feat(layout): 更新应用名称为表易智融

- 将MainLayout组件中的应用名称从"智联文档"更新为"表易智融"
- 更新侧边栏标题显示新的应用名称
- 统一所有相关界面的文字标识

fix(assistant): 同步更新AI助手介绍文本

- 更新Assistant页面中AI助手的自我介绍内容
- 将欢迎消息中的应用名称替换为"表易智融"

docs(dashboard): 更新欢迎页面应用名称

- 修改Dashboard页面欢迎消息中的应用名称展示
- 确保用户界面的一致性体验

refactor(instruction-chat): 更新指令聊天页面助手名称

- 同步更新InstructionChat页面中AI助手的介绍文本
- 保持整个应用中品牌名称的统一性

.claude/settings.local.json

@@ -0,0 +1,7 @@
+{
+  "permissions": {
+    "allow": [
+      "WebSearch"
+    ]
+  }
+}

.env.example

@@ -0,0 +1,35 @@
+# ============================================================
+# FilesReadSystem 环境变量配置模板
+# 复制此文件为 .env 并填入实际值
+# ============================================================
+
+# ==================== 应用配置 ====================
+DEBUG=false
+
+# ==================== MongoDB ====================
+MONGO_ROOT_USER=admin
+MONGO_ROOT_PASSWORD=your_mongo_password
+MONGODB_DB_NAME=document_system
+
+# ==================== MySQL ====================
+MYSQL_PASSWORD=your_mysql_password
+MYSQL_DATABASE=document
+
+# ==================== Redis ====================
+REDIS_PASSWORD=your_redis_password
+
+# ==================== LLM AI ====================
+LLM_API_KEY=your_llm_api_key
+LLM_BASE_URL=https://api.deepseek.com
+LLM_MODEL_NAME=deepseek-chat
+
+# ==================== Supabase ====================
+SUPABASE_URL=https://your-project.supabase.co
+SUPABASE_ANON_KEY=your_anon_key
+SUPABASE_SERVICE_KEY=your_service_key
+
+# ==================== Embedding / RAG ====================
+EMBEDDING_MODEL=all-MiniLM-L6-v2
+
+# ==================== 前端配置 ====================
+VITE_APP_ID=your_app_id

README.md

@@ -1,4 +1,4 @@
-# FilesReadSystem
+# 智联文档
 
 ## 项目介绍 / Project Introduction
 
@@ -26,37 +26,79 @@ A document understanding and multi-source data fusion system based on Large Lang
 
 ## 项目架构 / Project Architecture
 
+```mermaid
+flowchart TB
+    subgraph UI["用户界面 / User Interface"]
+        Frontend["React + TypeScript + shadcn/ui"]
+    end
+
+    subgraph Backend["FastAPI 后端 / Backend"]
+        Upload["上传 API<br/>/upload"]
+        Documents["文档管理<br/>/documents"]
+        RAG["RAG 检索<br/>/rag/search"]
+        AI["AI 分析<br/>/ai/analyze"]
+        Template["模板填充<br/>/templates/fill"]
+        Instruction["自然语言指令<br/>/instruction/execute"]
+        Visual["可视化<br/>/visualization"]
+    end
+
+    subgraph Data["数据层 / Data Layer"]
+        MongoDB["MongoDB<br/>文档存储"]
+        MySQL["MySQL<br/>结构化数据"]
+        Redis["Redis<br/>缓存/队列"]
+        FAISS["FAISS<br/>向量索引"]
+    end
+
+    UI --> Backend
+    Backend --> MongoDB
+    Backend --> MySQL
+    Backend --> Redis
+    MongoDB --> FAISS
 ```
-┌─────────────────────────────────────────────────────────────────┐
+
-│                         User Interface                           │
+---
-│              (React + TypeScript + shadcn/ui)                    │
+
-└─────────────────────────────────────────────────────────────────┘
+## 程序流程 / Program Flow
-                                │
+
-                                ▼
+```mermaid
-┌─────────────────────────────────────────────────────────────────┐
+flowchart TD
-│                      FastAPI Backend                             │
+    Start([用户上传文档<br/>User Uploads Document]) --> Parse{解析文档格式<br/>Parse Document Format}
-│  ┌─────────────┐  ┌──────────────┐  ┌─────────────────────────┐ │
+
-│  │ Upload API  │  │ RAG Search   │  │ Natural Language       │ │
+    Parse -->|Excel| ParseXlsx["解析 Excel<br/>Parse XLSX"]
-│  │ /documents  │  │ /rag/search  │  │ /instruction/execute   │ │
+    Parse -->|Word| ParseDocx["解析 Word<br/>Parse DOCX"]
-│  └─────────────┘  └──────────────┘  └─────────────────────────┘ │
+    Parse -->|Markdown| ParseMd["解析 Markdown<br/>Parse Markdown"]
-│  ┌─────────────┐  ┌──────────────┐  ┌─────────────────────────┐ │
+    Parse -->|Text| ParseTxt["解析文本<br/>Parse Text"]
-│  │ AI Analyze  │  │ Template Fill│  │ Visualization          │ │
+
-│  │ /ai/analyze │  │ /templates   │  │ /visualization         │ │
+    ParseXlsx --> Store1[(存储到<br/>MongoDB)]
-│  └─────────────┘  └──────────────┘  └─────────────────────────┘ │
+    ParseDocx --> Store1
-└─────────────────────────────────────────────────────────────────┘
+    ParseMd --> Store1
-                                │
+    ParseTxt --> Store1
-          ┌─────────────────────┼─────────────────────┐
+
-          ▼                     ▼                     ▼
+    Store1 --> Embed["Embedding 向量化<br/>Create Embeddings"]
-┌─────────────────┐   ┌─────────────────┐   ┌─────────────────┐
+    Embed --> Index[(索引到<br/>FAISS)]
-│    MongoDB      │   │      MySQL      │   │      Redis      │
+
-│  (Documents)    │   │  (Structured)   │   │   (Cache/Queue) │
+    Index --> TaskCreated{创建任务<br/>Create Task}
-└─────────────────┘   └─────────────────┘   └─────────────────┘
+
-          │
+    TaskCreated -->|同步| ProcessSync["同步处理<br/>Sync Process"]
-          ▼
+    TaskCreated -->|异步| QueueTask["加入任务队列<br/>Queue to Celery"]
-┌─────────────────┐
+
-│     FAISS       │
+    ProcessSync --> ReturnResult["返回结果<br/>Return Result"]
-│ (Vector Index)  │
+
-└─────────────────┘
+    QueueTask --> CeleryWorker["Celery Worker<br/>异步处理"]
+    CeleryWorker --> LLM["调用 LLM<br/>Call LLM API"]
+    LLM --> StoreResult["存储结果<br/>Store Result"]
+    StoreResult --> ReturnAsync["返回任务ID<br/>Return Task ID"]
+
+    ReturnResult --> End([完成<br/>Complete])
+    ReturnAsync --> Poll{轮询任务状态<br/>Poll Task Status}
+    Poll -->|进行中| Poll
+    Poll -->|完成| GetResult["获取结果<br/>Get Result"]
+    GetResult --> End
+
+    style Start fill:#e1f5fe
+    style End fill:#c8e6c9
+    style LLM fill:#fff3e0
+    style CeleryWorker fill:#fff3e0
 ```
 
 ---
@@ -233,6 +275,77 @@ pnpm dev
 
 ---
 
+## Docker 部署 / Docker Deployment
+
+### 快速启动 / Quick Start
+
+```bash
+# 1. 复制环境变量模板并编辑
+cp .env.example .env
+# 编辑 .env 填入实际配置
+
+# 2. 启动所有服务
+docker compose up -d
+
+# 3. 查看日志
+docker compose logs -f
+
+# 4. 检查服务状态
+docker compose ps
+
+# 5. 更新部署
+docker compose up -d --build
+```
+
+### 服务说明 / Services
+
+| 服务 | 端口 | 说明 |
+|:---|:---|:---|
+| frontend | 80 | React 前端 (Nginx) |
+| backend | 8000 | FastAPI 后端 |
+| mongodb | 27017 | MongoDB 数据库 |
+| mysql | 3306 | MySQL 数据库 |
+| redis | 6379 | Redis 缓存/队列 |
+
+### 环境变量 / Environment Variables
+
+创建 `.env` 文件，参考 `.env.example`:
+
+```bash
+# 数据库配置
+MONGO_ROOT_USER=admin
+MONGO_ROOT_PASSWORD=your_password
+MONGODB_DB_NAME=document_system
+MYSQL_PASSWORD=your_password
+MYSQL_DATABASE=document
+REDIS_PASSWORD=your_password
+
+# LLM 配置
+LLM_API_KEY=your_api_key
+LLM_BASE_URL=https://api.deepseek.com
+LLM_MODEL_NAME=deepseek-chat
+
+# Supabase 配置
+SUPABASE_URL=https://your-project.supabase.co
+SUPABASE_ANON_KEY=your_anon_key
+SUPABASE_SERVICE_KEY=your_service_key
+```
+
+### 验证部署 / Verify Deployment
+
+```bash
+# 检查所有服务状态
+docker compose ps
+
+# 访问前端
+curl http://localhost
+
+# 检查后端健康
+curl http://localhost:8000/health
+```
+
+---
+
 ## 许可证 / License
 
 ISC

backend/.env.example

@@ -34,9 +34,9 @@ REDIS_URL="redis://localhost:6379/0"
 #   - 模型: glm-4-flash (快速文本模型), glm-4 (标准), glm-4-plus (高性能)
 #   - API: https://open.bigmodel.cn
 #   - API Key: https://open.bigmodel.cn/usercenter/apikeys
-LLM_API_KEY="ca79ad9f96524cd5afc3e43ca97f347d.cpiLLx2oyitGvTeU"
+LLM_API_KEY="your_llm_api_key_here"
-LLM_BASE_URL="https://open.bigmodel.cn/api/paas/v4"
+LLM_BASE_URL="https://api.deepseek.com"
-LLM_MODEL_NAME="glm-4v-plus"
+LLM_MODEL_NAME="deepseek-chat"
 
 # ==================== Supabase 配置 ====================
 # Supabase 项目配置
@@ -45,10 +45,14 @@ SUPABASE_ANON_KEY="your_supabase_anon_key_here"
 SUPABASE_SERVICE_KEY="your_supabase_service_key_here"
 
 # ==================== 文件路径配置 ====================
-# 上传文件存储目录 (相对于项目根目录)
+# 上传文件存储目录
+# 本地开发: ./data/uploads
+# Docker部署: /app/data/uploads
 UPLOAD_DIR="./data/uploads"
 
-# Faiss 向量数据库持久化目录 (LangChain + Faiss 实现)
+# Faiss 向量数据库持久化目录
+# 本地开发: ./data/faiss
+# Docker部署: /app/data/faiss
 FAISS_INDEX_DIR="./data/faiss"
 
 # ==================== RAG 配置 ====================

backend/=4.0.0

@@ -0,0 +1,7 @@
+Collecting reportlab
+  Using cached reportlab-4.4.10-py3-none-any.whl.metadata (1.7 kB)
+Requirement already satisfied: pillow>=9.0.0 in d:\code\filesreadsystem\backend\venv\lib\site-packages (from reportlab) (12.1.1)
+Requirement already satisfied: charset-normalizer in d:\code\filesreadsystem\backend\venv\lib\site-packages (from reportlab) (3.4.6)
+Using cached reportlab-4.4.10-py3-none-any.whl (2.0 MB)
+Installing collected packages: reportlab
+Successfully installed reportlab-4.4.10

backend/Dockerfile

@@ -0,0 +1,40 @@
+# ============================================================
+# FilesReadSystem Backend Docker Image
+# ============================================================
+FROM python:3.12-slim
+
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV PYTHONUNBUFFERED=1
+
+# 安装系统依赖 (FAISS, Pillow, tesseract 等)
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    gcc \
+    g++ \
+    libgl1-mesa-glx \
+    libglib2.0-0 \
+    tesseract-ocr \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+# 先复制依赖文件，再安装（利用 Docker 缓存）
+COPY requirements.txt .
+
+# 安装 Python 依赖
+RUN pip install --no-cache-dir -r requirements.txt
+
+# 复制应用代码
+COPY app/ ./app/
+
+# 创建数据目录
+RUN mkdir -p /app/data/uploads /app/data/faiss /app/data/logs
+
+# 暴露端口
+EXPOSE 8000
+
+# 健康检查
+HEALTHCHECK --interval=30s --timeout=10s --start-period=10s --retries=3 \
+    CMD python -c "import httpx; httpx.get('http://localhost:8000/health')" || exit 1
+
+# 启动命令
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]

backend/app/api/__init__.py

@@ -15,6 +15,7 @@ from app.api.endpoints import (
     health,
     instruction,    # 智能指令
     conversation,   # 对话历史
+    pdf_converter,  # PDF转换
 )
 
 # 创建主路由
@@ -33,3 +34,4 @@ api_router.include_router(visualization.router)    # 可视化
 api_router.include_router(analysis_charts.router)  # 分析图表
 api_router.include_router(instruction.router)      # 智能指令
 api_router.include_router(conversation.router)     # 对话历史
+api_router.include_router(pdf_converter.router)   # PDF转换

backend/app/api/endpoints/ai_analyze.py

@@ -1,7 +1,7 @@
 """
 AI 分析 API 接口
 """
-from fastapi import APIRouter, UploadFile, File, HTTPException, Query, Body
+from fastapi import APIRouter, UploadFile, File, HTTPException, Query, Body, Form
 from fastapi.responses import StreamingResponse
 from typing import Optional
 import logging
@@ -21,7 +21,8 @@ router = APIRouter(prefix="/ai", tags=["AI 分析"])
 
 @router.post("/analyze/excel")
 async def analyze_excel(
-    file: UploadFile = File(...),
+    file: Optional[UploadFile] = File(None),
+    doc_id: Optional[str] = Form(None, description="文档ID（从数据库读取）"),
     user_prompt: str = Query("", description="用户自定义提示词"),
     analysis_type: str = Query("general", description="分析类型: general, summary, statistics, insights"),
     parse_all_sheets: bool = Query(False, description="是否分析所有工作表")
@@ -30,7 +31,8 @@ async def analyze_excel(
     上传并使用 AI 分析 Excel 文件
 
     Args:
-        file: 上传的 Excel 文件
+        file: 上传的 Excel 文件（与 doc_id 二选一）
+        doc_id: 文档ID（从数据库读取）
         user_prompt: 用户自定义提示词
         analysis_type: 分析类型
         parse_all_sheets: 是否分析所有工作表
@@ -38,7 +40,57 @@ async def analyze_excel(
     Returns:
         dict: 分析结果，包含 Excel 数据和 AI 分析结果
     """
-    # 检查文件类型
+    filename = None
+
+    # 从数据库读取模式
+    if doc_id:
+        try:
+            from app.core.database.mongodb import mongodb
+            doc = await mongodb.get_document(doc_id)
+            if not doc:
+                raise HTTPException(status_code=404, detail=f"文档不存在: {doc_id}")
+
+            filename = doc.get("metadata", {}).get("original_filename", "unknown.xlsx")
+            file_ext = filename.split('.')[-1].lower()
+
+            if file_ext not in ['xlsx', 'xls']:
+                raise HTTPException(status_code=400, detail=f"文档类型不是 Excel: {file_ext}")
+
+            file_path = doc.get("metadata", {}).get("file_path")
+            if not file_path:
+                raise HTTPException(status_code=400, detail="文档没有存储文件路径，请重新上传")
+
+            # 使用文件路径进行 AI 分析
+            if parse_all_sheets:
+                result = await excel_ai_service.batch_analyze_sheets_from_path(
+                    file_path=file_path,
+                    filename=filename,
+                    user_prompt=user_prompt,
+                    analysis_type=analysis_type
+                )
+            else:
+                result = await excel_ai_service.analyze_excel_file_from_path(
+                    file_path=file_path,
+                    filename=filename,
+                    user_prompt=user_prompt,
+                    analysis_type=analysis_type
+                )
+
+            if result.get("success"):
+                return result
+            else:
+                return result
+
+        except HTTPException:
+            raise
+        except Exception as e:
+            logger.error(f"从数据库读取 Excel 文档失败: {str(e)}")
+            raise HTTPException(status_code=500, detail=f"读取文档失败: {str(e)}")
+
+    # 文件上传模式
+    if not file:
+        raise HTTPException(status_code=400, detail="请提供文件或文档ID")
+
     if not file.filename:
         raise HTTPException(status_code=400, detail="文件名为空")
 
@@ -61,7 +113,11 @@ async def analyze_excel(
         # 读取文件内容
         content = await file.read()
 
-        logger.info(f"开始分析文件: {file.filename}, 分析类型: {analysis_type}")
+        # 验证文件内容不为空
+        if not content:
+            raise HTTPException(status_code=400, detail="文件内容为空，请确保文件已正确上传")
+
+        logger.info(f"开始分析文件: {file.filename}, 分析类型: {analysis_type}, 文件大小: {len(content)} bytes")
 
         # 调用 AI 分析服务
         if parse_all_sheets:
@@ -155,7 +211,7 @@ async def analyze_text(
 @router.post("/analyze/md")
 async def analyze_markdown(
     file: Optional[UploadFile] = File(None),
-    doc_id: Optional[str] = Query(None, description="文档ID（从数据库读取）"),
+    doc_id: Optional[str] = Form(None, description="文档ID（从数据库读取）"),
     analysis_type: str = Query("summary", description="分析类型: summary, outline, key_points, questions, tags, qa, statistics, section, charts"),
     user_prompt: str = Query("", description="用户自定义提示词"),
     section_number: Optional[str] = Query(None, description="指定章节编号，如 '一' 或 '（一）'")
@@ -198,7 +254,7 @@ async def analyze_markdown(
             if file_ext not in ['md', 'markdown']:
                 raise HTTPException(status_code=400, detail=f"文档类型不是 Markdown: {file_ext}")
 
-            content = doc.get("content", "")
+            content = doc.get("content") or ""
             if not content:
                 raise HTTPException(status_code=400, detail="文档内容为空")
 
@@ -392,7 +448,7 @@ async def get_markdown_outline(
 @router.post("/analyze/txt")
 async def analyze_txt(
     file: Optional[UploadFile] = File(None),
-    doc_id: Optional[str] = Query(None, description="文档ID（从数据库读取）"),
+    doc_id: Optional[str] = Form(None, description="文档ID（从数据库读取）"),
     analysis_type: str = Query("structured", description="分析类型: structured, charts")
 ):
     """
@@ -427,7 +483,7 @@ async def analyze_txt(
                 raise HTTPException(status_code=400, detail=f"文档类型不是 TXT: {file_ext}")
 
             # 使用数据库中的 content
-            text_content = doc.get("content", "")
+            text_content = doc.get("content") or ""
 
             if not text_content:
                 raise HTTPException(status_code=400, detail="文档内容为空")
@@ -498,8 +554,8 @@ async def analyze_txt(
 @router.post("/analyze/word")
 async def analyze_word(
     file: Optional[UploadFile] = File(None),
-    doc_id: Optional[str] = Query(None, description="文档ID（从数据库读取）"),
+    doc_id: Optional[str] = Form(None, description="文档ID（从数据库读取）"),
-    user_hint: str = Query("", description="用户提示词，如'请提取表格数据'"),
+    user_hint: str = Form("", description="用户提示词，如'请提取表格数据'"),
     analysis_type: str = Query("structured", description="分析类型: structured, charts")
 ):
     """
@@ -536,8 +592,9 @@ async def analyze_word(
                 raise HTTPException(status_code=400, detail=f"文档类型不是 Word: {file_ext}")
 
             # 使用数据库中的 content 进行分析
-            content = doc.get("content", "")
+            content = doc.get("content", "") or ""
-            tables = doc.get("structured_data", {}).get("tables", [])
+            structured_data = doc.get("structured_data") or {}
+            tables = structured_data.get("tables", [])
 
             # 调用 AI 分析服务，传入数据库内容
             if analysis_type == "charts":

backend/app/api/endpoints/pdf_converter.py

@@ -0,0 +1,208 @@
+"""
+PDF 转换 API 接口
+
+提供将 Word、Excel、Txt、Markdown 转换为 PDF 的功能
+"""
+import logging
+import uuid
+from typing import Optional
+
+from fastapi import APIRouter, UploadFile, File, Form, HTTPException
+from fastapi.responses import StreamingResponse
+
+from app.services.pdf_converter_service import pdf_converter_service
+from app.services.file_service import file_service
+
+logger = logging.getLogger(__name__)
+
+router = APIRouter(prefix="/pdf", tags=["PDF转换"])
+
+# 临时存储转换后的 PDF（key: download_id, value: (pdf_content, original_filename)）
+_pdf_cache: dict = {}
+
+
+# ==================== 请求/响应模型 ====================
+
+class ConvertResponse:
+    """转换响应"""
+    def __init__(self, success: bool, message: str = "", filename: str = ""):
+        self.success = success
+        self.message = message
+        self.filename = filename
+
+
+# ==================== 接口 ====================
+
+@router.post("/convert")
+async def convert_to_pdf(
+    file: UploadFile = File(...),
+):
+    """
+    将上传的文件转换为 PDF
+
+    支持格式: docx, xlsx, txt, md
+
+    Args:
+        file: 上传的文件
+
+    Returns:
+        PDF 文件流
+    """
+    try:
+        # 检查文件格式
+        filename = file.filename or "document"
+        file_ext = filename.rsplit('.', 1)[-1].lower() if '.' in filename else ''
+
+        if file_ext not in pdf_converter_service.supported_formats:
+            raise HTTPException(
+                status_code=400,
+                detail=f"不支持的格式: {file_ext}，支持的格式: {', '.join(pdf_converter_service.supported_formats)}"
+            )
+
+        # 读取文件内容
+        content = await file.read()
+        if not content:
+            raise HTTPException(status_code=400, detail="文件内容为空")
+
+        logger.info(f"开始转换文件: {filename} ({file_ext})")
+
+        # 转换为 PDF
+        pdf_content, error = await pdf_converter_service.convert_to_pdf(
+            file_content=content,
+            source_format=file_ext,
+            filename=filename.rsplit('.', 1)[0] if '.' in filename else filename
+        )
+
+        if error:
+            raise HTTPException(status_code=500, detail=error)
+
+        # 直接返回 PDF 文件流
+        return StreamingResponse(
+            iter([pdf_content]),
+            media_type="application/pdf",
+            headers={
+                "Content-Disposition": f"attachment; filename*=UTF-8''converted.pdf"
+            }
+        )
+
+    except HTTPException:
+        raise
+    except Exception as e:
+        logger.error(f"PDF转换失败: {e}")
+        raise HTTPException(status_code=500, detail=f"转换失败: {str(e)}")
+
+
+@router.get("/download/{download_id}")
+async def download_pdf(download_id: str):
+    """
+    通过下载 ID 下载 PDF（支持 IDM 拦截）
+    """
+    if download_id not in _pdf_cache:
+        raise HTTPException(status_code=404, detail="下载链接已过期或不存在")
+
+    pdf_content, filename = _pdf_cache.pop(download_id)  # 下载后删除
+
+    # 使用 RFC 5987 编码支持中文文件名
+    from starlette.responses import StreamingResponse
+    import urllib.parse
+
+    # URL 编码中文文件名
+    encoded_filename = urllib.parse.quote(f"{filename}.pdf")
+
+    return StreamingResponse(
+        iter([pdf_content]),
+        media_type="application/pdf",
+        headers={
+            "Content-Disposition": f"attachment; filename*=UTF-8''{encoded_filename}"
+        }
+    )
+
+
+@router.get("/formats")
+async def get_supported_formats():
+    """
+    获取支持的源文件格式
+
+    Returns:
+        支持的格式列表
+    """
+    return {
+        "success": True,
+        "formats": pdf_converter_service.get_supported_formats()
+    }
+
+
+@router.post("/convert/batch")
+async def batch_convert_to_pdf(
+    files: list[UploadFile] = File(...),
+):
+    """
+    批量将多个文件转换为 PDF
+
+    注意: 批量转换会返回多个 PDF 文件打包的 zip
+
+    Args:
+        files: 上传的文件列表
+
+    Returns:
+        ZIP 压缩包（包含所有PDF）
+    """
+    try:
+        import io
+        import zipfile
+
+        results = []
+        errors = []
+
+        for file in files:
+            try:
+                filename = file.filename or "document"
+                file_ext = filename.rsplit('.', 1)[-1].lower() if '.' in filename else ''
+
+                if file_ext not in pdf_converter_service.supported_formats:
+                    errors.append(f"{filename}: 不支持的格式")
+                    continue
+
+                content = await file.read()
+                pdf_content, error = await pdf_converter_service.convert_to_pdf(
+                    file_content=content,
+                    source_format=file_ext,
+                    filename=filename.rsplit('.', 1)[0] if '.' in filename else filename
+                )
+
+                if error:
+                    errors.append(f"{filename}: {error}")
+                else:
+                    results.append((filename, pdf_content))
+
+            except Exception as e:
+                errors.append(f"{file.filename}: {str(e)}")
+
+        if not results:
+            raise HTTPException(
+                status_code=400,
+                detail=f"没有可转换的文件。错误: {'; '.join(errors)}"
+            )
+
+        # 创建 ZIP 包
+        zip_buffer = io.BytesIO()
+        with zipfile.ZipFile(zip_buffer, 'w', zipfile.ZIP_DEFLATED) as zip_file:
+            for original_name, pdf_content in results:
+                pdf_name = f"{original_name.rsplit('.', 1)[0] if '.' in original_name else original_name}.pdf"
+                zip_file.writestr(pdf_name, pdf_content)
+
+        zip_buffer.seek(0)
+
+        return StreamingResponse(
+            iter([zip_buffer.getvalue()]),
+            media_type="application/zip",
+            headers={
+                "Content-Disposition": "attachment; filename*=UTF-8''converted_pdfs.zip"
+            }
+        )
+
+    except HTTPException:
+        raise
+    except Exception as e:
+        logger.error(f"批量PDF转换失败: {e}")
+        raise HTTPException(status_code=500, detail=f"批量转换失败: {str(e)}")

backend/app/celery_app.py

@@ -0,0 +1,27 @@
+# ============================================================
+# Celery 应用配置
+# ============================================================
+from celery import Celery
+
+# 优先使用环境变量，否则使用默认值
+import os
+
+CELERY_BROKER_URL = os.getenv("CELERY_BROKER_URL", "redis://localhost:6379/1")
+CELERY_RESULT_BACKEND = os.getenv("CELERY_RESULT_BACKEND", "redis://localhost:6379/2")
+
+celery_app = Celery(
+    "filesread",
+    broker=CELERY_BROKER_URL,
+    backend=CELERY_RESULT_BACKEND,
+)
+
+celery_app.conf.update(
+    task_serializer="json",
+    accept_content=["json"],
+    result_serializer="json",
+    timezone="Asia/Shanghai",
+    enable_utc=True,
+    task_track_started=True,
+    task_time_limit=3600,  # 1小时超时
+    worker_prefetch_multiplier=1,
+)

backend/app/core/document_parser/docx_parser.py

@@ -91,11 +91,15 @@ class DocxParser(BaseParser):
                 table_rows.append(row_data)
 
             if table_rows:
+                # 第一行作为表头，其余行作为数据
+                headers = table_rows[0] if table_rows else []
+                data_rows = table_rows[1:] if len(table_rows) > 1 else []
                 tables_data.append({
                     "table_index": i,
-                    "rows": table_rows,
+                    "headers": headers,  # 添加 headers 字段
-                    "row_count": len(table_rows),
+                    "rows": data_rows,  # 数据行（不含表头）
-                    "column_count": len(table_rows[0]) if table_rows else 0
+                    "row_count": len(data_rows),
+                    "column_count": len(headers) if headers else 0
                 })
 
         # 提取图片/嵌入式对象信息

backend/app/main.py

@@ -34,8 +34,8 @@ def setup_logging():
     # 根日志配置
     log_level = logging.DEBUG if settings.DEBUG else logging.INFO
 
-    # 日志目录
+    # 日志目录 (使用 settings.BASE_DIR 确保跨平台一致)
-    log_dir = Path("data/logs")
+    log_dir = settings.BASE_DIR / "data" / "logs"
     log_dir.mkdir(parents=True, exist_ok=True)
 
     # 日志文件路径

backend/app/services/excel_ai_service.py

@@ -223,6 +223,177 @@ class ExcelAIService:
             }
         }
 
+    async def analyze_excel_file_from_path(
+        self,
+        file_path: str,
+        filename: str,
+        user_prompt: str = "",
+        analysis_type: str = "general",
+        parse_options: Optional[Dict[str, Any]] = None
+    ) -> Dict[str, Any]:
+        """
+        从文件路径分析 Excel 文件（用于从数据库加载的文档）
+
+        Args:
+            file_path: Excel 文件路径
+            filename: 文件名
+            user_prompt: 用户自定义提示词
+            analysis_type: 分析类型
+            parse_options: 解析选项
+
+        Returns:
+            Dict[str, Any]: 分析结果
+        """
+        # 1. 解析 Excel 文件
+        excel_data = None
+        parse_result_metadata = None
+        try:
+            parse_options = parse_options or {}
+            parse_result = self.parser.parse(file_path, **parse_options)
+
+            if not parse_result.success:
+                return {
+                    "success": False,
+                    "error": parse_result.error,
+                    "analysis": None
+                }
+
+            excel_data = parse_result.data
+            parse_result_metadata = parse_result.metadata
+            logger.info(f"Excel 解析成功: {parse_result_metadata}")
+
+        except Exception as e:
+            logger.error(f"Excel 解析失败: {str(e)}")
+            return {
+                "success": False,
+                "error": f"Excel 解析失败: {str(e)}",
+                "analysis": None
+            }
+
+        # 2. 调用 LLM 进行分析
+        try:
+            if user_prompt and user_prompt.strip():
+                llm_result = await self.llm_service.analyze_with_template(
+                    excel_data,
+                    user_prompt
+                )
+            else:
+                llm_result = await self.llm_service.analyze_excel_data(
+                    excel_data,
+                    user_prompt,
+                    analysis_type
+                )
+
+            logger.info(f"AI 分析完成: {llm_result['success']}")
+
+            return {
+                "success": True,
+                "excel": {
+                    "data": excel_data,
+                    "metadata": parse_result_metadata,
+                    "saved_path": file_path
+                },
+                "analysis": llm_result
+            }
+
+        except Exception as e:
+            logger.error(f"AI 分析失败: {str(e)}")
+            return {
+                "success": False,
+                "error": f"AI 分析失败: {str(e)}",
+                "excel": {
+                    "data": excel_data,
+                    "metadata": parse_result_metadata
+                },
+                "analysis": None
+            }
+
+    async def batch_analyze_sheets_from_path(
+        self,
+        file_path: str,
+        filename: str,
+        user_prompt: str = "",
+        analysis_type: str = "general"
+    ) -> Dict[str, Any]:
+        """
+        从文件路径批量分析 Excel 文件的所有工作表（用于从数据库加载的文档）
+
+        Args:
+            file_path: Excel 文件路径
+            filename: 文件名
+            user_prompt: 用户自定义提示词
+            analysis_type: 分析类型
+
+        Returns:
+            Dict[str, Any]: 分析结果
+        """
+        # 1. 解析所有工作表
+        try:
+            parse_result = self.parser.parse_all_sheets(file_path)
+
+            if not parse_result.success:
+                return {
+                    "success": False,
+                    "error": parse_result.error,
+                    "analysis": None
+                }
+
+            sheets_data = parse_result.data.get("sheets", {})
+            logger.info(f"Excel 解析成功，共 {len(sheets_data)} 个工作表")
+
+        except Exception as e:
+            logger.error(f"Excel 解析失败: {str(e)}")
+            return {
+                "success": False,
+                "error": f"Excel 解析失败: {str(e)}",
+                "analysis": None
+            }
+
+        # 2. 批量分析每个工作表
+        sheet_analyses = {}
+        errors = {}
+
+        for sheet_name, sheet_data in sheets_data.items():
+            try:
+                if user_prompt and user_prompt.strip():
+                    llm_result = await self.llm_service.analyze_with_template(
+                        sheet_data,
+                        user_prompt
+                    )
+                else:
+                    llm_result = await self.llm_service.analyze_excel_data(
+                        sheet_data,
+                        user_prompt,
+                        analysis_type
+                    )
+
+                sheet_analyses[sheet_name] = llm_result
+
+                if not llm_result["success"]:
+                    errors[sheet_name] = llm_result.get("error", "未知错误")
+
+                logger.info(f"工作表 '{sheet_name}' 分析完成")
+
+            except Exception as e:
+                logger.error(f"工作表 '{sheet_name}' 分析失败: {str(e)}")
+                errors[sheet_name] = str(e)
+
+        # 3. 组合结果
+        return {
+            "success": len(errors) == 0,
+            "excel": {
+                "sheets": sheets_data,
+                "metadata": parse_result.metadata,
+                "saved_path": file_path
+            },
+            "analysis": {
+                "sheets": sheet_analyses,
+                "total_sheets": len(sheets_data),
+                "successful": len(sheet_analyses) - len(errors),
+                "errors": errors
+            }
+        }
+
     def get_supported_analysis_types(self) -> List[str]:
         """获取支持的分析类型"""
         return [

backend/app/services/llm_service.py

@@ -54,15 +54,21 @@ class LLMService:
         # 添加其他参数
         payload.update(kwargs)
 
+        import time
+        _start_time = time.time()
+        logger.info(f"🤖 [LLM] 正在调用 DeepSeek API... 模型: {self.model_name}")
         try:
-            async with httpx.AsyncClient(timeout=60.0) as client:
+            async with httpx.AsyncClient(timeout=120.0) as client:
                 response = await client.post(
                     f"{self.base_url}/chat/completions",
                     headers=headers,
                     json=payload
                 )
                 response.raise_for_status()
-                return response.json()
+                result = response.json()
+                _elapsed = time.time() - _start_time
+                logger.info(f"✅ [LLM] DeepSeek API 响应成功 | 模型: {self.model_name} | 耗时: {_elapsed:.2f}s | Token: {result.get('usage', {}).get('total_tokens', 'N/A')}")
+                return result
 
         except httpx.HTTPStatusError as e:
             error_detail = e.response.text
@@ -78,7 +84,7 @@ class LLMService:
                 pass
             raise
         except Exception as e:
-            logger.error(f"LLM API 调用异常: {str(e)}")
+            logger.error(f"LLM API 调用异常: {repr(e)} - {str(e)}")
             raise
 
     def extract_message_content(self, response: Dict[str, Any]) -> str:
@@ -133,6 +139,9 @@ class LLMService:
 
         payload.update(kwargs)
 
+        import time
+        _start_time = time.time()
+        logger.info(f"🤖 [LLM] 正在调用 DeepSeek API (流式) | 模型: {self.model_name}")
         try:
             async with httpx.AsyncClient(timeout=120.0) as client:
                 async with client.stream(
@@ -141,10 +150,13 @@ class LLMService:
                     headers=headers,
                     json=payload
                 ) as response:
+                    _elapsed = time.time() - _start_time
+                    logger.info(f"✅ [LLM] DeepSeek API 流式响应开始 | 模型: {self.model_name} | 耗时: {_elapsed:.2f}s")
                     async for line in response.aiter_lines():
                         if line.startswith("data: "):
                             data = line[6:]  # Remove "data: " prefix
                             if data == "[DONE]":
+                                logger.info(f"✅ [LLM] DeepSeek API 流式响应完成")
                                 break
                             try:
                                 import json as json_module

backend/app/services/pdf_converter_service.py

@@ -0,0 +1,403 @@
+"""
+PDF 转换服务
+
+支持将 Word(docx)、Excel(xlsx)、Txt、Markdown(md) 格式转换为 PDF
+策略：所有格式先转为 Markdown，再通过 Markdown 转 PDF
+"""
+import io
+import logging
+import platform
+from pathlib import Path
+from typing import List, Tuple
+
+from reportlab.lib.pagesizes import A4
+from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
+from reportlab.lib.enums import TA_LEFT, TA_CENTER, TA_JUSTIFY
+from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, Table, TableStyle
+from reportlab.pdfbase import pdfmetrics
+from reportlab.pdfbase.ttfonts import TTFont
+
+logger = logging.getLogger(__name__)
+
+
+class PDFConverterService:
+    """PDF 转换服务"""
+
+    def __init__(self):
+        self.supported_formats = ["docx", "xlsx", "txt", "md"]
+        self._font_name = None
+        self._styles = None
+        self._page_width = None
+        self._page_height = None
+        self._setup_fonts()
+
+    def _setup_fonts(self):
+        """设置字体"""
+        try:
+            self._page_width, self._page_height = A4
+
+            # 查找中文字体
+            font_path = self._find_chinese_font()
+            if font_path:
+                try:
+                    font = TTFont('ChineseFont', font_path)
+                    pdfmetrics.registerFont(font)
+                    from reportlab.pdfbase.pdfmetrics import registerFontFamily
+                    registerFontFamily('ChineseFont', normal='ChineseFont')
+                    self._font_name = 'ChineseFont'
+                    logger.info(f"成功注册中文字体: {font_path}")
+                except Exception as e:
+                    logger.warning(f"字体注册失败: {e}, 使用Helvetica")
+                    self._font_name = 'Helvetica'
+            else:
+                self._font_name = 'Helvetica'
+                logger.warning("未找到中文字体，使用 Helvetica（不支持中文）")
+
+            # 创建样式
+            styles = getSampleStyleSheet()
+
+            styles.add(ParagraphStyle(
+                name='ChineseTitle',
+                fontName=self._font_name,
+                fontSize=16,
+                leading=22,
+                alignment=TA_CENTER,
+                spaceAfter=12,
+            ))
+
+            styles.add(ParagraphStyle(
+                name='ChineseHeading',
+                fontName=self._font_name,
+                fontSize=14,
+                leading=20,
+                spaceBefore=10,
+                spaceAfter=8,
+            ))
+
+            styles.add(ParagraphStyle(
+                name='ChineseBody',
+                fontName=self._font_name,
+                fontSize=10,
+                leading=14,
+                alignment=TA_JUSTIFY,
+                spaceAfter=6,
+            ))
+
+            styles.add(ParagraphStyle(
+                name='ChineseCode',
+                fontName='Courier',
+                fontSize=9,
+                leading=12,
+            ))
+
+            self._styles = styles
+            logger.info("PDF服务初始化完成")
+
+        except Exception as e:
+            logger.error(f"PDF服务初始化失败: {e}")
+            raise
+
+    def _find_chinese_font(self) -> str:
+        """查找中文字体"""
+        system = platform.system()
+
+        if system == "Windows":
+            fonts = [
+                "C:/Windows/Fonts/simhei.ttf",
+                "C:/Windows/Fonts/simsun.ttc",
+                "C:/Windows/Fonts/msyh.ttc",
+                "C:/Windows/Fonts/simsun.ttf",
+            ]
+        elif system == "Darwin":
+            fonts = [
+                "/System/Library/Fonts/STHeiti Light.ttc",
+                "/System/Library/Fonts/PingFang.ttc",
+                "/Library/Fonts/Arial Unicode.ttf",
+            ]
+        else:
+            fonts = [
+                "/usr/share/fonts/truetype/wqy/wqy-microhei.ttc",
+                "/usr/share/fonts/opentype/noto/NotoSansCJK-Regular.ttc",
+            ]
+
+        for font in fonts:
+            if Path(font).exists():
+                return font
+        return None
+
+    def _sanitize_text(self, text: str) -> str:
+        """清理文本"""
+        if not text:
+            return ""
+        return text.replace('\x00', '')
+
+    async def convert_to_pdf(
+        self,
+        file_content: bytes,
+        source_format: str,
+        filename: str = "document"
+    ) -> Tuple[bytes, str]:
+        """将文档转换为 PDF"""
+        try:
+            if source_format.lower() not in self.supported_formats:
+                return b"", f"不支持的格式: {source_format}"
+
+            # 第一步：转换为 Markdown
+            markdown_content, error = await self._convert_to_markdown(file_content, source_format, filename)
+            if error:
+                return b"", error
+
+            # 第二步：Markdown 转 PDF
+            return await self._convert_markdown_to_pdf(markdown_content, filename)
+
+        except Exception as e:
+            logger.error(f"PDF转换失败: {e}")
+            import traceback
+            logger.error(f"详细错误: {traceback.format_exc()}")
+            return b"", f"转换失败: {str(e)}"
+
+    async def _convert_to_markdown(
+        self,
+        file_content: bytes,
+        source_format: str,
+        filename: str
+    ) -> Tuple[str, str]:
+        """将各种格式转换为 Markdown"""
+        converters = {
+            "docx": self._convert_docx_to_markdown,
+            "xlsx": self._convert_xlsx_to_markdown,
+            "txt": self._convert_txt_to_markdown,
+            "md": self._convert_md_to_markdown,
+        }
+        return await converters[source_format.lower()](file_content, filename)
+
+    async def _convert_txt_to_markdown(self, file_content: bytes, filename: str) -> Tuple[str, str]:
+        """Txt 转 Markdown"""
+        try:
+            text = self._decode_content(file_content)
+            text = self._sanitize_text(text)
+            return f"# {filename}\n\n{text}", ""
+        except Exception as e:
+            logger.error(f"Txt转Markdown失败: {e}")
+            return "", f"文本文件处理失败: {str(e)}"
+
+    async def _convert_md_to_markdown(self, file_content: bytes, filename: str) -> Tuple[str, str]:
+        """Markdown 原样返回"""
+        try:
+            content = self._decode_content(file_content)
+            content = self._sanitize_text(content)
+            return f"# {filename}\n\n{content}", ""
+        except Exception as e:
+            logger.error(f"Markdown处理失败: {e}")
+            return "", f"Markdown处理失败: {str(e)}"
+
+    async def _convert_docx_to_markdown(self, file_content: bytes, filename: str) -> Tuple[str, str]:
+        """Word 转 Markdown - 使用 zipfile 直接解析，更加健壮"""
+        try:
+            import zipfile
+            import re
+
+            lines = [f"# {filename}", ""]
+
+            # 直接使用 zipfile 解析 DOCX，避免 python-docx 的严格验证
+            try:
+                with zipfile.ZipFile(io.BytesIO(file_content), 'r') as zf:
+                    # 读取主文档内容
+                    xml_content = zf.read('word/document.xml').decode('utf-8')
+            except zipfile.BadZipFile:
+                return "", "文件不是有效的 DOCX 格式"
+            except KeyError:
+                return "", "DOCX 文件损坏：找不到 document.xml"
+
+            # 简单的 XML 解析 - 提取文本段落
+            # 移除 XML 标签，提取纯文本
+            xml_content = re.sub(r'<w:br[^>]*>', '\n', xml_content)
+            xml_content = re.sub(r'</w:p>', '\n', xml_content)
+            xml_content = re.sub(r'<[^>]+>', '', xml_content)
+            xml_content = re.sub(r'\n\s*\n', '\n\n', xml_content)
+
+            # 解码 HTML 实体
+            xml_content = xml_content.replace('&amp;', '&')
+            xml_content = xml_content.replace('&lt;', '<')
+            xml_content = xml_content.replace('&gt;', '>')
+            xml_content = xml_content.replace('&quot;', '"')
+            xml_content = xml_content.replace('&#39;', "'")
+
+            # 清理空白
+            lines_text = [line.strip() for line in xml_content.split('\n') if line.strip()]
+
+            # 生成 Markdown
+            for text in lines_text[:500]:  # 限制最多500行
+                if text:
+                    lines.append(text)
+
+            return '\n'.join(lines), ""
+
+        except Exception as e:
+            logger.error(f"Word转Markdown失败: {e}")
+            import traceback
+            logger.error(traceback.format_exc())
+            return "", f"Word文档处理失败: {str(e)}"
+            for table in doc.tables:
+                lines.append("")
+                for row in table.rows:
+                    row_data = [cell.text.strip() for cell in row.cells]
+                    lines.append("| " + " | ".join(row_data) + " |")
+                # 表头分隔符
+                if table.rows:
+                    lines.append("| " + " | ".join(["---"] * len(table.rows[0].cells)) + " |")
+
+            return "\n".join(lines), ""
+
+        except Exception as e:
+            logger.error(f"Word转Markdown失败: {e}")
+            return "", f"Word文档处理失败: {str(e)}"
+
+    async def _convert_xlsx_to_markdown(self, file_content: bytes, filename: str) -> Tuple[str, str]:
+        """Excel 转 Markdown"""
+        try:
+            import openpyxl
+
+            wb = openpyxl.load_workbook(io.BytesIO(file_content))
+            lines = [f"# {filename} - Excel数据", ""]
+
+            for sheet_name in wb.sheetnames[:10]:
+                ws = wb[sheet_name]
+                lines.append(f"## 工作表: {sheet_name}")
+                lines.append("")
+
+                for row_idx, row in enumerate(ws.iter_rows(max_row=50, values_only=True)):
+                    row_data = [str(cell) if cell is not None else "" for cell in row]
+                    if not any(row_data):
+                        continue
+                    lines.append("| " + " | ".join(row_data) + " |")
+                    if row_idx == 0:
+                        lines.append("| " + " | ".join(["---"] * len(row_data)) + " |")
+
+                lines.append("")
+
+            return "\n".join(lines), ""
+
+        except Exception as e:
+            logger.error(f"Excel转Markdown失败: {e}")
+            return "", f"Excel处理失败: {str(e)}"
+
+    async def _convert_markdown_to_pdf(self, markdown_content: str, filename: str) -> Tuple[bytes, str]:
+        """Markdown 转 PDF"""
+        try:
+            logger.info(f"Markdown转PDF开始 - filename={filename}, 字体={self._font_name}")
+            logger.info(f"styles['ChineseTitle'].fontName={self._styles['ChineseTitle'].fontName}")
+
+            buffer = io.BytesIO()
+            story = []
+
+            safe_filename = self._sanitize_text(filename)
+            logger.info(f"safe_filename={repr(safe_filename[:50])}")
+
+            story.append(Paragraph(text=safe_filename, style=self._styles['ChineseTitle']))
+            story.append(Spacer(1, 12))
+
+            in_code = False
+            for line in markdown_content.split('\n'):
+                line = line.strip()
+
+                if line.startswith('```'):
+                    in_code = not in_code
+                    story.append(Spacer(1, 6))
+                    continue
+
+                if in_code:
+                    story.append(Paragraph(text=self._sanitize_text(line), style=self._styles['ChineseCode']))
+                    continue
+
+                if not line:
+                    story.append(Spacer(1, 6))
+                    continue
+
+                # 标题处理
+                if line.startswith('# '):
+                    story.append(Paragraph(text=self._sanitize_text(line[2:]), style=self._styles['ChineseHeading']))
+                elif line.startswith('## '):
+                    story.append(Paragraph(text=self._sanitize_text(line[3:]), style=self._styles['ChineseHeading']))
+                elif line.startswith('### '):
+                    story.append(Paragraph(text=self._sanitize_text(line[4:]), style=self._styles['ChineseHeading']))
+                elif line.startswith('#### '):
+                    story.append(Paragraph(text=self._sanitize_text(line[5:]), style=self._styles['ChineseHeading']))
+                elif line.startswith('- ') or line.startswith('* '):
+                    story.append(Paragraph(text="• " + self._sanitize_text(line[2:]), style=self._styles['ChineseBody']))
+                # 表格处理
+                elif line.startswith('|'):
+                    # 跳过 markdown 表格分隔符
+                    if set(line.replace('|', '').replace('-', '').replace(':', '').replace(' ', '')) == set():
+                        continue
+                    # 解析并创建表格
+                    table_lines = []
+                    for _ in range(50):  # 最多50行
+                        if line.startswith('|'):
+                            row = [cell.strip() for cell in line.split('|')[1:-1]]
+                            if not any(row) or set(''.join(row).replace('-', '').replace(':', '').replace(' ', '')) == set():
+                                break
+                            table_lines.append(row)
+                            try:
+                                line = next(markdown_content.split('\n').__iter__()).strip()
+                            except StopIteration:
+                                break
+                        else:
+                            break
+
+                    if table_lines:
+                        # 创建表格
+                        t = Table(table_lines, colWidths=[100] * len(table_lines[0]))
+                        t.setStyle(TableStyle([
+                            ('FONTNAME', (0, 0), (-1, -1), self._font_name),
+                            ('FONTSIZE', (0, 0), (-1, -1), 9),
+                            ('GRID', (0, 0), (-1, -1), 0.5, '#999999'),
+                            ('BACKGROUND', (0, 0), (-1, 0), '#4472C4'),
+                            ('TEXTCOLOR', (0, 0), (-1, 0), '#FFFFFF'),
+                        ]))
+                        story.append(t)
+                        story.append(Spacer(1, 6))
+                else:
+                    story.append(Paragraph(text=self._sanitize_text(line), style=self._styles['ChineseBody']))
+
+            logger.info(f"准备构建PDF，story长度={len(story)}")
+
+            pdf_doc = SimpleDocTemplate(
+                buffer,
+                pagesize=(self._page_width, self._page_height),
+                rightMargin=72,
+                leftMargin=72,
+                topMargin=72,
+                bottomMargin=72
+            )
+            logger.info("调用pdf_doc.build()")
+            pdf_doc.build(story)
+            logger.info("pdf_doc.build()完成")
+
+            result = buffer.getvalue()
+            buffer.close()
+            return result, ""
+
+        except Exception as e:
+            logger.error(f"Markdown转PDF失败: {e}")
+            import traceback
+            logger.error(f"详细错误: {traceback.format_exc()}")
+            return b"", f"Markdown转PDF失败: {str(e)}"
+
+    def _decode_content(self, file_content: bytes) -> str:
+        """解码文件内容"""
+        encodings = ['utf-8', 'gbk', 'gb2312', 'gb18030', 'latin-1']
+        for enc in encodings:
+            try:
+                return file_content.decode(enc)
+            except (UnicodeDecodeError, LookupError):
+                continue
+        return file_content.decode('utf-8', errors='replace')
+
+    def get_supported_formats(self) -> List[str]:
+        """获取支持的格式"""
+        return self.supported_formats
+
+
+# 全局单例
+pdf_converter_service = PDFConverterService()

backend/app/services/rag_service.py

@@ -669,7 +669,7 @@ class RAGService:
         # 按融合分数降序排序
         fused_results.sort(key=lambda x: x["score"], reverse=True)
 
-        logger.debug(f"混合融合: {len(fused_results)} 个文档, 向量:{len(vector_results)}, BM25:{len(bm25_results)}")
+        logger.info(f"RRF 混合融合: {len(fused_results)} 个文档参与融合, 向量检索命中:{len(vector_results)}, BM25命中:{len(bm25_results)}")
 
         return fused_results[:top_k]
 

backend/app/services/txt_ai_service.py

@@ -19,6 +19,7 @@ class TxtAIService:
 
     def __init__(self):
         self.parser = TxtParser()
+        self.llm = llm_service
 
     async def analyze_txt_with_ai(
         self,
@@ -114,7 +115,7 @@ class TxtAIService:
             response = await self.llm.chat(
                 messages=messages,
                 temperature=0.1,
-                max_tokens=50000
+                max_tokens=8000
             )
 
             content_text = self.llm.extract_message_content(response)
@@ -220,7 +221,7 @@ class TxtAIService:
             response = await self.llm.chat(
                 messages=messages,
                 temperature=0.1,
-                max_tokens=50000
+                max_tokens=8000
             )
 
             content_text = self.llm.extract_message_content(response)

backend/app/services/visualization_service.py

@@ -53,7 +53,11 @@ class VisualizationService:
                 }
 
             # 转换为 DataFrame
-            df = pd.DataFrame(rows, columns=columns)
+            # 过滤掉行数与列数不匹配的数据
+            valid_rows = [row for row in rows if len(row) == len(columns)]
+            if len(valid_rows) < len(rows):
+                logger.warning(f"过滤了 {len(rows) - len(valid_rows)} 行无效数据（列数不匹配）")
+            df = pd.DataFrame(valid_rows, columns=columns)
 
             # 根据列类型分类
             numeric_columns = df.select_dtypes(include=[np.number]).columns.tolist()
@@ -141,18 +145,18 @@ class VisualizationService:
         charts = {}
 
         # 1. 数值型列的直方图
-        charts["histograms"] = []
+        charts["numeric_charts"] = []
         for col in numeric_columns[:5]:  # 限制最多 5 个数值列
             chart_data = self._create_histogram(df[col], col)
             if chart_data:
-                charts["histograms"].append(chart_data)
+                charts["numeric_charts"].append(chart_data)
 
         # 2. 分类型列的条形图
-        charts["bar_charts"] = []
+        charts["categorical_charts"] = []
         for col in categorical_columns[:5]:  # 限制最多 5 个分类型列
             chart_data = self._create_bar_chart(df[col], col)
             if chart_data:
-                charts["bar_charts"].append(chart_data)
+                charts["categorical_charts"].append(chart_data)
 
         # 3. 数值型列的箱线图
         charts["box_plots"] = []

backend/app/services/word_ai_service.py

@@ -184,7 +184,7 @@ class WordAIService:
             response = await self.llm.chat(
                 messages=messages,
                 temperature=0.1,
-                max_tokens=50000
+                max_tokens=8000
             )
 
             content = self.llm.extract_message_content(response)
@@ -276,7 +276,7 @@ class WordAIService:
             response = await self.llm.chat(
                 messages=messages,
                 temperature=0.1,
-                max_tokens=50000
+                max_tokens=8000
             )
 
             content = self.llm.extract_message_content(response)
@@ -849,10 +849,12 @@ class WordAIService:
 
             # 提取可用于图表的数据
             chart_data = None
+            logger.info(f"准备提取图表数据，structured_data type: {structured_data.get('type')}, keys: {list(structured_data.keys())}")
 
             if structured_data.get("type") == "table_data":
                 headers = structured_data.get("headers", [])
                 rows = structured_data.get("rows", [])
+                logger.info(f"table_data类型: headers数量={len(headers)}, rows数量={len(rows)}")
                 if headers and rows:
                     chart_data = {
                         "columns": headers,
@@ -860,15 +862,19 @@ class WordAIService:
                     }
             elif structured_data.get("type") == "structured_text":
                 tables_data = structured_data.get("tables", [])
+                logger.info(f"structured_text类型: tables数量={len(tables_data)}")
                 if tables_data and len(tables_data) > 0:
                     first_table = tables_data[0]
                     headers = first_table.get("headers", [])
                     rows = first_table.get("rows", [])
+                    logger.info(f"第一个表格: headers={headers[:5]}, rows数量={len(rows)}")
                     if headers and rows:
                         chart_data = {
                             "columns": headers,
                             "rows": rows
                         }
+            else:
+                logger.warning(f"无法识别的structured_data类型: {structured_data.get('type')}")
 
             # 生成可视化图表
             if chart_data:
@@ -904,3 +910,6 @@ class WordAIService:
                 "success": False,
                 "error": str(e)
             }
+
+
+word_ai_service = WordAIService()

backend/requirements.txt

@@ -42,6 +42,9 @@ chardet==5.2.0
 Pillow>=10.0.0
 pytesseract>=0.3.10
 
+# ==================== PDF 生成 ====================
+reportlab>=4.0.0
+
 # ==================== AI / LLM ====================
 httpx==0.25.2
 

docker-compose.yml

@@ -0,0 +1,203 @@
+# ============================================================
+# FilesReadSystem Docker Compose
+# 全栈 AI 文档理解与数据融合系统
+# ============================================================
+version: "3.8"
+
+services:
+  # ==================== 数据库服务 ====================
+
+  mongodb:
+    image: mongo:7.0
+    container_name: filesread_mongodb
+    restart: unless-stopped
+    ports:
+      - "27017:27017"
+    environment:
+      MONGO_INITDB_ROOT_USERNAME: ${MONGO_ROOT_USER:-admin}
+      MONGO_INITDB_ROOT_PASSWORD: ${MONGO_ROOT_PASSWORD:-20060825fhy}
+      MONGO_INITDB_DATABASE: ${MONGODB_DB_NAME:-document_system}
+    volumes:
+      - mongodb_data:/data/db
+    networks:
+      - filesread_network
+    healthcheck:
+      test: ["CMD", "mongosh", "--eval", "db.adminCommand('ping')", "--quiet"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+      start_period: 30s
+
+  mysql:
+    image: mysql:8.0
+    container_name: filesread_mysql
+    restart: unless-stopped
+    ports:
+      - "3306:3306"
+    environment:
+      MYSQL_ROOT_PASSWORD: ${MYSQL_PASSWORD:-123456}
+      MYSQL_DATABASE: ${MYSQL_DATABASE:-document}
+    volumes:
+      - mysql_data:/var/lib/mysql
+    networks:
+      - filesread_network
+    healthcheck:
+      test: ["CMD", "mysqladmin", "ping", "-h", "localhost", "-u", "root", "-p${MYSQL_PASSWORD:-123456}"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+      start_period: 30s
+
+  redis:
+    image: redis:7-alpine
+    container_name: filesread_redis
+    restart: unless-stopped
+    ports:
+      - "6379:6379"
+    volumes:
+      - redis_data:/data
+    networks:
+      - filesread_network
+    command: redis-server --appendonly yes --requirepass ${REDIS_PASSWORD:-}
+    healthcheck:
+      test: ["CMD", "redis-cli", "ping"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+
+  # ==================== 应用服务 ====================
+
+  backend:
+    build:
+      context: ./backend
+      dockerfile: Dockerfile
+    container_name: filesread_backend
+    restart: unless-stopped
+    ports:
+      - "8000:8000"
+    environment:
+      # 应用配置
+      APP_NAME: FilesReadSystem
+      DEBUG: ${DEBUG:-false}
+      API_V1_STR: /api/v1
+
+      # MongoDB 配置 (使用 docker-compose 服务名)
+      MONGODB_URL: mongodb://${MONGO_ROOT_USER:-admin}:${MONGO_ROOT_PASSWORD:-20060825fhy}@mongodb:27017/admin
+      MONGODB_DB_NAME: ${MONGODB_DB_NAME:-document_system}
+
+      # MySQL 配置
+      MYSQL_HOST: mysql
+      MYSQL_PORT: 3306
+      MYSQL_USER: root
+      MYSQL_PASSWORD: ${MYSQL_PASSWORD:-123456}
+      MYSQL_DATABASE: ${MYSQL_DATABASE:-document}
+      MYSQL_CHARSET: utf8mb4
+
+      # Redis 配置
+      REDIS_URL: redis://:${REDIS_PASSWORD:-}@redis:6379/0
+
+      # LLM AI 配置
+      LLM_API_KEY: ${LLM_API_KEY}
+      LLM_BASE_URL: ${LLM_BASE_URL:-https://api.deepseek.com}
+      LLM_MODEL_NAME: ${LLM_MODEL_NAME:-deepseek-chat}
+
+      # Supabase 配置
+      SUPABASE_URL: ${SUPABASE_URL}
+      SUPABASE_ANON_KEY: ${SUPABASE_ANON_KEY}
+      SUPABASE_SERVICE_KEY: ${SUPABASE_SERVICE_KEY}
+
+      # Embedding / RAG 配置
+      EMBEDDING_MODEL: ${EMBEDDING_MODEL:-all-MiniLM-L6-v2}
+      FAISS_INDEX_DIR: /app/data/faiss
+
+      # 文件路径配置
+      UPLOAD_DIR: /app/data/uploads
+      MAX_UPLOAD_SIZE: 104857600
+
+      # Celery 配置
+      CELERY_BROKER_URL: redis://:${REDIS_PASSWORD:-}@redis:6379/1
+      CELERY_RESULT_BACKEND: redis://:${REDIS_PASSWORD:-}@redis:6379/2
+    volumes:
+      - backend_data:/app/data
+    networks:
+      - filesread_network
+    depends_on:
+      mongodb:
+        condition: service_healthy
+      mysql:
+        condition: service_healthy
+      redis:
+        condition: service_healthy
+    healthcheck:
+      test: ["CMD", "python", "-c", "import httpx; httpx.get('http://localhost:8000/health')"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 40s
+
+  celery_worker:
+    build:
+      context: ./backend
+      dockerfile: Dockerfile
+    container_name: filesread_celery
+    restart: unless-stopped
+    command: celery -A app.celery_app worker --loglevel=info --prefetch-multiplier=1
+    environment:
+      # Celery 配置
+      CELERY_BROKER_URL: redis://:${REDIS_PASSWORD:-}@redis:6379/1
+      CELERY_RESULT_BACKEND: redis://:${REDIS_PASSWORD:-}@redis:6379/2
+
+      # 复用后端的数据库配置
+      MONGODB_URL: mongodb://${MONGO_ROOT_USER:-admin}:${MONGO_ROOT_PASSWORD:-20060825fhy}@mongodb:27017/admin
+      MONGODB_DB_NAME: ${MONGODB_DB_NAME:-document_system}
+      MYSQL_HOST: mysql
+      MYSQL_PORT: 3306
+      MYSQL_USER: root
+      MYSQL_PASSWORD: ${MYSQL_PASSWORD:-123456}
+      MYSQL_DATABASE: ${MYSQL_DATABASE:-document}
+      REDIS_URL: redis://:${REDIS_PASSWORD:-}@redis:6379/0
+
+      # LLM 配置
+      LLM_API_KEY: ${LLM_API_KEY}
+      LLM_BASE_URL: ${LLM_BASE_URL:-https://api.deepseek.com}
+      LLM_MODEL_NAME: ${LLM_MODEL_NAME:-deepseek-chat}
+
+      # Embedding 配置
+      EMBEDDING_MODEL: ${EMBEDDING_MODEL:-all-MiniLM-L6-v2}
+      FAISS_INDEX_DIR: /app/data/faiss
+    volumes:
+      - backend_data:/app/data
+    networks:
+      - filesread_network
+    depends_on:
+      - redis
+      - mongodb
+      - mysql
+
+  frontend:
+    build:
+      context: ./frontend
+      dockerfile: Dockerfile
+    container_name: filesread_frontend
+    restart: unless-stopped
+    ports:
+      - "80:80"
+    environment:
+      VITE_APP_ID: ${VITE_APP_ID:-}
+      VITE_SUPABASE_URL: ${SUPABASE_URL}
+      VITE_SUPABASE_ANON_KEY: ${SUPABASE_ANON_KEY}
+      VITE_BACKEND_API_URL: /api/v1
+    networks:
+      - filesread_network
+    depends_on:
+      - backend
+
+networks:
+  filesread_network:
+    driver: bridge
+
+volumes:
+  mongodb_data:
+  mysql_data:
+  redis_data:
+  backend_data:

docs/architecture.drawio

@@ -0,0 +1,169 @@
+<mxfile host="app.diagrams.net" modified="2026-04-16T14:00:00.000Z" agent="Claude" version="24.0.0">
+  <diagram name="系统架构图" id="architecture">
+    <mxGraphModel dx="1200" dy="800" grid="1" gridSize="10" guides="1" tooltips="1" connect="1" arrows="1" fold="1" page="1" pageScale="1" pageWidth="1920" pageHeight="1080" math="0" shadow="0">
+      <root>
+        <mxCell id="0" />
+        <mxCell id="1" parent="0" />
+
+        <!-- 用户访问层 -->
+        <mxCell id="layer1" value="用户访问层" style="text;html=1;strokeColor=none;fillColor=none;align=center;verticalAlign=middle;whiteSpace=wrap;rounded=0;fontSize=16;fontStyle=1;fontColor=#1a1a2e;" vertex="1" parent="1">
+          <mxGeometry x="800" y="20" width="120" height="30" as="geometry" />
+        </mxCell>
+        <mxCell id="browser" value="浏览器&#xa;(Browser)" style="rounded=1;whiteSpace=wrap;html=1;fillColor=#e3f2fd;strokeColor=#1976d2;fontColor=#0d47a1;" vertex="1" parent="1">
+          <mxGeometry x="860" y="60" width="120" height="50" as="geometry" />
+        </mxCell>
+
+        <!-- 前端展示层 -->
+        <mxCell id="layer2" value="前端展示层" style="text;html=1;strokeColor=none;fillColor=none;align=center;verticalAlign=middle;whiteSpace=wrap;rounded=0;fontSize=16;fontStyle=1;fontColor=#1a1a2e;" vertex="1" parent="1">
+          <mxGeometry x="800" y="140" width="120" height="30" as="geometry" />
+        </mxCell>
+        <mxCell id="frontend_box" value="" style="rounded=1;whiteSpace=wrap;html=1;fillColor=#f3e5f5;strokeColor=#7b1fa2;strokeWidth=2;" vertex="1" parent="1">
+          <mxGeometry x="200" y="180" width="1520" height="140" as="geometry" />
+        </mxCell>
+        <mxCell id="frontend_title" value="React 18 + TypeScript + Vite + shadcn/ui" style="text;html=1;strokeColor=none;fillColor=none;align=center;verticalAlign=middle;whiteSpace=wrap;rounded=0;fontSize=14;fontStyle=1;fontColor=#4a148c;" vertex="1" parent="1">
+          <mxGeometry x="760" y="185" width="280" height="25" as="geometry" />
+        </mxCell>
+        <mxCell id="dashboard" value="Dashboard&#xa;首页仪表盘" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#ce93d8;strokeColor=#8e24aa;fontColor=#fff;" vertex="1" parent="1">
+          <mxGeometry x="240" y="220" width="120" height="80" as="geometry" />
+        </mxCell>
+        <mxCell id="documents" value="Documents&#xa;文档管理" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#ce93d8;strokeColor=#8e24aa;fontColor=#fff;" vertex="1" parent="1">
+          <mxGeometry x="400" y="220" width="120" height="80" as="geometry" />
+        </mxCell>
+        <mxCell id="template" value="TemplateFill&#xa;智能填表" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#ce93d8;strokeColor=#8e24aa;fontColor=#fff;" vertex="1" parent="1">
+          <mxGeometry x="560" y="220" width="120" height="80" as="geometry" />
+        </mxCell>
+        <mxCell id="instruction" value="Instruction&#xa;指令助手" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#ce93d8;strokeColor=#8e24aa;fontColor=#fff;" vertex="1" parent="1">
+          <mxGeometry x="720" y="220" width="120" height="80" as="geometry" />
+        </mxCell>
+        <mxCell id="taskhistory" value="TaskHistory&#xa;任务历史" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#ce93d8;strokeColor=#8e24aa;fontColor=#fff;" vertex="1" parent="1">
+          <mxGeometry x="880" y="220" width="120" height="80" as="geometry" />
+        </mxCell>
+        <mxCell id="frontend_libs" value="Recharts + Lucide Icons + React Router" style="text;html=1;strokeColor=none;fillColor=none;align=center;verticalAlign=middle;whiteSpace=wrap;rounded=0;fontSize=11;fontColor=#6a1b9a;" vertex="1" parent="1">
+          <mxGeometry x="1040" y="250" width="280" height="25" as="geometry" />
+        </mxCell>
+
+        <!-- 连接线：浏览器到前端 -->
+        <mxCell id="conn1" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;strokeColor=#1976d2;strokeWidth=2;" edge="1" parent="1" source="browser" target="frontend_box">
+          <mxGeometry relative="1" as="geometry" />
+        </mxCell>
+
+        <!-- 后端服务层 -->
+        <mxCell id="layer3" value="后端服务层" style="text;html=1;strokeColor=none;fillColor=none;align=center;verticalAlign=middle;whiteSpace=wrap;rounded=0;fontSize=16;fontStyle=1;fontColor=#1a1a2e;" vertex="1" parent="1">
+          <mxGeometry x="800" y="350" width="120" height="30" as="geometry" />
+        </mxCell>
+        <mxCell id="backend_box" value="" style="rounded=1;whiteSpace=wrap;html=1;fillColor=#e8f5e9;strokeColor=#388e3c;strokeWidth=2;" vertex="1" parent="1">
+          <mxGeometry x="200" y="390" width="1520" height="180" as="geometry" />
+        </mxCell>
+        <mxCell id="backend_title" value="FastAPI + Uvicorn + Celery" style="text;html=1;strokeColor=none;fillColor=none;align=center;verticalAlign=middle;whiteSpace=wrap;rounded=0;fontSize=14;fontStyle=1;fontColor=#1b5e20;" vertex="1" parent="1">
+          <mxGeometry x="800" y="395" width="200" height="25" as="geometry" />
+        </mxCell>
+        <mxCell id="upload" value="文档上传&#xa;/upload/*" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#81c784;strokeColor=#2e7d32;fontColor=#1b5e20;" vertex="1" parent="1">
+          <mxGeometry x="240" y="430" width="140" height="60" as="geometry" />
+        </mxCell>
+        <mxCell id="ai" value="AI分析&#xa;/ai/*" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#81c784;strokeColor=#2e7d32;fontColor=#1b5e20;" vertex="1" parent="1">
+          <mxGeometry x="420" y="430" width="140" height="60" as="geometry" />
+        </mxCell>
+        <mxCell id="rag" value="RAG检索&#xa;/rag/*" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#81c784;strokeColor=#2e7d32;fontColor=#1b5e20;" vertex="1" parent="1">
+          <mxGeometry x="600" y="430" width="140" height="60" as="geometry" />
+        </mxCell>
+        <mxCell id="template_api" value="模板填充&#xa;/templates/*" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#81c784;strokeColor=#2e7d32;fontColor=#1b5e20;" vertex="1" parent="1">
+          <mxGeometry x="780" y="430" width="140" height="60" as="geometry" />
+        </mxCell>
+        <mxCell id="instruction_api" value="指令解析&#xa;/instruction/*" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#81c784;strokeColor=#2e7d32;fontColor=#1b5e20;" vertex="1" parent="1">
+          <mxGeometry x="960" y="430" width="140" height="60" as="geometry" />
+        </mxCell>
+        <mxCell id="visualization" value="可视化&#xa;/visualization/*" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#81c784;strokeColor=#2e7d32;fontColor=#1b5e20;" vertex="1" parent="1">
+          <mxGeometry x="1140" y="430" width="140" height="60" as="geometry" />
+        </mxCell>
+        <mxCell id="celery" value="Celery&#xa;任务调度" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#a5d6a7;strokeColor=#2e7d32;fontColor=#1b5e20;" vertex="1" parent="1">
+          <mxGeometry x="1320" y="430" width="120" height="60" as="geometry" />
+        </mxCell>
+        <mxCell id="logging" value="监控日志" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#a5d6a7;strokeColor=#2e7d32;fontColor=#1b5e20;" vertex="1" parent="1">
+          <mxGeometry x="1480" y="430" width="100" height="60" as="geometry" />
+        </mxCell>
+
+        <!-- 连接线：前端到后端 -->
+        <mxCell id="conn2" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;strokeColor=#388e3c;strokeWidth=2;dashed=1;dashPattern=8 8;" edge="1" parent="1" source="frontend_box" target="backend_box">
+          <mxGeometry relative="1" as="geometry" />
+        </mxCell>
+
+        <!-- AI服务层 -->
+        <mxCell id="layer4" value="AI服务层" style="text;html=1;strokeColor=none;fillColor=none;align=center;verticalAlign=middle;whiteSpace=wrap;rounded=0;fontSize=16;fontStyle=1;fontColor=#1a1a2e;" vertex="1" parent="1">
+          <mxGeometry x="800" y="600" width="120" height="30" as="geometry" />
+        </mxCell>
+        <mxCell id="ai_box" value="" style="rounded=1;whiteSpace=wrap;html=1;fillColor=#fff3e0;strokeColor=#f57c00;strokeWidth=2;" vertex="1" parent="1">
+          <mxGeometry x="300" y="640" width="1320" height="120" as="geometry" />
+        </mxCell>
+        <mxCell id="llm_title" value="LLMService - 大模型服务" style="text;html=1;strokeColor=none;fillColor=none;align=center;verticalAlign=middle;whiteSpace=wrap;rounded=0;fontSize=14;fontStyle=1;fontColor=#e65100;" vertex="1" parent="1">
+          <mxGeometry x="820" y="645" width="200" height="25" as="geometry" />
+        </mxCell>
+        <mxCell id="minimax" value="MiniMax-Text-01" style="rounded=1;whiteSpace=wrap;html=1;fillColor=#ffcc80;strokeColor=#ef6c00;fontColor=#e65100;" vertex="1" parent="1">
+          <mxGeometry x="400" y="680" width="150" height="50" as="geometry" />
+        </mxCell>
+        <mxCell id="deepseek" value="DeepSeek-chat" style="rounded=1;whiteSpace=wrap;html=1;fillColor=#ffcc80;strokeColor=#ef6c00;fontColor=#e65100;" vertex="1" parent="1">
+          <mxGeometry x="600" y="680" width="150" height="50" as="geometry" />
+        </mxCell>
+        <mxCell id="excel_ai" value="ExcelAIService" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#ffe0b2;strokeColor=#f57c00;fontColor=#e65100;" vertex="1" parent="1">
+          <mxGeometry x="820" y="680" width="130" height="50" as="geometry" />
+        </mxCell>
+        <mxCell id="word_ai" value="WordAIService" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#ffe0b2;strokeColor=#f57c00;fontColor=#e65100;" vertex="1" parent="1">
+          <mxGeometry x="980" y="680" width="130" height="50" as="geometry" />
+        </mxCell>
+        <mxCell id="md_ai" value="MarkdownAIService" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#ffe0b2;strokeColor=#f57c00;fontColor=#e65100;" vertex="1" parent="1">
+          <mxGeometry x="1140" y="680" width="130" height="50" as="geometry" />
+        </mxCell>
+        <mxCell id="txt_ai" value="TxtAIService" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#ffe0b2;strokeColor=#f57c00;fontColor=#e65100;" vertex="1" parent="1">
+          <mxGeometry x="1300" y="680" width="130" height="50" as="geometry" />
+        </mxCell>
+
+        <!-- 连接线：后端到AI -->
+        <mxCell id="conn3" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;strokeColor=#f57c00;strokeWidth=2;dashed=1;dashPattern=8 8;" edge="1" parent="1" source="backend_box" target="ai_box">
+          <mxGeometry relative="1" as="geometry" />
+        </mxCell>
+
+        <!-- 数据存储层 -->
+        <mxCell id="layer5" value="数据存储层" style="text;html=1;strokeColor=none;fillColor=none;align=center;verticalAlign=middle;whiteSpace=wrap;rounded=0;fontSize=16;fontStyle=1;fontColor=#1a1a2e;" vertex="1" parent="1">
+          <mxGeometry x="800" y="790" width="120" height="30" as="geometry" />
+        </mxCell>
+        <mxCell id="mongodb" value="MongoDB&#xa;文档数据库&#xa;&#xa;• 原始文档内容&#xa;• 元数据信息&#xa;• 文档标签&#xa;• 处理状态" style="rounded=1;whiteSpace=wrap;html=1;fillColor=#e0e0e0;strokeColor=#616161;fontColor=#212121;align=left;spacingLeft=10;" vertex="1" parent="1">
+          <mxGeometry x="240" y="830" width="200" height="160" as="geometry" />
+        </mxCell>
+        <mxCell id="mysql" value="MySQL&#xa;关系数据库&#xa;&#xa;• Excel表格数据&#xa;• 结构化数据&#xa;• 字段描述&#xa;• RAG索引" style="rounded=1;whiteSpace=wrap;html=1;fillColor=#e0e0e0;strokeColor=#616161;fontColor=#212121;align=left;spacingLeft=10;" vertex="1" parent="1">
+          <mxGeometry x="520" y="830" width="200" height="160" as="geometry" />
+        </mxCell>
+        <mxCell id="redis" value="Redis&#xa;缓存/队列&#xa;&#xa;• 会话缓存&#xa;• 任务队列&#xa;• Celery broker&#xa;• 临时数据" style="rounded=1;whiteSpace=wrap;html=1;fillColor=#e0e0e0;strokeColor=#616161;fontColor=#212121;align=left;spacingLeft=10;" vertex="1" parent="1">
+          <mxGeometry x="800" y="830" width="200" height="160" as="geometry" />
+        </mxCell>
+        <mxCell id="faiss" value="FAISS&#xa;向量数据库&#xa;&#xa;• 文档向量索引&#xa;• 语义相似度&#xa;• RAG检索&#xa;• sentence-transformers" style="rounded=1;whiteSpace=wrap;html=1;fillColor=#e0e0e0;strokeColor=#616161;fontColor=#212121;align=left;spacingLeft=10;" vertex="1" parent="1">
+          <mxGeometry x="1080" y="830" width="240" height="160" as="geometry" />
+        </mxCell>
+
+        <!-- 连接线：AI到存储 -->
+        <mxCell id="conn4" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;strokeColor=#616161;strokeWidth=2;dashed=1;dashPattern=8 8;" edge="1" parent="1" source="ai_box" target="mongodb">
+          <mxGeometry relative="1" as="geometry" />
+        </mxCell>
+        <mxCell id="conn5" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;strokeColor=#616161;strokeWidth=2;dashed=1;dashPattern=8 8;" edge="1" parent="1" source="ai_box" target="mysql">
+          <mxGeometry relative="1" as="geometry" />
+        </mxCell>
+        <mxCell id="conn6" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;strokeColor=#616161;strokeWidth=2;dashed=1;dashPattern=8 8;" edge="1" parent="1" source="ai_box" target="redis">
+          <mxGeometry relative="1" as="geometry" />
+        </mxCell>
+        <mxCell id="conn7" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;strokeColor=#616161;strokeWidth=2;dashed=1;dashPattern=8 8;" edge="1" parent="1" source="ai_box" target="faiss">
+          <mxGeometry relative="1" as="geometry" />
+        </mxCell>
+
+        <!-- 标注 -->
+        <mxCell id="arrow1" value="HTTP/HTTPS&#xa;WebSocket" style="text;html=1;strokeColor=none;fillColor=none;align=center;verticalAlign=middle;whiteSpace=wrap;rounded=0;fontSize=10;fontColor=#1976d2;" vertex="1" parent="1">
+          <mxGeometry x="1020" y="130" width="80" height="30" as="geometry" />
+        </mxCell>
+        <mxCell id="arrow2" value="API调用" style="text;html=1;strokeColor=none;fillColor=none;align=center;verticalAlign=middle;whiteSpace=wrap;rounded=0;fontSize=10;fontColor=#388e3c;" vertex="1" parent="1">
+          <mxGeometry x="1020" y="570" width="60" height="20" as="geometry" />
+        </mxCell>
+        <mxCell id="arrow3" value="数据读写" style="text;html=1;strokeColor=none;fillColor=none;align=center;verticalAlign=middle;whiteSpace=wrap;rounded=0;fontSize=10;fontColor=#616161;" vertex="1" parent="1">
+          <mxGeometry x="1020" y="770" width="60" height="20" as="geometry" />
+        </mxCell>
+
+      </root>
+    </mxGraphModel>
+  </diagram>
+</mxfile>

frontend/Dockerfile

@@ -0,0 +1,36 @@
+# ============================================================
+# FilesReadSystem Frontend - React + Vite
+# 多阶段构建: Node 构建 -> Nginx 运行
+# ============================================================
+
+# === 阶段1: 构建阶段 ===
+FROM node:20-alpine AS builder
+
+WORKDIR /app
+
+# 复制 package 文件和锁文件
+COPY package.json pnpm-lock.yaml* ./
+
+# 安装 pnpm 并安装依赖
+RUN npm install -g pnpm && \
+    pnpm install --frozen-lockfile
+
+# 复制源码
+COPY . .
+
+# 构建生产版本
+RUN pnpm build
+
+# === 阶段2: 运行阶段 ===
+FROM nginx:alpine
+
+# 复制 nginx 配置
+COPY nginx.conf /etc/nginx/conf.d/default.conf
+
+# 复制构建产物
+COPY --from=builder /app/dist /usr/share/nginx/html
+
+# 暴露端口
+EXPOSE 80
+
+CMD ["nginx", "-g", "daemon off;"]

frontend/nginx.conf

@@ -0,0 +1,47 @@
+# ============================================================
+# FilesReadSystem Nginx 配置
+# 反向代理 API 请求到后端
+# ============================================================
+
+server {
+    listen 80;
+    server_name localhost;
+
+    # 前端静态文件
+    root /usr/share/nginx/html;
+    index index.html;
+
+    # SPA 支持 - 所有请求都尝试返回 index.html
+    location / {
+        try_files $uri $uri/ /index.html;
+    }
+
+    # 静态资源缓存
+    location ~* \.(js|css|png|jpg|jpeg|gif|ico|svg|woff|woff2|ttf|eot)$ {
+        expires 1y;
+        add_header Cache-Control "public, immutable";
+    }
+
+    # API 反向代理到后端
+    location /api/ {
+        proxy_pass http://backend:8000/api/;
+        proxy_http_version 1.1;
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+        proxy_set_header X-Forwarded-Proto $scheme;
+
+        # 超时设置
+        proxy_connect_timeout 60s;
+        proxy_send_timeout 60s;
+        proxy_read_timeout 60s;
+    }
+
+    # 文件上传代理
+    location /uploads/ {
+        proxy_pass http://backend:8000/uploads/;
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        client_max_body_size 100M;
+    }
+}

frontend/src/components/layouts/MainLayout.tsx

@@ -8,7 +8,8 @@ import {
   Menu,
   ChevronRight,
   Sparkles,
-  Clock
+  Clock,
+  FileDown
 } from 'lucide-react';
 import { Button } from '@/components/ui/button';
 import { cn } from '@/lib/utils';
@@ -19,6 +20,7 @@ const navItems = [
   { name: '文档中心', path: '/documents', icon: FileText },
   { name: '智能填表', path: '/form-fill', icon: TableProperties },
   { name: '智能助手', path: '/assistant', icon: MessageSquareCode },
+  { name: '文档转PDF', path: '/pdf-converter', icon: FileDown },
   { name: '任务历史', path: '/task-history', icon: Clock },
 ];
 
@@ -32,7 +34,7 @@ const MainLayout: React.FC = () => {
           <FileText size={24} />
         </div>
         <div className="flex flex-col">
-          <span className="font-bold text-lg tracking-tight text-sidebar-foreground">智联文档</span>
+          <span className="font-bold text-lg tracking-tight text-sidebar-foreground">表易智融</span>
           <span className="text-xs text-muted-foreground">多源数据融合平台</span>
         </div>
       </div>
@@ -66,7 +68,7 @@ const MainLayout: React.FC = () => {
               <Sparkles size={20} className="text-primary" />
             </div>
             <div className="flex flex-col overflow-hidden">
-              <span className="font-semibold text-sm truncate">智联文档</span>
+              <span className="font-semibold text-sm truncate">表易智融</span>
               <span className="text-[10px] uppercase tracking-wider text-muted-foreground">多源数据融合</span>
             </div>
           </div>

frontend/src/db/backend-api.ts

@@ -1153,6 +1153,120 @@ export const backendApi = {
     }
   },
 
+  // ==================== PDF 转换 API ====================
+
+  /**
+   * 将文件转换为 PDF
+   */
+  /**
+   * PDF转换并直接下载（使用XHR，支持IDM拦截）
+   */
+  async convertAndDownloadPdf(file: File): Promise<void> {
+    return new Promise((resolve, reject) => {
+      const xhr = new XMLHttpRequest();
+      xhr.open('POST', `${BACKEND_BASE_URL}/pdf/convert`);
+
+      xhr.onload = function() {
+        if (xhr.status >= 200 && xhr.status < 300) {
+          // 创建 blob 并触发下载
+          const blob = xhr.response;
+          const url = URL.createObjectURL(blob);
+          const a = document.createElement('a');
+          a.href = url;
+          a.download = `${file.name.replace(/\.[^.]+$/, '')}.pdf`;
+          document.body.appendChild(a);
+          a.click();
+          document.body.removeChild(a);
+          URL.revokeObjectURL(url);
+          resolve();
+        } else {
+          reject(new Error(`转换失败: ${xhr.status}`));
+        }
+      };
+
+      xhr.onerror = function() {
+        reject(new Error('网络错误'));
+      };
+
+      const formData = new FormData();
+      formData.append('file', file);
+      xhr.responseType = 'blob';
+      xhr.send(formData);
+    });
+  },
+
+  /**
+   * PDF转换（返回Blob）
+   */
+  async convertToPdf(file: File): Promise<Blob> {
+    return new Promise((resolve, reject) => {
+      const xhr = new XMLHttpRequest();
+      xhr.open('POST', `${BACKEND_BASE_URL}/pdf/convert`);
+
+      xhr.onload = function() {
+        if (xhr.status >= 200 && xhr.status < 300) {
+          resolve(xhr.response);
+        } else {
+          reject(new Error(`转换失败: ${xhr.status}`));
+        }
+      };
+
+      xhr.onerror = function() {
+        reject(new Error('网络错误'));
+      };
+
+      const formData = new FormData();
+      formData.append('file', file);
+      xhr.responseType = 'blob';
+      xhr.send(formData);
+    });
+  },
+
+  /**
+   * 批量将文件转换为 PDF
+   */
+  async batchConvertToPdf(files: File[]): Promise<Blob> {
+    const formData = new FormData();
+    files.forEach(file => formData.append('files', file));
+
+    const url = `${BACKEND_BASE_URL}/pdf/convert/batch`;
+
+    try {
+      const response = await fetch(url, {
+        method: 'POST',
+        body: formData,
+      });
+
+      if (!response.ok) {
+        const error = await response.json();
+        throw new Error(error.detail || '批量PDF转换失败');
+      }
+
+      return await response.blob();
+    } catch (error) {
+      console.error('批量PDF转换失败:', error);
+      throw error;
+    }
+  },
+
+  /**
+   * 获取支持的 PDF 转换格式
+   */
+  async getPdfSupportedFormats(): Promise<{
+    success: boolean;
+    formats: string[];
+  }> {
+    const url = `${BACKEND_BASE_URL}/pdf/formats`;
+
+    try {
+      const response = await fetch(url);
+      if (!response.ok) throw new Error('获取支持的格式失败');
+      return await response.json();
+    } catch (error) {
+      console.error('获取支持的格式失败:', error);
+      return { success: false, formats: ['docx', 'xlsx', 'txt', 'md'] };
+    }
+  }
 };
 
 // ==================== AI 分析 API ====================
@@ -1187,11 +1301,19 @@ export const aiApi = {
    * 上传并使用 AI 分析 Excel 文件
    */
   async analyzeExcel(
-    file: File,
+    file: File | null,
-    options: AIAnalyzeOptions = {}
+    options: AIAnalyzeOptions = {},
+    docId: string | null = null
   ): Promise<AIExcelAnalyzeResult> {
     const formData = new FormData();
-    formData.append('file', file);
+
+    if (docId) {
+      formData.append('doc_id', docId);
+    } else if (file) {
+      formData.append('file', file);
+    } else {
+      throw new Error('必须提供文件或文档ID');
+    }
 
     const params = new URLSearchParams();
     if (options.userPrompt) {
@@ -1268,7 +1390,9 @@ export const aiApi = {
     try {
       const response = await fetch(url);
       if (!response.ok) throw new Error('获取分析类型失败');
-      return await response.json();
+      const data = await response.json();
+      // 转换后端返回格式 {excel_types: [], markdown_types: []} 为前端期望的 {types: []}
+      return { types: data.excel_types || [] };
     } catch (error) {
       console.error('获取分析类型失败:', error);
       throw error;
@@ -1795,5 +1919,6 @@ export const aiApi = {
       console.error('获取会话列表失败:', error);
       return { success: false, conversations: [] };
     }
-  }
+  },
+
 };

frontend/src/pages/Assistant.tsx

@@ -41,7 +41,7 @@ const Assistant: React.FC = () => {
         {
           id: '1',
           role: 'assistant',
-          content: '您好！我是智联文档 AI 助手。您可以告诉我您想对文档进行的操作，例如：\n- "帮我列出最近上传的所有 docx 文档"\n- "从 2026 财报文档中提取出关键的利润数据"\n- "帮我创建一个汇总各部门报销单的填表任务"\n\n请问有什么我可以帮您的？',
+          content: '您好！我是表易智融 AI 助手。您可以告诉我您想对文档进行的操作，例如：\n- "帮我列出最近上传的所有 docx 文档"\n- "从 2026 财报文档中提取出关键的利润数据"\n- "帮我创建一个汇总各部门报销单的填表任务"\n\n请问有什么我可以帮您的？',
           created_at: new Date().toISOString()
         }
       ]);

frontend/src/pages/Dashboard.tsx

@@ -89,7 +89,7 @@ const Dashboard: React.FC = () => {
       <section className="flex flex-col md:flex-row md:items-center justify-between gap-4">
         <div className="space-y-1">
           <h1 className="text-3xl font-extrabold tracking-tight">
-            欢迎使用 <span className="text-primary">智联文档</span> 系统 👋
+            欢迎使用 <span className="text-primary">表易智融</span> 系统 👋
           </h1>
           <p className="text-muted-foreground">基于大语言模型的文档理解与多源数据融合系统</p>
         </div>

frontend/src/pages/Documents.tsx

@@ -472,11 +472,17 @@ const Documents: React.FC = () => {
     setAnalysisCharts(null);
 
     try {
-      const result = await aiApi.analyzeExcel(uploadedFile, {
+      // 判断是从历史文档还是本地上传
-        userPrompt: aiOptions.userPrompt,
+      const docId = selectedDocument?.doc_id && uploadedFile.size === 0 ? selectedDocument.doc_id : null;
-        analysisType: aiOptions.analysisType,
+      const result = await aiApi.analyzeExcel(
-        parseAllSheets: aiOptions.parseAllSheetsForAI
+        uploadedFile.size > 0 ? uploadedFile : null,
-      });
+        {
+          userPrompt: aiOptions.userPrompt,
+          analysisType: aiOptions.analysisType,
+          parseAllSheets: aiOptions.parseAllSheetsForAI
+        },
+        docId
+      );
 
       if (result.success) {
         toast.success('AI 分析完成');
@@ -706,6 +712,12 @@ const Documents: React.FC = () => {
 
   const handleSelectDocument = async (docId: string) => {
     setLoadingDocument(true);
+    // 重置所有 AI 分析结果，避免显示上一个文档的分析
+    setAiAnalysis(null);
+    setAnalysisCharts(null);
+    setMdAnalysis(null);
+    setWordAnalysis(null);
+    setTxtAnalysis(null);
     try {
       const result = await backendApi.getDocument(docId);
       if (result.success && result.document) {
@@ -2264,39 +2276,57 @@ const Documents: React.FC = () => {
   );
 };
 
-// 数据表格组件
+// 数据表格组件 - 滑动窗口样式
 const DataTable: React.FC<{ columns: string[]; rows: Record<string, any>[] }> = ({ columns, rows }) => {
   if (!columns.length || !rows.length) {
     return <div className="text-center py-8 text-muted-foreground text-sm">暂无数据</div>;
   }
 
+  const displayRows = rows.slice(0, 500); // 限制最多显示500行
+
   return (
-    <div className="rounded-lg border overflow-x-auto">
+    <div className="rounded-lg border overflow-hidden">
-      <TableComponent>
+      {/* 表头 - 固定 */}
-        <TableHeader>
+      <div className="overflow-x-auto">
-          <TableRow>
+        <TableComponent>
-            <TableHead className="w-16 text-center text-muted-foreground">#</TableHead>
+          <TableHeader>
-            {columns.map((col, idx) => (
+            <TableRow className="bg-muted/50">
-              <TableHead key={idx} className="whitespace-nowrap">{col || `<列${idx + 1}>`}</TableHead>
+              <TableHead className="w-16 text-center text-muted-foreground">#</TableHead>
-            ))}
+              {columns.map((col, idx) => (
-          </TableRow>
+                <TableHead key={idx} className="whitespace-nowrap">{col || `<列${idx + 1}>`}</TableHead>
-        </TableHeader>
-        <TableBody>
-          {rows.slice(0, 100).map((row, rowIdx) => (
-            <TableRow key={rowIdx}>
-              <TableCell className="text-center text-muted-foreground font-medium">{rowIdx + 1}</TableCell>
-              {columns.map((col, colIdx) => (
-                <TableCell key={colIdx} className="whitespace-nowrap">
-                  {row[col] !== null && row[col] !== undefined ? String(row[col]) : '-'}
-                </TableCell>
               ))}
             </TableRow>
-          ))}
+          </TableHeader>
-        </TableBody>
+        </TableComponent>
-      </TableComponent>
+      </div>
-      {rows.length > 100 && (
+      {/* 表体 - 可滚动 */}
+      <div
+        className="overflow-y-auto"
+        style={{ maxHeight: '400px' }}
+      >
+        <TableComponent>
+          <TableBody>
+            {displayRows.map((row, rowIdx) => (
+              <TableRow key={rowIdx}>
+                <TableCell className="text-center text-muted-foreground font-medium w-16">{rowIdx + 1}</TableCell>
+                {columns.map((col, colIdx) => (
+                  <TableCell key={colIdx} className="whitespace-nowrap">
+                    {row[col] !== null && row[col] !== undefined ? String(row[col]) : '-'}
+                  </TableCell>
+                ))}
+              </TableRow>
+            ))}
+          </TableBody>
+        </TableComponent>
+      </div>
+      {rows.length > 500 && (
         <div className="p-3 text-center text-sm text-muted-foreground bg-muted/30">
-          仅显示前 100 行数据
+          仅显示前 500 行数据（共 {rows.length} 行）
+        </div>
+      )}
+      {rows.length > 100 && rows.length <= 500 && (
+        <div className="p-2 text-center text-xs text-muted-foreground bg-muted/20">
+          共 {rows.length} 行数据，向下滚动查看更多
         </div>
       )}
     </div>

frontend/src/pages/InstructionChat.tsx

@@ -45,7 +45,7 @@ const InstructionChat: React.FC = () => {
         {
           id: 'welcome',
           role: 'assistant',
-          content: `您好！我是智联文档 AI 助手。
+          content: `您好！我是表易智融 AI 助手。
 
 **📄 文档智能操作**
 - "提取文档中的医院数量和床位数"

frontend/src/pages/PdfConverter.tsx

@@ -0,0 +1,446 @@
+/**
+ * PDF 转换页面
+ * 支持将 Word、Excel、Txt、Markdown 格式转换为 PDF
+ */
+import React, { useState, useCallback } from 'react';
+import { useDropzone } from 'react-dropzone';
+import {
+  FileText,
+  Upload,
+  Download,
+  FileSpreadsheet,
+  File as FileIcon,
+  Loader2,
+  CheckCircle,
+  AlertCircle,
+  Trash2,
+  FileDown,
+  X,
+  Copy
+} from 'lucide-react';
+import { Button } from '@/components/ui/button';
+import { Card, CardContent, CardHeader, CardTitle, CardDescription } from '@/components/ui/card';
+import { Badge } from '@/components/ui/badge';
+import { Label } from '@/components/ui/label';
+import { toast } from 'sonner';
+import { cn } from '@/lib/utils';
+import { backendApi } from '@/db/backend-api';
+
+type FileState = {
+  file: File;
+  status: 'pending' | 'converting' | 'success' | 'failed';
+  progress: number;
+  pdfBlob?: Blob;
+  error?: string;
+};
+
+const SUPPORTED_FORMATS = [
+  { ext: 'docx', name: 'Word 文档', icon: FileText, color: 'blue' },
+  { ext: 'xlsx', name: 'Excel 表格', icon: FileSpreadsheet, color: 'emerald' },
+  { ext: 'txt', name: '文本文件', icon: FileIcon, color: 'gray' },
+  { ext: 'md', name: 'Markdown', icon: FileText, color: 'purple' },
+];
+
+const PdfConverter: React.FC = () => {
+  const [files, setFiles] = useState<FileState[]>([]);
+  const [converting, setConverting] = useState(false);
+  const [convertedCount, setConvertedCount] = useState(0);
+
+  const onDrop = useCallback((acceptedFiles: File[]) => {
+    const newFiles: FileState[] = acceptedFiles.map(file => ({
+      file,
+      status: 'pending',
+      progress: 0,
+    }));
+    setFiles(prev => [...prev, ...newFiles]);
+  }, []);
+
+  const { getRootProps, getInputProps, isDragActive } = useDropzone({
+    onDrop,
+    accept: {
+      'application/vnd.openxmlformats-officedocument.wordprocessingml.document': ['.docx'],
+      'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet': ['.xlsx'],
+      'application/vnd.ms-excel': ['.xls'],
+      'text/markdown': ['.md'],
+      'text/plain': ['.txt'],
+    },
+    multiple: true,
+  });
+
+  const handleConvert = async () => {
+    if (files.length === 0) {
+      toast.error('请先上传文件');
+      return;
+    }
+
+    setConverting(true);
+    setConvertedCount(0);
+
+    const pendingFiles = files.filter(f => f.status === 'pending' || f.status === 'failed');
+    let successCount = 0;
+
+    for (let i = 0; i < pendingFiles.length; i++) {
+      const fileState = pendingFiles[i];
+      const fileIndex = files.findIndex(f => f.file === fileState.file);
+
+      // 更新状态为转换中
+      setFiles(prev => prev.map((f, idx) =>
+        idx === fileIndex ? { ...f, status: 'converting', progress: 10 } : f
+      ));
+
+      try {
+        // 获取 PDF blob
+        const pdfBlob = await backendApi.convertToPdf(fileState.file);
+
+        // 触发下载
+        const url = URL.createObjectURL(pdfBlob);
+        const a = document.createElement('a');
+        a.href = url;
+        a.download = `${fileState.file.name.replace(/\.[^.]+$/, '')}.pdf`;
+        document.body.appendChild(a);
+        a.click();
+        document.body.removeChild(a);
+        URL.revokeObjectURL(url);
+
+        // 保存 blob 以便批量下载
+        setFiles(prev => prev.map((f, idx) =>
+          idx === fileIndex ? { ...f, status: 'success', progress: 100, pdfBlob } : f
+        ));
+        successCount++;
+        setConvertedCount(successCount);
+        toast.success(`${fileState.file.name} 下载已开始`);
+      } catch (error: any) {
+        setFiles(prev => prev.map((f, idx) =>
+          idx === fileIndex ? { ...f, status: 'failed', error: error.message || '转换失败' } : f
+        ));
+      }
+    }
+
+    setConverting(false);
+    toast.success(`转换完成：${successCount}/${pendingFiles.length} 个文件`);
+  };
+
+  const handleDownload = (fileState: FileState) => {
+    if (!fileState.pdfBlob) return;
+
+    const url = URL.createObjectURL(fileState.pdfBlob);
+    const link = document.createElement('a');
+    link.href = url;
+    link.download = `${fileState.file.name.replace(/\.[^.]+$/, '')}.pdf`;
+    document.body.appendChild(link);
+    link.click();
+    document.body.removeChild(link);
+    URL.revokeObjectURL(url);
+  };
+
+  const handleDownloadAll = async () => {
+    const successFiles = files.filter(f => f.status === 'success' && f.pdfBlob);
+
+    if (successFiles.length === 0) {
+      toast.error('没有可下载的文件');
+      return;
+    }
+
+    if (successFiles.length === 1) {
+      handleDownload(successFiles[0]);
+      return;
+    }
+
+    // 多个文件，下载 ZIP
+    try {
+      const zipBlob = await backendApi.batchConvertToPdf(
+        successFiles.map(f => f.file)
+      );
+      const url = URL.createObjectURL(zipBlob);
+      const link = document.createElement('a');
+      link.href = url;
+      link.download = 'converted_pdfs.zip';
+      document.body.appendChild(link);
+      link.click();
+      document.body.removeChild(link);
+      URL.revokeObjectURL(url);
+      toast.success('ZIP 下载开始');
+    } catch (error: any) {
+      toast.error(error.message || '下载失败');
+    }
+  };
+
+  const handleRemove = (index: number) => {
+    setFiles(prev => prev.filter((_, i) => i !== index));
+  };
+
+  const handleClear = () => {
+    setFiles([]);
+    setConvertedCount(0);
+  };
+
+  const getFileIcon = (filename: string) => {
+    const ext = filename.split('.').pop()?.toLowerCase();
+    const format = SUPPORTED_FORMATS.find(f => f.ext === ext);
+    if (!format) return FileIcon;
+    return format.icon;
+  };
+
+  const getFileColor = (filename: string) => {
+    const ext = filename.split('.').pop()?.toLowerCase();
+    const format = SUPPORTED_FORMATS.find(f => f.ext === ext);
+    return format?.color || 'gray';
+  };
+
+  const colorClasses: Record<string, string> = {
+    blue: 'bg-blue-500/10 text-blue-500',
+    emerald: 'bg-emerald-500/10 text-emerald-500',
+    purple: 'bg-purple-500/10 text-purple-500',
+    gray: 'bg-gray-500/10 text-gray-500',
+  };
+
+  return (
+    <div className="space-y-8 pb-10">
+      <section className="flex flex-col md:flex-row md:items-center justify-between gap-4">
+        <div className="space-y-1">
+          <h1 className="text-3xl font-extrabold tracking-tight">文档转 PDF</h1>
+          <p className="text-muted-foreground">将 Word、Excel、文本、Markdown 文件转换为 PDF 格式</p>
+        </div>
+        {files.length > 0 && (
+          <div className="flex gap-2">
+            <Button variant="outline" onClick={handleClear}>
+              <Trash2 size={18} className="mr-2" />
+              清空
+            </Button>
+            <Button onClick={handleDownloadAll} disabled={files.filter(f => f.status === 'success').length === 0}>
+              <Download size={18} className="mr-2" />
+              打包下载 ({files.filter(f => f.status === 'success').length})
+            </Button>
+          </div>
+        )}
+      </section>
+
+      <div className="grid grid-cols-1 lg:grid-cols-3 gap-6">
+        {/* 左侧：上传区域 */}
+        <div className="lg:col-span-1 space-y-6">
+          {/* 上传卡片 */}
+          <Card className="border-none shadow-md">
+            <CardHeader className="pb-4">
+              <CardTitle className="flex items-center gap-2">
+                <Upload className="text-primary" size={20} />
+                上传文件
+              </CardTitle>
+              <CardDescription>拖拽或点击上传要转换的文件</CardDescription>
+            </CardHeader>
+            <CardContent className="space-y-4">
+              <div
+                {...getRootProps()}
+                className={cn(
+                  "border-2 border-dashed rounded-2xl p-8 transition-all duration-300 flex flex-col items-center justify-center text-center cursor-pointer group",
+                  isDragActive ? "border-primary bg-primary/5" : "border-muted-foreground/20 hover:border-primary/50 hover:bg-primary/5",
+                  converting && "opacity-50 pointer-events-none"
+                )}
+              >
+                <input {...getInputProps()} />
+                <div className="w-14 h-14 rounded-xl bg-primary/10 text-primary flex items-center justify-center mb-4 group-hover:scale-110 transition-transform">
+                  {converting ? <Loader2 className="animate-spin" size={28} /> : <Upload size={28} />}
+                </div>
+                <p className="font-semibold text-sm">
+                  {isDragActive ? '释放以开始上传' : '点击或拖拽文件到这里'}
+                </p>
+                <div className="mt-4 flex flex-wrap justify-center gap-2">
+                  {SUPPORTED_FORMATS.map(format => (
+                    <Badge key={format.ext} variant="outline" className={cn("text-xs", colorClasses[format.color])}>
+                      {format.name}
+                    </Badge>
+                  ))}
+                </div>
+              </div>
+
+              {/* 转换按钮 */}
+              {files.length > 0 && (
+                <Button
+                  onClick={handleConvert}
+                  disabled={converting || files.filter(f => f.status === 'pending' || f.status === 'failed').length === 0}
+                  className="w-full bg-gradient-to-r from-primary to-purple-600 hover:from-primary/90 hover:to-purple-600/90"
+                >
+                  {converting ? (
+                    <>
+                      <Loader2 className="mr-2 animate-spin" size={16} />
+                      转换中... ({convertedCount}/{files.filter(f => f.status === 'pending' || f.status === 'failed').length})
+                    </>
+                  ) : (
+                    <>
+                      <FileDown className="mr-2" size={16} />
+                      开始转换 ({files.filter(f => f.status === 'pending' || f.status === 'failed').length})
+                    </>
+                  )}
+                </Button>
+              )}
+            </CardContent>
+          </Card>
+
+          {/* 格式说明 */}
+          <Card className="border-none shadow-md">
+            <CardHeader className="pb-4">
+              <CardTitle className="flex items-center gap-2">
+                <FileText className="text-primary" size={20} />
+                支持的格式
+              </CardTitle>
+            </CardHeader>
+            <CardContent>
+              <div className="space-y-3">
+                {SUPPORTED_FORMATS.map(format => {
+                  const Icon = format.icon;
+                  return (
+                    <div key={format.ext} className="flex items-center gap-3 p-2 rounded-lg hover:bg-muted/30 transition-colors">
+                      <div className={cn("w-8 h-8 rounded flex items-center justify-center", colorClasses[format.color])}>
+                        <Icon size={16} />
+                      </div>
+                      <div className="flex-1">
+                        <p className="text-sm font-medium">.{format.ext.toUpperCase()}</p>
+                        <p className="text-xs text-muted-foreground">{format.name}</p>
+                      </div>
+                    </div>
+                  );
+                })}
+              </div>
+            </CardContent>
+          </Card>
+        </div>
+
+        {/* 右侧：文件列表 */}
+        <div className="lg:col-span-2 space-y-6">
+          <Card className="border-none shadow-md">
+            <CardHeader>
+              <div className="flex items-center justify-between">
+                <div className="space-y-1">
+                  <CardTitle className="flex items-center gap-2">
+                    <FileIcon className="text-primary" size={20} />
+                    文件列表
+                  </CardTitle>
+                  <CardDescription>
+                    共 {files.length} 个文件，已转换 {files.filter(f => f.status === 'success').length} 个
+                  </CardDescription>
+                </div>
+              </div>
+            </CardHeader>
+            <CardContent>
+              {files.length === 0 ? (
+                <div className="text-center py-12 text-muted-foreground">
+                  <FileIcon size={48} className="mx-auto mb-4 opacity-30" />
+                  <p>暂无文件，上传文件开始转换</p>
+                </div>
+              ) : (
+                <div className="space-y-3">
+                  {files.map((fileState, index) => {
+                    const Icon = getFileIcon(fileState.file.name);
+                    const color = getFileColor(fileState.file.name);
+
+                    return (
+                      <div
+                        key={index}
+                        className="flex items-center gap-4 p-4 rounded-xl border bg-card hover:bg-muted/30 transition-colors"
+                      >
+                        <div className={cn("w-10 h-10 rounded-lg flex items-center justify-center shrink-0", colorClasses[color])}>
+                          <Icon size={20} />
+                        </div>
+                        <div className="flex-1 min-w-0">
+                          <p className="font-semibold truncate">{fileState.file.name}</p>
+                          <div className="flex items-center gap-2">
+                            <span className="text-xs text-muted-foreground">
+                              {(fileState.file.size / 1024).toFixed(1)} KB
+                            </span>
+                            {fileState.status === 'pending' && (
+                              <Badge variant="secondary" className="text-xs">待转换</Badge>
+                            )}
+                            {fileState.status === 'converting' && (
+                              <Badge variant="default" className="text-xs bg-blue-500">转换中</Badge>
+                            )}
+                            {fileState.status === 'success' && (
+                              <Badge variant="default" className="text-xs bg-emerald-500">已转换</Badge>
+                            )}
+                            {fileState.status === 'failed' && (
+                              <Badge variant="destructive" className="text-xs">失败</Badge>
+                            )}
+                          </div>
+                          {fileState.status === 'converting' && (
+                            <div className="mt-1 h-1 bg-muted rounded-full overflow-hidden">
+                              <div
+                                className="h-full bg-primary transition-all duration-300"
+                                style={{ width: `${fileState.progress}%` }}
+                              />
+                            </div>
+                          )}
+                          {fileState.error && (
+                            <p className="text-xs text-destructive mt-1">{fileState.error}</p>
+                          )}
+                        </div>
+                        <div className="flex items-center gap-2 shrink-0">
+                          {fileState.status === 'success' && (
+                            <>
+                              <Button variant="ghost" size="icon" onClick={() => handleDownload(fileState)}>
+                                <Download size={18} className="text-emerald-500" />
+                              </Button>
+                              <Button
+                                variant="ghost"
+                                size="icon"
+                                onClick={() => {
+                                  // 复制下载链接到剪贴板
+                                  if (fileState.pdfBlob) {
+                                    const url = URL.createObjectURL(fileState.pdfBlob);
+                                    navigator.clipboard.writeText(url);
+                                    toast.success('链接已复制');
+                                  }
+                                }}
+                              >
+                                <Copy size={18} />
+                              </Button>
+                            </>
+                          )}
+                          {(fileState.status === 'pending' || fileState.status === 'failed') && (
+                            <Button
+                              variant="ghost"
+                              size="icon"
+                              onClick={() => handleRemove(index)}
+                              className="text-destructive hover:bg-destructive/10"
+                            >
+                              <X size={18} />
+                            </Button>
+                          )}
+                        </div>
+                      </div>
+                    );
+                  })}
+                </div>
+              )}
+            </CardContent>
+          </Card>
+
+          {/* 使用说明 */}
+          <Card className="border-none shadow-md bg-gradient-to-br from-primary/5 to-purple-500/5">
+            <CardHeader className="pb-4">
+              <CardTitle className="flex items-center gap-2">
+                <FileText className="text-primary" size={20} />
+                使用说明
+              </CardTitle>
+            </CardHeader>
+            <CardContent>
+              <div className="space-y-3 text-sm text-muted-foreground">
+                <div className="flex gap-3">
+                  <div className="w-6 h-6 rounded-full bg-primary/10 text-primary flex items-center justify-center shrink-0 text-xs font-bold">1</div>
+                  <p>上传要转换的文件，支持 Word(.docx)、Excel(.xlsx)、文本(.txt)、Markdown(.md) 格式</p>
+                </div>
+                <div className="flex gap-3">
+                  <div className="w-6 h-6 rounded-full bg-primary/10 text-primary flex items-center justify-center shrink-0 text-xs font-bold">2</div>
+                  <p>点击「开始转换」按钮，系统将自动将文件转换为 PDF 格式</p>
+                </div>
+                <div className="flex gap-3">
+                  <div className="w-6 h-6 rounded-full bg-primary/10 text-primary flex items-center justify-center shrink-0 text-xs font-bold">3</div>
+                  <p>转换完成后，点击下载按钮获取 PDF 文件，或使用「打包下载」一次性下载所有文件</p>
+                </div>
+              </div>
+            </CardContent>
+          </Card>
+        </div>
+      </div>
+    </div>
+  );
+};
+
+export default PdfConverter;

frontend/src/routes.tsx

@@ -4,6 +4,7 @@ import Documents from '@/pages/Documents';
 import TemplateFill from '@/pages/TemplateFill';
 import InstructionChat from '@/pages/InstructionChat';
 import TaskHistory from '@/pages/TaskHistory';
+import PdfConverter from '@/pages/PdfConverter';
 import MainLayout from '@/components/layouts/MainLayout';
 
 export const routes = [
@@ -31,6 +32,10 @@ export const routes = [
         path: '/task-history',
         element: <TaskHistory />,
       },
+      {
+        path: '/pdf-converter',
+        element: <PdfConverter />,
+      },
     ],
   },
   {

frontend/tsconfig.app.json

@@ -23,7 +23,6 @@
     "noUnusedParameters": true,
     "noFallthroughCasesInSwitch": true,
     "noUncheckedSideEffectImports": true,
-    "baseUrl": ".",
     "paths": {
       "@/*": ["./src/*"]
     },