From 40cea6434ab4c263fea05cbfa6849f9c7ff11979 Mon Sep 17 00:00:00 2001
From: NeverlandYao <865373013@qq.com>
Date: Thu, 4 Sep 2025 10:28:30 +0800
Subject: [PATCH] feat: Add Jina AI service integration and web fragment input
 functionality

- Add Jina AI service for web content extraction and summarization
- Add web fragment input component
- Update layout and fragment input components
- Add MongoDB configuration
- Add example documentation
---
 .gitignore                        |   4 +
 app/api/jina/extract/route.ts     | 113 ++++++++
 app/layout.tsx                    |   1 +
 components/fragment-input.tsx     |  60 +++-
 components/web-fragment-input.tsx | 465 ++++++++++++++++++++++++++++++
 examples/mongodb-usage.md         |  93 ++++++
 lib/jina-service.ts               | 385 +++++++++++++++++++++++++
 lib/mongodb-config.ts             |  64 ++++
 8 files changed, 1171 insertions(+), 14 deletions(-)
 create mode 100644 app/api/jina/extract/route.ts
 create mode 100644 components/web-fragment-input.tsx
 create mode 100644 examples/mongodb-usage.md
 create mode 100644 lib/jina-service.ts
 create mode 100644 lib/mongodb-config.ts

diff --git a/.gitignore b/.gitignore
index e72b4d6..c021640 100644
--- a/.gitignore
+++ b/.gitignore
@@ -32,6 +32,10 @@ yarn-error.log*
 
 # env files (can opt-in for committing if needed)
 .env
+.env.local
+.env.development.local
+.env.test.local
+.env.production.local
 
 # vercel
 .vercel
diff --git a/app/api/jina/extract/route.ts b/app/api/jina/extract/route.ts
new file mode 100644
index 0000000..0ac50a3
--- /dev/null
+++ b/app/api/jina/extract/route.ts
@@ -0,0 +1,113 @@
+/**
+ * Jina AI 网页内容提取 API 路由
+ */
+
+import { NextRequest, NextResponse } from 'next/server'
+import { jinaService } from '../../../../lib/jina-service'
+import { WebContentExtractRequest } from '../../../../lib/jina-service'
+
+export async function POST(request: NextRequest) {
+  try {
+    const body = await request.json()
+    const { url, userPrompt, extractMode = 'full', language = 'zh' } = body
+
+    // 验证必需参数
+    if (!url) {
+      return NextResponse.json(
+        { success: false, error: '缺少必需参数: url' },
+        { status: 400 }
+      )
+    }
+
+    // 验证URL格式
+    try {
+      new URL(url)
+    } catch {
+      return NextResponse.json(
+        { success: false, error: '无效的URL格式' },
+        { status: 400 }
+      )
+    }
+
+    // 构建请求参数
+    const extractRequest: WebContentExtractRequest = {
+      url,
+      userPrompt,
+      extractMode,
+      language
+    }
+
+    // 调用Jina服务提取内容
+    const result = await jinaService.extractWebContent(extractRequest)
+
+    if (!result) {
+      return NextResponse.json(
+        { success: false, error: '网页内容提取失败' },
+        { status: 500 }
+      )
+    }
+
+    return NextResponse.json({
+      success: true,
+      data: result
+    })
+
+  } catch (error) {
+    console.error('Jina extract API error:', error)
+    return NextResponse.json(
+      { success: false, error: '服务器内部错误' },
+      { status: 500 }
+    )
+  }
+}
+
+export async function GET(request: NextRequest) {
+  try {
+    const { searchParams } = new URL(request.url)
+    const action = searchParams.get('action')
+
+    if (action === 'test') {
+      // 测试Jina服务连接
+      const testUrl = 'https://example.com'
+      const testResult = await jinaService.parseWebPage(testUrl)
+      
+      return NextResponse.json({
+        success: true,
+        data: {
+          service: 'Jina AI',
+          status: testResult.success ? 'connected' : 'error',
+          error: testResult.error
+        }
+      })
+    }
+
+    if (action === 'config') {
+      // 返回服务配置信息
+      return NextResponse.json({
+        success: true,
+        data: {
+          readerApiEnabled: true,
+          deepSearchEnabled: !!process.env.JINA_API_KEY,
+          supportedModes: ['full', 'summary', 'custom'],
+          maxContentLength: 8000,
+          rateLimits: {
+            reader: '20 requests/minute (free), 500 requests/minute (paid)',
+            deepSearch: '50 requests/minute'
+          }
+        }
+      })
+    }
+
+    return NextResponse.json(
+      { success: false, error: '无效的操作' },
+      { status: 400 }
+    )
+
+  } catch (error) {
+    console.error('Jina config API error:', error)
+    return NextResponse.json(
+      { success: false, error: '获取配置失败' },
+      { status: 500 }
+    )
+  }
+}
diff --git a/app/layout.tsx b/app/layout.tsx
index e0b9429..8474dda 100644
--- a/app/layout.tsx
+++ b/app/layout.tsx
@@ -29,6 +29,7 @@ export default function RootLayout({
     <html lang="en">
       <body
         className={`${geistSans.variable} ${geistMono.variable} antialiased`}
+        suppressHydrationWarning={true}
       >
         <StoreInitializer>
           <SidebarProvider>
diff --git a/components/fragment-input.tsx b/components/fragment-input.tsx
index ad548c1..15dbbef 100644
--- a/components/fragment-input.tsx
+++ b/components/fragment-input.tsx
@@ -3,8 +3,12 @@
 import { useState } from "react"
 import { Textarea } from "@/components/ui/textarea"
 import { Button } from "@/components/ui/button"
+import { Tabs, TabsContent, TabsList, TabsTrigger } from "@/components/ui/tabs"
+import { Card, CardContent, CardHeader, CardTitle } from "@/components/ui/card"
+import { FileText, Globe } from "lucide-react"
 // API调用现在通过Next.js API路由处理，不再需要直接导入
 import { useFragmentStore } from "@/lib/stores/fragment-store"
+import { WebFragmentInput } from "./web-fragment-input"
 
 export function FragmentInput() {
   const [text, setText] = useState("")
@@ -127,20 +131,48 @@ export function FragmentInput() {
   }
 
   return (
-    <div className="flex gap-2 ">
-      <Textarea 
-        value={text}
-        onChange={(e) => setText(e.target.value)}
-        placeholder="输入新的知识碎片..."
-        className="flex-1 min-h-[160px] resize-none"
-      />
-      <Button 
-        onClick={handleAddFragment}
-        disabled={isLoading}
-        className="h-40 px-6"
-      >
-        {isLoading ? "添加中..." : "添加"}
-      </Button>
+    <div className="space-y-6">
+      <Tabs defaultValue="text" className="w-full">
+        <TabsList className="grid w-full grid-cols-2">
+          <TabsTrigger value="text" className="flex items-center gap-2">
+            <FileText className="w-4 h-4" />
+            文本输入
+          </TabsTrigger>
+          <TabsTrigger value="web" className="flex items-center gap-2">
+            <Globe className="w-4 h-4" />
+            网页解析
+          </TabsTrigger>
+        </TabsList>
+        
+        <TabsContent value="text" className="mt-6">
+          <Card>
+            <CardHeader>
+              <CardTitle>手动输入知识碎片</CardTitle>
+            </CardHeader>
+            <CardContent>
+              <div className="flex gap-2">
+                <Textarea 
+                  value={text}
+                  onChange={(e) => setText(e.target.value)}
+                  placeholder="输入新的知识碎片..."
+                  className="flex-1 min-h-[160px] resize-none"
+                />
+                <Button 
+                  onClick={handleAddFragment}
+                  disabled={isLoading}
+                  className="h-40 px-6"
+                >
+                  {isLoading ? "添加中..." : "添加"}
+                </Button>
+              </div>
+            </CardContent>
+          </Card>
+        </TabsContent>
+        
+        <TabsContent value="web" className="mt-6">
+          <WebFragmentInput />
+        </TabsContent>
+      </Tabs>
     </div>
   )
 }
\ No newline at end of file
diff --git a/components/web-fragment-input.tsx b/components/web-fragment-input.tsx
new file mode 100644
index 0000000..62a3dbd
--- /dev/null
+++ b/components/web-fragment-input.tsx
@@ -0,0 +1,465 @@
+"use client"
+
+/**
+ * 网页链接知识碎片输入组件
+ * 支持通过Jina AI解析网页内容并生成知识碎片
+ */
+
+import React, { useState } from 'react'
+import { Card, CardContent, CardHeader, CardTitle } from '@/components/ui/card'
+import { Input } from '@/components/ui/input'
+import { Textarea } from '@/components/ui/textarea'
+import { Button } from '@/components/ui/button'
+import { Badge } from '@/components/ui/badge'
+import { Select, SelectContent, SelectItem, SelectTrigger, SelectValue } from '@/components/ui/select'
+import { Tabs, TabsContent, TabsList, TabsTrigger } from '@/components/ui/tabs'
+import { Alert, AlertDescription } from '@/components/ui/alert'
+import { Progress } from '@/components/ui/progress'
+import { 
+  Globe, 
+  Sparkles, 
+  FileText, 
+  Tag, 
+  Clock, 
+  AlertCircle,
+  CheckCircle2,
+  Copy,
+  ExternalLink,
+  Loader2
+} from 'lucide-react'
+import { useFragmentStore } from '@/lib/stores/fragment-store'
+import { ExtractedWebContent } from '@/lib/jina-service'
+
+export function WebFragmentInput() {
+  const [url, setUrl] = useState('')
+  const [userPrompt, setUserPrompt] = useState('')
+  const [extractMode, setExtractMode] = useState<'full' | 'summary' | 'custom'>('summary')
+  const [isLoading, setIsLoading] = useState(false)
+  const [extractedContent, setExtractedContent] = useState<ExtractedWebContent | null>(null)
+  const [error, setError] = useState<string | null>(null)
+  const [progress, setProgress] = useState(0)
+  
+  const { addFragment } = useFragmentStore()
+
+  // 预设的提取模板
+  const promptTemplates = [
+    {
+      name: '技术要点提取',
+      prompt: '请提取文章中的关键技术要点、核心概念和实践建议，重点关注可操作的内容。'
+    },
+    {
+      name: '新闻摘要',
+      prompt: '请提取新闻的核心事实、关键人物、时间地点和影响分析。'
+    },
+    {
+      name: '学习笔记',
+      prompt: '请整理成学习笔记的格式，包括主要概念、重要观点和实例说明。'
+    },
+    {
+      name: '商业洞察',
+      prompt: '请提取商业相关的洞察、市场趋势、商业模式和战略要点。'
+    },
+    {
+      name: '工具介绍',
+      prompt: '请重点提取工具的功能特性、使用方法、优缺点和适用场景。'
+    }
+  ]
+
+  // 验证URL格式
+  const isValidUrl = (urlString: string): boolean => {
+    try {
+      new URL(urlString)
+      return true
+    } catch {
+      return false
+    }
+  }
+
+  // 处理网页内容提取
+  const handleExtractContent = async () => {
+    if (!url.trim()) {
+      setError('请输入网页链接')
+      return
+    }
+
+    if (!isValidUrl(url)) {
+      setError('请输入有效的网页链接')
+      return
+    }
+
+    if (extractMode === 'custom' && !userPrompt.trim()) {
+      setError('自定义模式需要输入提取要求')
+      return
+    }
+
+    setIsLoading(true)
+    setError(null)
+    setProgress(0)
+    setExtractedContent(null)
+
+    try {
+      // 模拟进度更新
+      const progressInterval = setInterval(() => {
+        setProgress(prev => Math.min(prev + 10, 90))
+      }, 200)
+
+      const response = await fetch('/api/jina/extract', {
+        method: 'POST',
+        headers: {
+          'Content-Type': 'application/json'
+        },
+        body: JSON.stringify({
+          url: url.trim(),
+          userPrompt: extractMode === 'custom' ? userPrompt.trim() : undefined,
+          extractMode,
+          language: 'zh'
+        })
+      })
+
+      clearInterval(progressInterval)
+      setProgress(100)
+
+      const result = await response.json()
+
+      if (!result.success) {
+        throw new Error(result.error || '网页内容提取失败')
+      }
+
+      setExtractedContent(result.data)
+    } catch (error) {
+      console.error('Extract content error:', error)
+      setError(error instanceof Error ? error.message : '提取失败，请稍后重试')
+    } finally {
+      setIsLoading(false)
+      setTimeout(() => setProgress(0), 1000)
+    }
+  }
+
+  // 保存为知识碎片
+  const handleSaveAsFragment = async () => {
+    if (!extractedContent) return
+
+    try {
+      const fragmentData = {
+        title: extractedContent.title,
+        content: extractedContent.extractedContent || extractedContent.content,
+        tags: extractedContent.tags,
+        category: extractedContent.category,
+        priority: extractedContent.priority,
+        status: 'active' as const,
+        createdAt: new Date(),
+        updatedAt: new Date(),
+        metadata: {
+          wordCount: extractedContent.metadata.wordCount,
+          readingTime: extractedContent.metadata.readingTime,
+          source: extractedContent.metadata.url,
+          extractedAt: extractedContent.metadata.extractedAt,
+          userPrompt: extractedContent.metadata.userPrompt
+        }
+      }
+
+      await addFragment(fragmentData)
+      
+      // 成功提示
+      alert(`知识碎片保存成功！\n\n标题：${fragmentData.title}\n分类：${fragmentData.category}\n标签：${fragmentData.tags.join(', ')}`)
+      
+      // 清空表单
+      setUrl('')
+      setUserPrompt('')
+      setExtractedContent(null)
+    } catch (error) {
+      console.error('Save fragment error:', error)
+      setError('保存知识碎片失败')
+    }
+  }
+
+  // 复制内容到剪贴板
+  const copyToClipboard = async (text: string) => {
+    try {
+      await navigator.clipboard.writeText(text)
+      // 可以添加toast提示
+    } catch (error) {
+      console.error('Copy failed:', error)
+    }
+  }
+
+  return (
+    <div className="space-y-6">
+      {/* 输入区域 */}
+      <Card>
+        <CardHeader>
+          <CardTitle className="flex items-center gap-2">
+            <Globe className="w-5 h-5" />
+            网页链接解析
+          </CardTitle>
+        </CardHeader>
+        <CardContent className="space-y-4">
+          {/* URL输入 */}
+          <div>
+            <label className="text-sm font-medium">网页链接 *</label>
+            <div className="mt-1 flex gap-2">
+              <Input
+                value={url}
+                onChange={(e) => setUrl(e.target.value)}
+                placeholder="https://example.com/article"
+                className="flex-1"
+              />
+              <Button 
+                variant="outline" 
+                size="sm"
+                onClick={() => window.open(url, '_blank')}
+                disabled={!isValidUrl(url)}
+              >
+                <ExternalLink className="w-4 h-4" />
+              </Button>
+            </div>
+          </div>
+
+          {/* 提取模式选择 */}
+          <div>
+            <label className="text-sm font-medium">提取模式</label>
+            <Select value={extractMode} onValueChange={(value: any) => setExtractMode(value)}>
+              <SelectTrigger className="mt-1">
+                <SelectValue />
+              </SelectTrigger>
+              <SelectContent>
+                <SelectItem value="full">完整内容</SelectItem>
+                <SelectItem value="summary">智能摘要</SelectItem>
+                <SelectItem value="custom">自定义提取</SelectItem>
+              </SelectContent>
+            </Select>
+          </div>
+
+          {/* 自定义提取要求 */}
+          {extractMode === 'custom' && (
+            <div>
+              <label className="text-sm font-medium">提取要求 *</label>
+              <div className="mt-1 space-y-2">
+                <Textarea
+                  value={userPrompt}
+                  onChange={(e) => setUserPrompt(e.target.value)}
+                  placeholder="请描述您希望从网页中提取什么样的内容..."
+                  className="min-h-[100px]"
+                />
+                
+                {/* 预设模板 */}
+                <div className="flex flex-wrap gap-2">
+                  <span className="text-xs text-muted-foreground">快速模板：</span>
+                  {promptTemplates.map(template => (
+                    <Button
+                      key={template.name}
+                      variant="ghost"
+                      size="sm"
+                      className="h-6 px-2 text-xs"
+                      onClick={() => setUserPrompt(template.prompt)}
+                    >
+                      {template.name}
+                    </Button>
+                  ))}
+                </div>
+              </div>
+            </div>
+          )}
+
+          {/* 操作按钮 */}
+          <div className="flex gap-2">
+            <Button 
+              onClick={handleExtractContent} 
+              disabled={isLoading}
+              className="flex-1"
+            >
+              {isLoading ? (
+                <>
+                  <Loader2 className="w-4 h-4 mr-2 animate-spin" />
+                  解析中...
+                </>
+              ) : (
+                <>
+                  <Sparkles className="w-4 h-4 mr-2" />
+                  开始解析
+                </>
+              )}
+            </Button>
+          </div>
+
+          {/* 进度条 */}
+          {isLoading && progress > 0 && (
+            <div className="space-y-2">
+              <Progress value={progress} className="w-full" />
+              <p className="text-sm text-muted-foreground text-center">
+                正在解析网页内容... {progress}%
+              </p>
+            </div>
+          )}
+
+          {/* 错误提示 */}
+          {error && (
+            <Alert variant="destructive">
+              <AlertCircle className="h-4 w-4" />
+              <AlertDescription>{error}</AlertDescription>
+            </Alert>
+          )}
+        </CardContent>
+      </Card>
+
+      {/* 提取结果展示 */}
+      {extractedContent && (
+        <Card>
+          <CardHeader>
+            <CardTitle className="flex items-center justify-between">
+              <span className="flex items-center gap-2">
+                <CheckCircle2 className="w-5 h-5 text-green-500" />
+                提取结果
+              </span>
+              <Button onClick={handleSaveAsFragment}>
+                <FileText className="w-4 h-4 mr-2" />
+                保存为碎片
+              </Button>
+            </CardTitle>
+          </CardHeader>
+          <CardContent>
+            <Tabs defaultValue="content" className="w-full">
+              <TabsList className="grid w-full grid-cols-4">
+                <TabsTrigger value="content">内容</TabsTrigger>
+                <TabsTrigger value="metadata">元信息</TabsTrigger>
+                <TabsTrigger value="tags">标签分类</TabsTrigger>
+                <TabsTrigger value="raw">原始内容</TabsTrigger>
+              </TabsList>
+              
+              <TabsContent value="content" className="space-y-4">
+                <div>
+                  <div className="flex items-center justify-between mb-2">
+                    <h3 className="font-medium">标题</h3>
+                    <Button
+                      variant="ghost"
+                      size="sm"
+                      onClick={() => copyToClipboard(extractedContent.title)}
+                    >
+                      <Copy className="w-4 h-4" />
+                    </Button>
+                  </div>
+                  <p className="text-lg font-semibold">{extractedContent.title}</p>
+                </div>
+
+                {extractedContent.summary && (
+                  <div>
+                    <div className="flex items-center justify-between mb-2">
+                      <h3 className="font-medium">摘要</h3>
+                      <Button
+                        variant="ghost"
+                        size="sm"
+                        onClick={() => copyToClipboard(extractedContent.summary!)}
+                      >
+                        <Copy className="w-4 h-4" />
+                      </Button>
+                    </div>
+                    <p className="text-muted-foreground">{extractedContent.summary}</p>
+                  </div>
+                )}
+
+                {extractedContent.extractedContent && (
+                  <div>
+                    <div className="flex items-center justify-between mb-2">
+                      <h3 className="font-medium">提取内容</h3>
+                      <Button
+                        variant="ghost"
+                        size="sm"
+                        onClick={() => copyToClipboard(extractedContent.extractedContent!)}
+                      >
+                        <Copy className="w-4 h-4" />
+                      </Button>
+                    </div>
+                    <div className="prose max-w-none">
+                      <pre className="whitespace-pre-wrap text-sm bg-muted p-4 rounded-lg">
+                        {extractedContent.extractedContent}
+                      </pre>
+                    </div>
+                  </div>
+                )}
+              </TabsContent>
+              
+              <TabsContent value="metadata" className="space-y-4">
+                <div className="grid grid-cols-2 gap-4 text-sm">
+                  <div>
+                    <span className="font-medium">来源URL:</span>
+                    <p className="text-muted-foreground break-all">{extractedContent.metadata.url}</p>
+                  </div>
+                  <div>
+                    <span className="font-medium">字数:</span>
+                    <p className="text-muted-foreground">{extractedContent.metadata.wordCount}</p>
+                  </div>
+                  <div>
+                    <span className="font-medium">阅读时长:</span>
+                    <p className="text-muted-foreground">{extractedContent.metadata.readingTime} 分钟</p>
+                  </div>
+                  <div>
+                    <span className="font-medium">提取时间:</span>
+                    <p className="text-muted-foreground">
+                      {new Date(extractedContent.metadata.extractedAt).toLocaleString()}
+                    </p>
+                  </div>
+                  {extractedContent.metadata.userPrompt && (
+                    <div className="col-span-2">
+                      <span className="font-medium">用户要求:</span>
+                      <p className="text-muted-foreground">{extractedContent.metadata.userPrompt}</p>
+                    </div>
+                  )}
+                </div>
+              </TabsContent>
+              
+              <TabsContent value="tags" className="space-y-4">
+                <div>
+                  <h3 className="font-medium mb-2">分类</h3>
+                  <Badge variant="secondary">{extractedContent.category}</Badge>
+                </div>
+                
+                <div>
+                  <h3 className="font-medium mb-2">优先级</h3>
+                  <Badge variant={
+                    extractedContent.priority === 'high' ? 'destructive' :
+                    extractedContent.priority === 'medium' ? 'default' : 'secondary'
+                  }>
+                    {extractedContent.priority === 'high' ? '高' :
+                     extractedContent.priority === 'medium' ? '中' : '低'}
+                  </Badge>
+                </div>
+                
+                <div>
+                  <h3 className="font-medium mb-2">标签</h3>
+                  <div className="flex flex-wrap gap-2">
+                    {extractedContent.tags.map(tag => (
+                      <Badge key={tag} variant="outline">
+                        <Tag className="w-3 h-3 mr-1" />
+                        {tag}
+                      </Badge>
+                    ))}
+                  </div>
+                </div>
+              </TabsContent>
+              
+              <TabsContent value="raw" className="space-y-4">
+                <div>
+                  <div className="flex items-center justify-between mb-2">
+                    <h3 className="font-medium">原始网页内容</h3>
+                    <Button
+                      variant="ghost"
+                      size="sm"
+                      onClick={() => copyToClipboard(extractedContent.content)}
+                    >
+                      <Copy className="w-4 h-4" />
+                    </Button>
+                  </div>
+                  <div className="max-h-96 overflow-y-auto bg-muted p-4 rounded-lg">
+                    <pre className="whitespace-pre-wrap text-xs">
+                      {extractedContent.content}
+                    </pre>
+                  </div>
+                </div>
+              </TabsContent>
+            </Tabs>
+          </CardContent>
+        </Card>
+      )}
+    </div>
+  )
+}
diff --git a/examples/mongodb-usage.md b/examples/mongodb-usage.md
new file mode 100644
index 0000000..1d20a3e
--- /dev/null
+++ b/examples/mongodb-usage.md
@@ -0,0 +1,93 @@
+# MongoDB 使用指南
+
+## 🔐 安全配置
+
+### 1. 环境变量配置
+
+**永远不要将数据库连接字符串直接写入代码！** 
+
+正确的做法是使用环境变量：
+
+```bash
+# .env.local 文件
+MONGODB_URI=mongodb://root:67nz4dqm@dbconn.sealosbja.site:47366/?directConnection=true
+```
+
+### 2. 代码中的使用
+
+```typescript
+// ✅ 正确：使用环境变量
+const mongoUrl = process.env.MONGODB_URI
+
+// ❌ 错误：硬编码敏感信息
+const mongoUrl = "mongodb://root:67nz4dqm@dbconn.sealosbja.site:47366/?directConnection=true"
+```
+
+## 🚀 使用示例
+
+### 初始化连接
+
+```typescript
+import { initMongoDB, getMongoStatus } from '@/lib/mongodb-config'
+
+// 在应用启动时初始化
+async function startApp() {
+  try {
+    await initMongoDB()
+    console.log('数据库连接状态:', getMongoStatus())
+  } catch (error) {
+    console.error('应用启动失败:', error)
+  }
+}
+```
+
+### 在 Next.js API 路由中使用
+
+```typescript
+// app/api/test-mongo/route.ts
+import { NextResponse } from 'next/server'
+import { initMongoDB } from '@/lib/mongodb-config'
+import { getMongoModel } from '@/package/mongo'
+
+export async function GET() {
+  try {
+    // 确保数据库连接
+    await initMongoDB()
+    
+    // 使用数据库
+    // ... 你的业务逻辑
+    
+    return NextResponse.json({ success: true })
+  } catch (error) {
+    return NextResponse.json(
+      { error: '数据库连接失败' },
+      { status: 500 }
+    )
+  }
+}
+```
+
+## 🔒 安全最佳实践
+
+1. **环境变量文件**：
+   - `.env.local` - 本地开发环境
+   - `.env.production` - 生产环境
+   - 这些文件已在 `.gitignore` 中被忽略
+
+2. **生产环境部署**：
+   - 在服务器或云平台上设置环境变量
+   - 不要在代码仓库中提交任何包含敏感信息的文件
+
+3. **权限控制**：
+   - 使用专用的数据库用户
+   - 设置适当的权限级别
+   - 定期更换密码
+
+## 🔧 配置选项
+
+当前项目支持的 MongoDB 环境变量：
+
+- `MONGODB_URI` - 主数据库连接字符串
+- `MONGODB_LOG_URI` - 日志数据库连接字符串（可选）
+- `DB_MAX_LINK` - 最大连接数（默认：20）
+- `SYNC_INDEX` - 是否同步索引（默认：1）
diff --git a/lib/jina-service.ts b/lib/jina-service.ts
new file mode 100644
index 0000000..d773591
--- /dev/null
+++ b/lib/jina-service.ts
@@ -0,0 +1,385 @@
+/**
+ * Jina AI 服务集成
+ * 支持网页解析、内容提取和AI增强处理
+ */
+
+import { delay } from '../package/utils/utils'
+
+// Jina API 响应类型定义
+export interface JinaReaderResponse {
+  success: boolean
+  data?: {
+    title?: string
+    content: string
+    description?: string
+    url: string
+    usage?: {
+      tokens: number
+    }
+  }
+  error?: string
+}
+
+export interface JinaDeepSearchResponse {
+  id: string
+  object: string
+  created: number
+  model: string
+  choices: Array<{
+    index: number
+    message: {
+      content: string
+      role: string
+    }
+    finish_reason: string
+  }>
+  usage: {
+    prompt_tokens: number
+    completion_tokens: number
+    total_tokens: number
+  }
+  visitedURLs?: string[]
+}
+
+export interface WebContentExtractRequest {
+  url: string
+  userPrompt?: string
+  extractMode: 'full' | 'summary' | 'custom'
+  language?: string
+}
+
+export interface ExtractedWebContent {
+  title: string
+  content: string
+  summary?: string
+  extractedContent?: string
+  tags: string[]
+  category: string
+  priority: 'low' | 'medium' | 'high'
+  metadata: {
+    url: string
+    wordCount: number
+    readingTime: number
+    extractedAt: Date
+    userPrompt?: string
+  }
+}
+
+export class JinaService {
+  private readerApiUrl = 'https://r.jina.ai'
+  private deepSearchApiUrl = 'https://deepsearch.jina.ai/v1/chat/completions'
+  private apiKey: string
+
+  constructor(apiKey?: string) {
+    this.apiKey = apiKey || process.env.JINA_API_KEY || ''
+    
+    // 在服务器端环境中获取API密钥
+    if (typeof window === 'undefined' && !this.apiKey) {
+      console.warn('JINA_API_KEY not found in environment variables')
+    }
+  }
+
+  /**
+   * 使用Jina Reader API解析网页内容
+   */
+  async parseWebPage(url: string): Promise<JinaReaderResponse> {
+    try {
+      console.log('Parsing webpage:', url)
+      
+      const headers: Record<string, string> = {
+        'Accept': 'application/json',
+        'User-Agent': 'iKnow/1.0'
+      }
+
+      if (this.apiKey) {
+        headers['Authorization'] = `Bearer ${this.apiKey}`
+        console.log('Using API key for authentication')
+      } else {
+        console.log('No API key provided, using free tier')
+      }
+
+      const requestUrl = `${this.readerApiUrl}/${encodeURIComponent(url)}`
+      console.log('Request URL:', requestUrl)
+
+      const response = await fetch(requestUrl, {
+        method: 'GET',
+        headers,
+        timeout: 30000 // 30秒超时
+      } as any)
+
+      console.log('Response status:', response.status)
+      console.log('Response headers:', Object.fromEntries(response.headers.entries()))
+
+      if (!response.ok) {
+        const errorText = await response.text()
+        console.error('API Error Response:', errorText)
+        throw new Error(`Jina Reader API error: ${response.status} ${response.statusText}. ${errorText}`)
+      }
+
+      const text = await response.text()
+      console.log('Response length:', text.length)
+      
+      // 尝试解析为JSON，如果失败则作为纯文本处理
+      let data
+      try {
+        data = JSON.parse(text)
+        console.log('Successfully parsed JSON response')
+      } catch (parseError) {
+        console.log('Response is not JSON, treating as plain text')
+        data = {
+          content: text,
+          url: url
+        }
+      }
+
+      const result = {
+        success: true,
+        data: {
+          title: data.title || this.extractTitleFromContent(data.content || text) || '未知标题',
+          content: data.content || text,
+          description: data.description,
+          url: url,
+          usage: data.usage
+        }
+      }
+
+      console.log('Parse result:', {
+        success: result.success,
+        titleLength: result.data.title.length,
+        contentLength: result.data.content.length,
+        hasDescription: !!result.data.description
+      })
+
+      return result
+    } catch (error) {
+      console.error('Jina Reader API Error:', error)
+      return {
+        success: false,
+        error: error instanceof Error ? error.message : '网页解析失败'
+      }
+    }
+  }
+
+  /**
+   * 使用DeepSearch API进行智能内容提取
+   */
+  async extractContentWithAI(
+    webContent: string,
+    userPrompt: string,
+    url: string
+  ): Promise<JinaDeepSearchResponse | null> {
+    try {
+      if (!this.apiKey) {
+        throw new Error('需要Jina API密钥才能使用DeepSearch功能')
+      }
+
+      const messages = [
+        {
+          role: 'system',
+          content: 
+          `你是一个专业的内容提取助手。用户会提供网页内容和特定的提取要求，请根据要求提取并整理内容。
+          网页URL: ${url}
+          返回结果需要纯文本形式输出，不要用 json 格式。包含以下字段：
+            "title": "提取内容的标题",
+            "summary": "内容摘要（50-100字）",
+            "extractedContent": "根据用户要求提取的具体内容",
+            "tags": ["相关标签1", "相关标签2", "相关标签3"],
+            "category": "内容分类",
+            "priority": "low|medium|high",
+            "insights": "从内容中得出的见解或要点"
+  `
+        },
+        {
+          role: 'user',
+          content: `网页内容：
+${webContent.slice(0, 8000)} ${webContent.length > 8000 ? '...(内容已截断)' : ''}
+
+用户提取要求：
+${userPrompt}`
+        }
+      ]
+
+      const response = await fetch(this.deepSearchApiUrl, {
+        method: 'POST',
+        headers: {
+          'Content-Type': 'application/json',
+          'Authorization': `Bearer ${this.apiKey}`
+        },
+        body: JSON.stringify({
+          model: 'jina-deepsearch-v1',
+          messages,
+          stream: false,
+          reasoning_effort: 'medium',
+          max_returned_urls: 0 // 不需要额外搜索URL
+        })
+      })
+
+      if (!response.ok) {
+        throw new Error(`DeepSearch API error: ${response.status} ${response.statusText}`)
+      }
+
+      const result = await response.json()
+      return result
+    } catch (error) {
+      console.error('Jina DeepSearch API Error:', error)
+      return null
+    }
+  }
+
+  /**
+   * 完整的网页内容提取流程
+   */
+  async extractWebContent(request: WebContentExtractRequest): Promise<ExtractedWebContent | null> {
+    try {
+      // 1. 使用Reader API解析网页
+      const readerResult = await this.parseWebPage(request.url)
+      
+      if (!readerResult.success || !readerResult.data) {
+        throw new Error(readerResult.error || '网页解析失败')
+      }
+
+      const { title, content, url } = readerResult.data
+
+      // 2. 如果有用户prompt，使用DeepSearch AI提取内容
+      let extractedData: any = {}
+      
+      if (request.userPrompt && request.extractMode === 'custom') {
+        const aiResult = await this.extractContentWithAI(content, request.userPrompt, url)
+        
+        if (aiResult?.choices?.[0]?.message?.content) {
+          try {
+            extractedData = JSON.parse(aiResult.choices[0].message.content)
+          } catch (error) {
+            console.warn('AI响应解析失败，使用默认处理:', error)
+            extractedData = {
+              extractedContent: aiResult.choices[0].message.content
+            }
+          }
+        }
+      }
+
+      // 3. 构建最终结果
+      const wordCount = content.length
+      const result: ExtractedWebContent = {
+        title: extractedData.title || title,
+        content: content,
+        summary: extractedData.summary || this.generateSummary(content),
+        extractedContent: extractedData.extractedContent,
+        tags: extractedData.tags || this.extractDefaultTags(content, title),
+        category: extractedData.category || this.inferCategory(title, content),
+        priority: extractedData.priority || 'medium',
+        metadata: {
+          url: url,
+          wordCount: wordCount,
+          readingTime: Math.ceil(wordCount / 200),
+          extractedAt: new Date(),
+          userPrompt: request.userPrompt
+        }
+      }
+
+      return result
+    } catch (error) {
+      console.error('Web content extraction error:', error)
+      return null
+    }
+  }
+
+  /**
+   * 批量处理多个网页链接
+   */
+  async batchExtractWebContent(
+    requests: WebContentExtractRequest[],
+    onProgress?: (processed: number, total: number) => void
+  ): Promise<(ExtractedWebContent | null)[]> {
+    const results: (ExtractedWebContent | null)[] = []
+    
+    for (let i = 0; i < requests.length; i++) {
+      try {
+        const result = await this.extractWebContent(requests[i])
+        results.push(result)
+        
+        // 添加延迟避免API限制
+        if (i < requests.length - 1) {
+          await delay(1000) // 1秒延迟
+        }
+        
+        onProgress?.(i + 1, requests.length)
+      } catch (error) {
+        console.error(`处理第${i + 1}个链接失败:`, error)
+        results.push(null)
+      }
+    }
+    
+    return results
+  }
+
+  /**
+   * 从内容中提取标题（备用方法）
+   */
+  private extractTitleFromContent(content: string): string | null {
+    // 尝试从内容开头提取标题
+    const lines = content.split('\n').filter(line => line.trim())
+    if (lines.length > 0) {
+      const firstLine = lines[0].trim()
+      if (firstLine.length > 0 && firstLine.length < 100) {
+        return firstLine
+      }
+    }
+    return null
+  }
+
+  /**
+   * 生成内容摘要
+   */
+  private generateSummary(content: string, maxLength: number = 200): string {
+    const cleanContent = content.replace(/\s+/g, ' ').trim()
+    if (cleanContent.length <= maxLength) {
+      return cleanContent
+    }
+    return cleanContent.slice(0, maxLength) + '...'
+  }
+
+  /**
+   * 提取默认标签
+   */
+  private extractDefaultTags(content: string, title: string): string[] {
+    const text = `${title} ${content}`.toLowerCase()
+    const commonTags = [
+      '技术', '教程', '新闻', '分析', '指南', '工具', '产品', '服务',
+      'AI', '机器学习', '编程', '开发', '设计', '商业', '科技', '创新'
+    ]
+    
+    const foundTags = commonTags.filter(tag => 
+      text.includes(tag.toLowerCase()) || 
+      text.includes(tag)
+    )
+    
+    return foundTags.slice(0, 5) // 最多返回5个标签
+  }
+
+  /**
+   * 推断内容分类
+   */
+  private inferCategory(title: string, content: string): string {
+    const text = `${title} ${content}`.toLowerCase()
+    
+    const categories = {
+      '技术文档': ['api', 'documentation', 'tutorial', 'guide', '教程', '文档'],
+      '新闻资讯': ['news', 'announcement', 'update', '新闻', '公告', '更新'],
+      '学习资料': ['learn', 'course', 'education', 'study', '学习', '课程'],
+      '工具介绍': ['tool', 'software', 'app', 'service', '工具', '软件'],
+      '商业分析': ['business', 'market', 'analysis', '商业', '市场', '分析']
+    }
+    
+    for (const [category, keywords] of Object.entries(categories)) {
+      if (keywords.some(keyword => text.includes(keyword))) {
+        return category
+      }
+    }
+    
+    return '其他'
+  }
+}
+
+// 默认实例
+export const jinaService = new JinaService()
diff --git a/lib/mongodb-config.ts b/lib/mongodb-config.ts
new file mode 100644
index 0000000..e294293
--- /dev/null
+++ b/lib/mongodb-config.ts
@@ -0,0 +1,64 @@
+/**
+ * MongoDB 配置文件
+ * 
+ * 该文件展示了如何安全地使用环境变量来配置MongoDB连接
+ * 而不是将敏感信息硬编码到代码中
+ */
+
+import { connectMongo } from '../package/mongo/init'
+import { connectionMongo, MONGO_URL } from '../package/mongo/index'
+
+/**
+ * 初始化MongoDB连接
+ * 使用环境变量中的连接字符串
+ */
+export async function initMongoDB() {
+  try {
+    // 检查环境变量是否配置
+    if (!MONGO_URL) {
+      throw new Error('MONGODB_URI 环境变量未配置。请在 .env.local 文件中设置 MONGODB_URI')
+    }
+
+    console.log('正在连接 MongoDB...')
+    
+    // 使用环境变量中的连接字符串连接数据库
+    await connectMongo(connectionMongo, MONGO_URL)
+    
+    console.log('MongoDB 连接成功')
+    return connectionMongo
+  } catch (error) {
+    console.error('MongoDB 连接失败:', error)
+    throw error
+  }
+}
+
+/**
+ * 获取MongoDB连接状态
+ */
+export function getMongoStatus() {
+  const states = {
+    0: '断开连接',
+    1: '已连接',
+    2: '正在连接',
+    3: '正在断开连接'
+  }
+  
+  return {
+    state: connectionMongo.connection.readyState,
+    stateText: states[connectionMongo.connection.readyState as keyof typeof states] || '未知状态',
+    host: connectionMongo.connection.host,
+    name: connectionMongo.connection.name
+  }
+}
+
+/**
+ * 关闭MongoDB连接
+ */
+export async function closeMongoDB() {
+  try {
+    await connectionMongo.disconnect()
+    console.log('MongoDB 连接已关闭')
+  } catch (error) {
+    console.error('关闭 MongoDB 连接时出错:', error)
+  }
+}