Merge remote changes with local modifications

- Add docx and html2pdf.js export functionality (from remote)
- Update backend with new API endpoints
- Sync local configuration changes

backend/main.py

@@ -2,6 +2,8 @@ import asyncio
 import base64
 import json
 import logging
+import os
+import tempfile
 import uuid
 from typing import Optional
 
@@ -14,6 +16,7 @@ from pydantic import BaseModel
 from geoip import get_ip_location_text
 from llm import call_ollama, call_vlm_ocr
 from prompt import build_completion_prompts, prepare_prompt_context
+import markitdown
 
 logging.basicConfig(
     level=logging.INFO,
@@ -73,6 +76,11 @@ class OCRRequest(BaseModel):
     language: str = "auto"
 
 
+class ConvertRequest(BaseModel):
+    file: str
+    filename: str = "document.pdf"
+
+
 def _preview(text: str, limit: int = 80) -> str:
     value = (text or "").replace("\n", "\\n")
     if len(value) <= limit:
@@ -243,6 +251,58 @@ async def ocr_image(request: OCRRequest, api_key: str = Security(get_api_key)):
         return JSONResponse(content={"error": str(e)}, status_code=500)
 
 
+@app.post("/v1/convert")
+async def convert_to_markdown(request: ConvertRequest, api_key: str = Security(get_api_key)):
+    """将文件转换为Markdown格式"""
+    request_id = str(uuid.uuid4())[:8]
+    
+    try:
+        logger.info(
+            "[%s] /v1/convert filename=%s file_base64_chars=%d",
+            request_id,
+            request.filename,
+            len(request.file or ""),
+        )
+        
+        # 解码Base64文件内容
+        file_bytes = base64.b64decode(request.file)
+        logger.info("[%s] /v1/convert decoded file_bytes=%d", request_id, len(file_bytes))
+        
+        # 获取文件扩展名
+        ext = os.path.splitext(request.filename)[1].lower()
+        
+        # 创建临时文件
+        with tempfile.NamedTemporaryFile(delete=False, suffix=ext) as tmp:
+            tmp.write(file_bytes)
+            tmp_path = tmp.name
+        
+        try:
+            # 使用MarkItDown转换为Markdown
+            md = markitdown.MarkItDown()
+            result = md.convert(tmp_path)
+            markdown_text = result.text_content
+            
+            logger.info(
+                "[%s] /v1/convert success text_chars=%d text_preview='%s'",
+                request_id,
+                len(markdown_text or ""),
+                _preview(markdown_text, 120),
+            )
+            
+            return {
+                "markdown": markdown_text,
+                "filename": request.filename
+            }
+        finally:
+            # 清理临时文件
+            if os.path.exists(tmp_path):
+                os.unlink(tmp_path)
+                
+    except Exception as e:
+        logger.exception("[%s] /v1/convert failed: %s", request_id, e)
+        return JSONResponse(content={"error": str(e)}, status_code=500)
+
+
 if __name__ == "__main__":
     import uvicorn
 

backend/requirements.txt

@@ -5,3 +5,8 @@ pydantic
 python-dotenv
 httpx
 geoip2
+markitdown
+python-docx
+python-pptx
+openpyxl
+pypdf