✨ Add support for new filetypes

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;

frontend/public/locales/en/common.json

@@ -75,10 +75,10 @@
   "chatInput.thisFileTypeCannotBePreviewed": "This file type cannot be previewed",
   "chatInput.fileCountExceedsLimit": "File count exceeds limit. Maximum {{count}} files allowed",
   "chatInput.fileSizeExceedsLimit": "File \"{{name}}\" exceeds size limit. Maximum 10MB per file",
-  "chatInput.unsupportedFileType": "File \"{{name}}\" is not a supported file type. Supported formats: images, documents (PDF, Word, Excel, PPT), text files, CSV/TSV, Markdown",
+  "chatInput.unsupportedFileType": "File \"{{name}}\" is not a supported file type. Supported formats: images, documents (PDF, Word, Excel, PPT), text files, CSV/TSV, Markdown、JSON、HTML、XML",
   "chatInput.unsupportedFileTypeSimple": "Unsupported file type",
   "chatInput.dragAndDropFilesHere": "Drag and drop files here to upload",
-  "chatInput.supportedFileFormats": "Supported formats: images, documents (PDF, Word, Excel, PPT), text files, CSV/TSV, Markdown",
+  "chatInput.supportedFileFormats": "Supported formats: images, documents (PDF, Word, Excel, PPT, EPUB), text files, CSV/TSV, Markdown、JSON、HTML、XML",
   "chatInput.sendMessageTo": "Send message to {{appName}}",
   "chatInput.stopRecording": "Stop Recording",
   "chatInput.startRecording": "Start Recording",
@@ -443,13 +443,13 @@
   "knowledgeBase.hint.selectFirst": "Please select a knowledge base to upload files",
   "knowledgeBase.hint.changeName": "Please modify the knowledge base name to continue",
   "knowledgeBase.upload.dragHint": "Click or drag files to this area to upload and add knowledge to the knowledge base",
-  "knowledgeBase.upload.supportedFormats": "Supports PDF, Word, PPT, Excel, MD, TXT file formats",
+  "knowledgeBase.upload.supportedFormats": "Supports PDF, Word, PPT, Excel, MD, TXT, EPUB, CSV, JSON, HTML, XML file formats",
   "knowledgeBase.upload.completed": "Upload completed",
   "knowledgeBase.upload.fileCount": "{{count}} files",
   "knowledgeBase.upload.status.uploading": "Uploading",
   "knowledgeBase.upload.status.completed": "Completed",
   "knowledgeBase.upload.status.failed": "Upload failed",
-  "knowledgeBase.upload.invalidFileType": "Only PDF, Word, PPT, Excel, MD, TXT, CSV file formats are supported!",
+  "knowledgeBase.upload.invalidFileType": "Only PDF, Word, PPT, Excel, MD, TXT, CSV, JSON, EPUB, HTML, XML file formats are supported!",
   "knowledgeBase.check.nameError": "Failed to check knowledge base name",
   "knowledgeBase.fetch.error": "Failed to fetch knowledge base information",
   "knowledgeBase.fetch.retryError": "Failed to fetch knowledge base information, please try again later",

frontend/public/locales/zh/common.json

@@ -75,10 +75,10 @@
   "chatInput.thisFileTypeCannotBePreviewed": "此文件类型无法预览",
   "chatInput.fileCountExceedsLimit": "文件数量超过限制，最多只能上传{{count}}个文件",
   "chatInput.fileSizeExceedsLimit": "文件\"{{name}}\"超过大小限制，单个文件最大10MB",
-  "chatInput.unsupportedFileType": "文件\"{{name}}\"不是支持的文件类型，支持的格式包括：图片、文档（PDF、Word、Excel、PPT）、纯文本、CSV/TSV、Markdown",
+  "chatInput.unsupportedFileType": "文件\"{{name}}\"不是支持的文件类型，支持的格式包括：图片、文档（PDF、Word、Excel、PPT、EPUB）、纯文本、CSV/TSV、Markdown、JSON、HTML、XML",
   "chatInput.unsupportedFileTypeSimple": "不支持的文件类型",
   "chatInput.dragAndDropFilesHere": "文件拖动到此处即可上传",
-  "chatInput.supportedFileFormats": "支持的格式包括：图片、文档（PDF、Word、Excel、PPT）、纯文本、CSV/TSV、Markdown",
+  "chatInput.supportedFileFormats": "支持的格式包括：图片、文档（PDF、Word、Excel、PPT、EPUB）、纯文本、CSV/TSV、Markdown、JSON、HTML、XML",
   "chatInput.sendMessageTo": "给 {{appName}} 发送消息",
   "chatInput.stopRecording": "停止录音",
   "chatInput.startRecording": "开始录音",
@@ -446,13 +446,13 @@
   "knowledgeBase.hint.selectFirst": "请先选择一个知识库以上传文件",
   "knowledgeBase.hint.changeName": "请修改知识库名称后继续",
   "knowledgeBase.upload.dragHint": "点击或拖拽文件到此区域上传，为知识库添加知识",
-  "knowledgeBase.upload.supportedFormats": "支持 PDF、Word、Excel、PPT、纯文本、CSV、TSV、Markdown 文件格式",
+  "knowledgeBase.upload.supportedFormats": "支持 PDF、Word、Excel、PPT、纯文本、CSV、TSV、Markdown、JSON、EPUB、HTML、XML 文件格式",
   "knowledgeBase.upload.completed": "上传完成",
   "knowledgeBase.upload.fileCount": "{{count}} 个文件",
   "knowledgeBase.upload.status.uploading": "上传中",
   "knowledgeBase.upload.status.completed": "已完成",
   "knowledgeBase.upload.status.failed": "上传失败",
-  "knowledgeBase.upload.invalidFileType": "只支持 PDF、Word、PPT、Excel、MD、TXT、CSV 文件格式！",
+  "knowledgeBase.upload.invalidFileType": "只支持 PDF、Word、PPT、Excel、MD、TXT、CSV、JSON、EPUB、HTML、XML 文件格式！",
   "knowledgeBase.check.nameError": "检查知识库名称失败",
   "knowledgeBase.fetch.error": "获取知识库信息失败",
   "knowledgeBase.fetch.retryError": "获取知识库信息失败，请稍后重试",

frontend/services/uploadService.ts

@@ -57,7 +57,13 @@ export const validateFileType = (file: File, t: TFunction, message: any): boolea
     'text/markdown',
     'text/plain',
     'text/csv',
-    'application/csv'
+    'application/csv',
+    'application/epub',
+    'application/epub+zip',
+    'text/html',
+    'application/json',
+    'application/xml',
+    'text/xml'
   ];
 
   // First check MIME type

sdk/nexent/data_process/core.py

@@ -17,7 +17,7 @@ class DataProcessCore:
 
     Supported file types:
     - Excel files: .xlsx, .xls
-    - Generic files: .txt, .pdf, .docx, .doc, .html, .htm, .md, .rtf, .odt, .pptx, .ppt
+    - Generic files: .txt, .pdf, .docx, .doc, .html, .htm, .md, .rtf, .odt, .pptx, .ppt, .epub, .xml, .csv, .json
 
     Supported input methods:
     - In-memory byte data
@@ -147,6 +147,10 @@ def get_supported_file_types(self) -> Dict[str, List[str]]:
                 ".odt",
                 ".pptx",
                 ".ppt",
+                ".epub",
+                ".json",
+                ".xml",
+                ".csv",
             ]
 
         return {"excel": list(self.EXCEL_EXTENSIONS), "generic": generic_formats}