MAP = {
   [FILE_EXTENSIONS.PPT]: FILE_TYPES.POWERPOINT,
   [FILE_EXTENSIONS.PPTX]: FILE_TYPES.POWERPOINT,
   [FILE_EXTENSIONS.TXT]: FILE_TYPES.TEXT,
-  [FILE_EXTENSIONS.MD]: FILE_TYPES.MARKDOWN
+  [FILE_EXTENSIONS.MD]: FILE_TYPES.MARKDOWN,
+  [FILE_EXTENSIONS.CSV]: FILE_TYPES.CSV,
+  [FILE_EXTENSIONS.JSON]: FILE_EXTENSIONS.JSON,
+  [FILE_EXTENSIONS.HTML]: FILE_TYPES.HTML,
+  [FILE_EXTENSIONS.XML]: FILE_TYPES.XML,
+  [FILE_EXTENSIONS.EPUB]: FILE_TYPES.EPUB
 } as const;