添加系统架构图

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/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

@@ -58,7 +58,7 @@ class LLMService:
         _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,
@@ -84,7 +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:

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()

frontend/src/db/backend-api.ts

@@ -1187,11 +1187,19 @@ 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();
+
+    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 +1276,9 @@ 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;

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
+      const docId = selectedDocument?.doc_id && uploadedFile.size === 0 ? selectedDocument.doc_id : null;
+      const result = await aiApi.analyzeExcel(
+        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) {
@@ -2264,27 +2276,39 @@ 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">
+      {/* 表头 - 固定 */}
+      <div className="overflow-x-auto">
         <TableComponent>
           <TableHeader>
-          <TableRow>
+            <TableRow className="bg-muted/50">
               <TableHead className="w-16 text-center text-muted-foreground">#</TableHead>
               {columns.map((col, idx) => (
                 <TableHead key={idx} className="whitespace-nowrap">{col || `<列${idx + 1}>`}</TableHead>
               ))}
             </TableRow>
           </TableHeader>
+        </TableComponent>
+      </div>
+      {/* 表体 - 可滚动 */}
+      <div
+        className="overflow-y-auto"
+        style={{ maxHeight: '400px' }}
+      >
+        <TableComponent>
           <TableBody>
-          {rows.slice(0, 100).map((row, rowIdx) => (
+            {displayRows.map((row, rowIdx) => (
               <TableRow key={rowIdx}>
-              <TableCell className="text-center text-muted-foreground font-medium">{rowIdx + 1}</TableCell>
+                <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]) : '-'}
@@ -2294,9 +2318,15 @@ const DataTable: React.FC<{ columns: string[]; rows: Record<string, any>[] }> =
             ))}
           </TableBody>
         </TableComponent>
-      {rows.length > 100 && (
+      </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>