http://hblu.top:3000/Python2025-CourseDesign/SPC.git

Project_Design.md

@@ -0,0 +1,16 @@
+# 智能知识库问答 - 项目设计文档
+
+## 一句话描述
+我的应用叫"智能知识库问答"，它是给企业和课程使用的，用于自有文档精准问答，减少人工答疑。
+
+## 核心功能（MVP）
+1. **文档上传** - 支持上传PDF、Word、TXT等格式的文档，系统自动解析并建立知识库索引
+2. **智能问答** - 用户输入问题，AI基于上传的文档内容进行精准检索和回答
+3. **知识库管理** - 查看已上传的文档列表，支持删除文档，查看文档处理状态
+
+## 交互流程
+1. 用户打开 App → 看到主界面，包含文档上传区和问答区
+2. 用户点击"上传文档"按钮 → 选择本地文档文件 → 系统显示上传进度和处理状态
+3. 文档处理完成后 → 在问答输入框中输入问题
+4. 点击"提问"按钮 → AI检索知识库并返回答案，同时显示参考文档来源
+5. 用户可以继续提问或上传更多文档

README.md

@@ -0,0 +1,235 @@
+# 🧠 智能知识库问答系统
+
+一个基于 Flask 的企业/课程智能问答系统，支持上传自有文档并进行精准问答，减少人工答疑成本。
+
+## ✨ 核心功能
+
+- 📚 **文档上传与管理**：支持上传 PDF、Word、TXT 等格式的文档，自动进行智能解析
+- 🤖 **智能问答**：基于上传的文档内容，提供精准的问答服务
+- 💾 **对话历史**：自动保存所有问答记录，方便回顾和查看
+- 📱 **响应式设计**：完美支持桌面端和移动端访问
+- 🎨 **美观界面**：现代化的 UI 设计，提供良好的用户体验
+
+## 🚀 快速开始
+
+### 环境要求
+
+- Python 3.8+
+- pip
+
+### 安装步骤
+
+1. **克隆项目**
+```bash
+git clone <repository-url>
+cd 12
+```
+
+2. **安装依赖**
+```bash
+pip install -r requirements.txt
+```
+
+3. **配置环境变量**
+
+创建 `.env` 文件并配置以下变量：
+```env
+OPENAI_API_KEY=your_openai_api_key_here
+FLASK_SECRET_KEY=your_secret_key_here
+```
+
+4. **初始化数据库**
+```bash
+python app.py
+```
+
+数据库会自动创建在项目根目录下的 `knowledge_base.db` 文件中。
+
+5. **启动应用**
+```bash
+python app.py
+```
+
+应用将在 `http://localhost:5000` 启动。
+
+## 📖 使用指南
+
+### 1. 上传文档
+
+- 点击左侧知识库面板的"📤 点击或拖拽上传文档"区域
+- 选择要上传的文档（支持 PDF、Word、TXT 格式）
+- 系统会自动解析文档内容并建立知识库索引
+
+### 2. 提问
+
+- 在右侧聊天输入框中输入问题
+- 点击"发送"按钮或按 Enter 键提交问题
+- 系统会基于上传的文档内容提供精准答案
+- 答案会显示参考来源，包括文档名称和页码
+
+### 3. 管理文档
+
+- 在知识库面板中查看所有已上传的文档
+- 点击"🗑️ 删除"按钮可以删除不需要的文档
+- 文档状态会显示处理进度（处理中/已完成）
+
+### 4. 查看历史
+
+- 所有问答记录会自动保存
+- 刷新页面后会自动加载历史对话
+- 可以随时查看之前的问答内容
+
+## 🎬 演示流程
+
+### 场景 1：课程答疑
+
+1. **准备阶段**
+   - 上传课程讲义 PDF 文件
+   - 等待系统完成文档解析（约 2-3 秒）
+
+2. **提问演示**
+   - 输入："这门课程的主要学习目标是什么？"
+   - 系统返回基于讲义的答案，并标注参考页码
+   - 继续提问："如何完成期末作业？"
+   - 系统提供详细的作业要求说明
+
+3. **效果展示**
+   - 展示答案的准确性和参考来源
+   - 展示对话历史的保存和加载
+
+### 场景 2：企业文档查询
+
+1. **准备阶段**
+   - 上传公司规章制度文档
+   - 上传产品说明书文档
+
+2. **提问演示**
+   - 输入："公司的请假流程是怎样的？"
+   - 系统从规章制度中提取相关内容
+   - 输入："产品 A 的保修期是多久？"
+   - 系统从产品说明书中找到答案
+
+3. **效果展示**
+   - 展示多文档知识库的整合能力
+   - 展示移动端的响应式设计
+
+## 🛠️ 技术架构
+
+### 后端技术栈
+
+- **Flask**：轻量级 Web 框架
+- **SQLite**：本地数据库，用于存储对话历史和文档信息
+- **OpenAI API**：提供智能问答能力
+- **LangChain**：文档处理和向量检索（计划中）
+- **ChromaDB**：向量数据库（计划中）
+
+### 前端技术栈
+
+- **HTML5**：页面结构
+- **CSS3**：样式设计，包含响应式布局
+- **JavaScript**：交互逻辑和 API 调用
+
+### 项目结构
+
+```
+12/
+├── app.py                      # Flask 应用主文件
+├── requirements.txt            # Python 依赖
+├── Project_Design.md          # 项目设计文档
+├── README.md                  # 项目说明文档
+├── knowledge_base.db          # SQLite 数据库（自动生成）
+├── templates/
+│   └── index.html            # 前端页面模板
+└── static/
+    ├── style.css             # 样式文件
+    └── script.js             # JavaScript 脚本
+```
+
+## 🔧 API 接口
+
+### 上传文档
+```
+POST /api/upload
+Content-Type: multipart/form-data
+
+Body: file (文件)
+Response: { id, name, status }
+```
+
+### 获取文档列表
+```
+GET /api/documents
+Response: [{ id, name, status, chunks, created_at }]
+```
+
+### 删除文档
+```
+DELETE /api/documents/{doc_id}
+Response: { success: true }
+```
+
+### 提问
+```
+POST /api/ask
+Content-Type: application/json
+
+Body: { question: "问题内容" }
+Response: { answer, sources: [{ name, page }] }
+```
+
+### 获取对话历史
+```
+GET /api/conversations
+Response: [{ id, question, answer, sources, created_at }]
+```
+
+## 🎨 界面特性
+
+### 响应式设计
+
+- **桌面端**（>1024px）：双栏布局，左侧知识库，右侧聊天
+- **平板端**（768px-1024px）：单栏布局，优化间距
+- **移动端**（<768px）：全屏显示，垂直堆叠，大按钮设计
+
+### 交互反馈
+
+- Toast 通知系统，实时显示操作状态
+- 字符计数器，提示输入长度
+- 加载状态指示，提升用户体验
+- Emoji 图标，增强视觉识别
+
+## 📝 注意事项
+
+1. **API 密钥**：确保正确配置 OpenAI API 密钥
+2. **文档格式**：目前支持 PDF、Word、TXT 格式
+3. **问题长度**：建议问题长度在 3-500 字之间
+4. **数据库**：对话历史保存在本地 SQLite 数据库中
+5. **浏览器兼容**：建议使用 Chrome、Firefox、Edge 等现代浏览器
+
+## 🚧 未来规划
+
+- [ ] 集成 LangChain 进行更强大的文档处理
+- [ ] 使用 ChromaDB 建立向量数据库
+- [ ] 支持更多文档格式（Excel、PPT 等）
+- [ ] 添加文档预览功能
+- [ ] 实现对话导出功能
+- [ ] 添加用户认证和权限管理
+- [ ] 支持多语言问答
+
+## 📄 许可证
+
+MIT License
+
+## 🤝 贡献
+
+欢迎提交 Issue 和 Pull Request！
+
+## 📧 联系方式
+
+如有问题或建议，请通过以下方式联系：
+- 提交 Issue
+- 发送邮件至：your-email@example.com
+
+---
+
+**享受智能问答带来的便利！** 🎉

app.py

@@ -0,0 +1,334 @@
+import os
+import sqlite3
+import json
+from flask import Flask, render_template, request, jsonify
+from werkzeug.utils import secure_filename
+import uuid
+from datetime import datetime
+from dotenv import load_dotenv
+from openai import OpenAI
+
+load_dotenv()
+
+app = Flask(__name__)
+app.config['UPLOAD_FOLDER'] = 'uploads'
+app.config['MAX_CONTENT_LENGTH'] = 16 * 1024 * 1024
+app.config['DATABASE'] = 'knowledge_base.db'
+
+DEEPSEEK_API_KEY = os.getenv('DEEPSEEK_API_KEY')
+DEEPSEEK_BASE_URL = os.getenv('DEEPSEEK_BASE_URL', 'https://api.deepseek.com')
+
+client = OpenAI(
+    api_key=DEEPSEEK_API_KEY,
+    base_url=DEEPSEEK_BASE_URL
+)
+
+ALLOWED_EXTENSIONS = {'txt', 'pdf', 'docx'}
+
+os.makedirs(app.config['UPLOAD_FOLDER'], exist_ok=True)
+
+documents = {}
+
+def init_db():
+    conn = sqlite3.connect(app.config['DATABASE'])
+    cursor = conn.cursor()
+    cursor.execute('''
+        CREATE TABLE IF NOT EXISTS conversations (
+            id INTEGER PRIMARY KEY AUTOINCREMENT,
+            question TEXT NOT NULL,
+            answer TEXT NOT NULL,
+            sources TEXT,
+            created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
+        )
+    ''')
+    cursor.execute('''
+        CREATE TABLE IF NOT EXISTS documents (
+            id TEXT PRIMARY KEY,
+            name TEXT NOT NULL,
+            status TEXT NOT NULL,
+            chunks INTEGER DEFAULT 0,
+            created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
+        )
+    ''')
+    conn.commit()
+    conn.close()
+
+def get_db_connection():
+    conn = sqlite3.connect(app.config['DATABASE'])
+    conn.row_factory = sqlite3.Row
+    return conn
+
+def load_documents_from_db():
+    conn = get_db_connection()
+    docs = conn.execute('SELECT * FROM documents ORDER BY created_at DESC').fetchall()
+    conn.close()
+    
+    global documents
+    documents = {doc['id']: dict(doc) for doc in docs}
+
+def allowed_file(filename):
+    return '.' in filename and filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS
+
+def read_document_content(doc_id):
+    try:
+        for file in os.listdir(app.config['UPLOAD_FOLDER']):
+            if file.startswith(doc_id):
+                filepath = os.path.join(app.config['UPLOAD_FOLDER'], file)
+                
+                # 根据文件扩展名判断类型
+                if file.lower().endswith('.txt'):
+                    with open(filepath, 'r', encoding='utf-8') as f:
+                        return f.read()
+                
+                elif file.lower().endswith('.pdf'):
+                    import pypdf
+                    with open(filepath, 'rb') as f:
+                        reader = pypdf.PdfReader(f)
+                        text = ''
+                        for page in reader.pages:
+                            text += page.extract_text() + '\n'
+                        return text
+                
+                elif file.lower().endswith('.docx'):
+                    from docx import Document
+                    doc = Document(filepath)
+                    text = ''
+                    for paragraph in doc.paragraphs:
+                        text += paragraph.text + '\n'
+                    return text
+                
+                # 如果没有扩展名，尝试按顺序尝试不同格式
+                else:
+                    # 先尝试作为 docx 文件
+                    try:
+                        from docx import Document
+                        doc = Document(filepath)
+                        text = ''
+                        for paragraph in doc.paragraphs:
+                            text += paragraph.text + '\n'
+                        if text.strip():
+                            return text
+                    except:
+                        pass
+                    
+                    # 再尝试作为 txt 文件
+                    try:
+                        with open(filepath, 'r', encoding='utf-8') as f:
+                            text = f.read()
+                            if text.strip():
+                                return text
+                    except:
+                        pass
+                    
+                    # 最后尝试作为 pdf 文件
+                    try:
+                        import pypdf
+                        with open(filepath, 'rb') as f:
+                            reader = pypdf.PdfReader(f)
+                            text = ''
+                            for page in reader.pages:
+                                text += page.extract_text() + '\n'
+                            if text.strip():
+                                return text
+                    except:
+                        pass
+        
+        return None
+    except Exception as e:
+        print(f"Error reading document: {e}")
+        import traceback
+        traceback.print_exc()
+        return None
+
+@app.route('/')
+def index():
+    load_documents_from_db()
+    return render_template('index.html')
+
+@app.route('/api/upload', methods=['POST'])
+def upload_document():
+    try:
+        if 'file' not in request.files:
+            return jsonify({'error': '没有文件'}), 400
+        
+        file = request.files['file']
+        if file.filename == '':
+            return jsonify({'error': '没有选择文件'}), 400
+        
+        if file and allowed_file(file.filename):
+            doc_id = str(uuid.uuid4())
+            filename = secure_filename(file.filename)
+            filepath = os.path.join(app.config['UPLOAD_FOLDER'], f"{doc_id}_{filename}")
+            file.save(filepath)
+            
+            conn = get_db_connection()
+            conn.execute(
+                'INSERT INTO documents (id, name, status, chunks) VALUES (?, ?, ?, ?)',
+                (doc_id, filename, 'completed', 1)
+            )
+            conn.commit()
+            conn.close()
+            
+            load_documents_from_db()
+            
+            return jsonify({
+                'id': doc_id,
+                'name': filename,
+                'status': 'completed'
+            })
+        
+        return jsonify({'error': '不支持的文件格式'}), 400
+    
+    except Exception as e:
+        return jsonify({'error': f'上传失败：{str(e)}'}), 500
+
+@app.route('/api/ask', methods=['POST'])
+def ask_question():
+    try:
+        data = request.json
+        question = data.get('question', '')
+        
+        if not question or not question.strip():
+            return jsonify({'error': '请输入问题'}), 400
+        
+        if len(question) > 1000:
+            return jsonify({'error': '问题长度不能超过1000字'}), 400
+        
+        load_documents_from_db()
+        
+        if not documents:
+            return jsonify({'error': '请先上传文档'}), 400
+        
+        context_parts = []
+        sources = []
+        
+        for doc_id, doc_info in documents.items():
+            if doc_info['status'] == 'completed':
+                content = read_document_content(doc_id)
+                if content:
+                    context_parts.append(f"文档：{doc_info['name']}\n内容：{content[:3000]}")
+                    sources.append({
+                        'doc_id': doc_id,
+                        'name': doc_info['name'],
+                        'page': 1
+                    })
+        
+        if not context_parts:
+            return jsonify({'error': '没有可用的文档内容'}), 400
+        
+        context = '\n\n'.join(context_parts)
+        
+        system_prompt = """你是一个智能知识库问答助手。请基于提供的文档内容回答用户的问题。
+要求：
+1. 只使用文档中的信息回答问题
+2. 如果文档中没有相关信息，请明确说明
+3. 回答要准确、简洁、有条理
+4. 使用中文回答"""
+        
+        user_prompt = f"""文档内容：
+{context}
+
+用户问题：{question}
+
+请基于以上文档内容回答用户的问题。"""
+        
+        try:
+            response = client.chat.completions.create(
+                model="deepseek-chat",
+                messages=[
+                    {"role": "system", "content": system_prompt},
+                    {"role": "user", "content": user_prompt}
+                ],
+                temperature=0.7,
+                max_tokens=2000
+            )
+            
+            answer = response.choices[0].message.content
+            
+            result = {
+                'question': question,
+                'answer': answer,
+                'sources': sources
+            }
+            
+            conn = get_db_connection()
+            conn.execute(
+                'INSERT INTO conversations (question, answer, sources) VALUES (?, ?, ?)',
+                (question, result['answer'], json.dumps(result['sources']))
+            )
+            conn.commit()
+            conn.close()
+            
+            return jsonify(result)
+        
+        except Exception as api_error:
+            print(f"DeepSeek API Error: {api_error}")
+            return jsonify({'error': f'AI服务暂时不可用：{str(api_error)}'}), 500
+    
+    except Exception as e:
+        return jsonify({'error': f'回答问题时出错：{str(e)}'}), 500
+
+@app.route('/api/documents', methods=['GET'])
+def get_documents():
+    try:
+        load_documents_from_db()
+        return jsonify(list(documents.values()))
+    except Exception as e:
+        return jsonify({'error': f'获取文档列表失败：{str(e)}'}), 500
+
+@app.route('/api/documents/<doc_id>', methods=['DELETE'])
+def delete_document(doc_id):
+    try:
+        conn = get_db_connection()
+        cursor = conn.execute('DELETE FROM documents WHERE id = ?', (doc_id,))
+        
+        if cursor.rowcount == 0:
+            conn.close()
+            return jsonify({'error': '文档不存在'}), 404
+        
+        conn.commit()
+        conn.close()
+        
+        load_documents_from_db()
+        return jsonify({'success': True})
+    
+    except Exception as e:
+        return jsonify({'error': f'删除文档失败：{str(e)}'}), 500
+
+@app.route('/api/conversations', methods=['GET'])
+def get_conversations():
+    try:
+        conn = get_db_connection()
+        conversations = conn.execute(
+            'SELECT * FROM conversations ORDER BY created_at DESC LIMIT 50'
+        ).fetchall()
+        conn.close()
+        
+        result = []
+        for conv in conversations:
+            conv_dict = dict(conv)
+            conv_dict['sources'] = json.loads(conv_dict['sources']) if conv_dict['sources'] else []
+            result.append(conv_dict)
+        
+        return jsonify(result)
+    
+    except Exception as e:
+        return jsonify({'error': f'获取对话历史失败：{str(e)}'}), 500
+
+@app.route('/api/conversations', methods=['DELETE'])
+def clear_conversations():
+    try:
+        conn = get_db_connection()
+        conn.execute('DELETE FROM conversations')
+        conn.commit()
+        conn.close()
+        
+        return jsonify({'success': True})
+    
+    except Exception as e:
+        return jsonify({'error': f'清除对话历史失败：{str(e)}'}), 500
+
+if __name__ == '__main__':
+    init_db()
+    load_documents_from_db()
+    app.run(debug=True, port=5000)

check_db.py

@@ -0,0 +1,27 @@
+import sqlite3
+import os
+
+conn = sqlite3.connect('knowledge_base.db')
+cursor = conn.cursor()
+
+print("=== 数据库中的文档 ===")
+cursor.execute('SELECT * FROM documents')
+docs = cursor.fetchall()
+if docs:
+    for row in docs:
+        print(f"ID: {row[0]}, Name: {row[1]}, Status: {row[2]}, Chunks: {row[3]}")
+else:
+    print("数据库中没有文档")
+
+print("\n=== uploads 文件夹中的文件 ===")
+if os.path.exists('uploads'):
+    files = os.listdir('uploads')
+    if files:
+        for f in files:
+            print(f"文件: {f}")
+    else:
+        print("uploads 文件夹为空")
+else:
+    print("uploads 文件夹不存在")
+
+conn.close()

cleanup_db.py

@@ -0,0 +1,34 @@
+import sqlite3
+import os
+
+conn = sqlite3.connect('knowledge_base.db')
+cursor = conn.cursor()
+
+print("=== 清理无效的文档记录 ===\n")
+
+cursor.execute('SELECT * FROM documents')
+docs = cursor.fetchall()
+
+for doc in docs:
+    doc_id, name, status, chunks, created_at = doc
+    print(f"检查文档: ID={doc_id}, Name={name}, Status={status}")
+    
+    found = False
+    if os.path.exists('uploads'):
+        for file in os.listdir('uploads'):
+            if file.startswith(doc_id):
+                print(f"  ✓ 找到文件: {file}")
+                found = True
+                break
+    
+    if not found:
+        print(f"  ✗ 未找到文件，删除记录")
+        cursor.execute('DELETE FROM documents WHERE id = ?', (doc_id,))
+    else:
+        print(f"  ✓ 保留记录")
+    print()
+
+conn.commit()
+conn.close()
+
+print("=== 清理完成 ===")

requirements.txt

@@ -0,0 +1,8 @@
+flask==3.0.0
+openai>=1.50.0
+python-dotenv==1.0.0
+langchain==0.1.0
+langchain-openai==0.0.2
+pypdf==3.17.4
+python-docx==1.1.0
+chromadb==0.4.22

static/script.js

@@ -0,0 +1,272 @@
+const uploadArea = document.getElementById('upload-area');
+const fileInput = document.getElementById('file-input');
+const documentList = document.getElementById('document-list');
+const chatMessages = document.getElementById('chat-messages');
+const questionInput = document.getElementById('question-input');
+const docCount = document.getElementById('doc-count');
+const charCount = document.getElementById('char-count');
+const toast = document.getElementById('toast');
+
+function showToast(message, duration = 3000) {
+    toast.textContent = message;
+    toast.classList.add('show');
+    
+    setTimeout(() => {
+        toast.classList.remove('show');
+    }, duration);
+}
+
+uploadArea.addEventListener('click', () => fileInput.click());
+
+uploadArea.addEventListener('dragover', (e) => {
+    e.preventDefault();
+    uploadArea.style.borderColor = '#1e3c72';
+    uploadArea.style.background = '#e8f0fe';
+});
+
+uploadArea.addEventListener('dragleave', () => {
+    uploadArea.style.borderColor = '#cbd5e0';
+    uploadArea.style.background = 'transparent';
+});
+
+uploadArea.addEventListener('drop', (e) => {
+    e.preventDefault();
+    uploadArea.style.borderColor = '#cbd5e0';
+    uploadArea.style.background = 'transparent';
+    
+    const files = e.dataTransfer.files;
+    if (files.length > 0) {
+        uploadFile(files[0]);
+    }
+});
+
+fileInput.addEventListener('change', (e) => {
+    if (e.target.files.length > 0) {
+        uploadFile(e.target.files[0]);
+    }
+});
+
+async function uploadFile(file) {
+    const formData = new FormData();
+    formData.append('file', file);
+    
+    try {
+        showToast('⏳ 正在上传文档...');
+        
+        const response = await fetch('/api/upload', {
+            method: 'POST',
+            body: formData
+        });
+        
+        const data = await response.json();
+        
+        if (data.error) {
+            showToast(`❌ ${data.error}`);
+            return;
+        }
+        
+        loadDocuments();
+        showToast(`✅ 文档 "${data.name}" 上传成功，正在处理中...`);
+        addMessage('bot', `📄 文档 "${data.name}" 已上传，系统正在智能解析文档内容...`);
+        
+        setTimeout(() => {
+            loadDocuments();
+        }, 2000);
+        
+    } catch (error) {
+        showToast('❌ 上传失败，请重试');
+        console.error(error);
+    }
+}
+
+async function loadDocuments() {
+    try {
+        const response = await fetch('/api/documents');
+        const documents = await response.json();
+        
+        docCount.textContent = `${documents.length} 个文档`;
+        
+        if (documents.length === 0) {
+            documentList.innerHTML = `
+                <div class="empty-state">
+                    <div class="empty-icon">📭</div>
+                    <p>暂无文档</p>
+                    <p class="empty-hint">上传文档后即可开始问答</p>
+                </div>
+            `;
+            return;
+        }
+        
+        documentList.innerHTML = documents.map(doc => `
+            <div class="document-item">
+                <div class="document-info">
+                    <div class="document-name">📄 ${doc.name}</div>
+                    <div class="document-status ${doc.status}">
+                        ${doc.status === 'processing' ? '⏳ 处理中...' : '✅ 已完成'}
+                    </div>
+                </div>
+                <button class="delete-btn" onclick="deleteDocument('${doc.id}')">🗑️ 删除</button>
+            </div>
+        `).join('');
+        
+    } catch (error) {
+        console.error(error);
+        showToast('❌ 加载文档列表失败');
+    }
+}
+
+async function deleteDocument(docId) {
+    if (!confirm('确定要删除这个文档吗？')) {
+        return;
+    }
+    
+    try {
+        showToast('⏳ 正在删除文档...');
+        
+        await fetch(`/api/documents/${docId}`, {
+            method: 'DELETE'
+        });
+        
+        loadDocuments();
+        showToast('✅ 文档已删除');
+        addMessage('bot', '🗑️ 文档已从知识库中删除');
+        
+    } catch (error) {
+        showToast('❌ 删除失败，请重试');
+        console.error(error);
+    }
+}
+
+async function askQuestion() {
+    const question = questionInput.value.trim();
+    
+    if (!question) {
+        showToast('⚠️ 请输入问题');
+        questionInput.focus();
+        return;
+    }
+    
+    if (question.length < 3) {
+        showToast('⚠️ 问题太短，请输入至少3个字符');
+        questionInput.focus();
+        return;
+    }
+    
+    addMessage('user', question);
+    questionInput.value = '';
+    updateCharCount();
+    
+    try {
+        showToast('🤖 正在思考中...');
+        
+        const response = await fetch('/api/ask', {
+            method: 'POST',
+            headers: {
+                'Content-Type': 'application/json'
+            },
+            body: JSON.stringify({ question })
+        });
+        
+        const data = await response.json();
+        
+        if (data.error) {
+            showToast(`❌ ${data.error}`);
+            addMessage('bot', `❌ 抱歉，${data.error}`);
+            return;
+        }
+        
+        let answerHtml = `<p>${data.answer}</p>`;
+        
+        if (data.sources && data.sources.length > 0) {
+            answerHtml += `
+                <div class="sources">
+                    <div class="sources-title">📚 参考来源：</div>
+                    ${data.sources.map(source => `
+                        <div class="source-item">📄 ${source.name} (第${source.page}页)</div>
+                    `).join('')}
+                </div>
+            `;
+        }
+        
+        showToast('✅ 回答完成');
+        addMessage('bot', answerHtml);
+        
+    } catch (error) {
+        showToast('❌ 回答问题时出错了，请重试');
+        addMessage('bot', '❌ 抱歉，回答问题时出错了，请重试');
+        console.error(error);
+    }
+}
+
+function addMessage(type, content) {
+    const messageDiv = document.createElement('div');
+    messageDiv.className = `message ${type}`;
+    messageDiv.innerHTML = `
+        <div class="message-content">
+            ${content}
+        </div>
+    `;
+    
+    chatMessages.appendChild(messageDiv);
+    chatMessages.scrollTop = chatMessages.scrollHeight;
+}
+
+function updateCharCount() {
+    const length = questionInput.value.length;
+    charCount.textContent = `${length} 字`;
+    
+    if (length > 500) {
+        charCount.style.color = '#e53e3e';
+    } else if (length > 300) {
+        charCount.style.color = '#d69e2e';
+    } else {
+        charCount.style.color = '#718096';
+    }
+}
+
+async function loadConversationHistory() {
+    try {
+        const response = await fetch('/api/conversations');
+        const conversations = await response.json();
+        
+        if (conversations.length === 0) {
+            addMessage('bot', '👋 欢迎使用智能知识库问答系统！上传文档后，您可以向我提问任何与文档相关的问题。');
+            return;
+        }
+        
+        conversations.forEach(conv => {
+            addMessage('user', conv.question);
+            
+            let answerHtml = `<p>${conv.answer}</p>`;
+            
+            if (conv.sources && conv.sources.length > 0) {
+                answerHtml += `
+                    <div class="sources">
+                        <div class="sources-title">📚 参考来源：</div>
+                        ${conv.sources.map(source => `
+                            <div class="source-item">📄 ${source.name} (第${source.page}页)</div>
+                        `).join('')}
+                    </div>
+                `;
+            }
+            
+            addMessage('bot', answerHtml);
+        });
+        
+    } catch (error) {
+        console.error(error);
+        addMessage('bot', '👋 欢迎使用智能知识库问答系统！上传文档后，您可以向我提问任何与文档相关的问题。');
+    }
+}
+
+questionInput.addEventListener('input', updateCharCount);
+
+questionInput.addEventListener('keydown', (e) => {
+    if (e.key === 'Enter' && !e.shiftKey) {
+        e.preventDefault();
+        askQuestion();
+    }
+});
+
+loadDocuments();
+loadConversationHistory();

static/style.css

@@ -0,0 +1,490 @@
+* {
+    margin: 0;
+    padding: 0;
+    box-sizing: border-box;
+}
+
+body {
+    font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;
+    background: linear-gradient(135deg, #1e3c72 0%, #2a5298 100%);
+    min-height: 100vh;
+    padding: 20px;
+}
+
+.container {
+    max-width: 1400px;
+    margin: 0 auto;
+    background: white;
+    border-radius: 20px;
+    padding: 30px;
+    box-shadow: 0 20px 60px rgba(0, 0, 0, 0.3);
+}
+
+.header {
+    text-align: center;
+    margin-bottom: 30px;
+}
+
+h1 {
+    color: #1e3c72;
+    margin-bottom: 10px;
+    font-size: 32px;
+}
+
+.subtitle {
+    color: #666;
+    font-size: 15px;
+}
+
+.main-content {
+    display: grid;
+    grid-template-columns: 380px 1fr;
+    gap: 25px;
+}
+
+.left-panel,
+.right-panel {
+    display: flex;
+    flex-direction: column;
+    gap: 20px;
+}
+
+.panel-section {
+    background: #f8f9fa;
+    border-radius: 15px;
+    padding: 25px;
+    box-shadow: 0 2px 8px rgba(0, 0, 0, 0.1);
+}
+
+.panel-header {
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+    margin-bottom: 20px;
+}
+
+.panel-header h2 {
+    font-size: 20px;
+    color: #1e3c72;
+    margin: 0;
+}
+
+.doc-count {
+    background: #1e3c72;
+    color: white;
+    padding: 5px 12px;
+    border-radius: 20px;
+    font-size: 13px;
+    font-weight: 600;
+}
+
+.upload-area {
+    border: 3px dashed #cbd5e0;
+    border-radius: 15px;
+    padding: 50px 30px;
+    text-align: center;
+    cursor: pointer;
+    transition: all 0.3s;
+    background: white;
+}
+
+.upload-area:hover {
+    border-color: #1e3c72;
+    background: #e8f0fe;
+    transform: translateY(-2px);
+    box-shadow: 0 4px 12px rgba(30, 60, 114, 0.15);
+}
+
+.upload-icon {
+    font-size: 56px;
+    margin-bottom: 15px;
+}
+
+.upload-text {
+    color: #333;
+    font-size: 16px;
+    font-weight: 600;
+    margin-bottom: 8px;
+}
+
+.upload-hint {
+    font-size: 13px;
+    color: #666;
+}
+
+.document-list {
+    max-height: 450px;
+    overflow-y: auto;
+}
+
+.document-item {
+    background: white;
+    border-radius: 12px;
+    padding: 18px;
+    margin-bottom: 12px;
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+    box-shadow: 0 2px 6px rgba(0, 0, 0, 0.1);
+    transition: transform 0.2s, box-shadow 0.2s;
+}
+
+.document-item:hover {
+    transform: translateY(-2px);
+    box-shadow: 0 4px 12px rgba(0, 0, 0, 0.15);
+}
+
+.document-info {
+    flex: 1;
+}
+
+.document-name {
+    font-weight: 600;
+    color: #333;
+    margin-bottom: 8px;
+    font-size: 15px;
+}
+
+.document-status {
+    font-size: 13px;
+    color: #666;
+    display: flex;
+    align-items: center;
+    gap: 5px;
+}
+
+.document-status.processing {
+    color: #f59e0b;
+}
+
+.document-status.completed {
+    color: #10b981;
+}
+
+.delete-btn {
+    background: #ef4444;
+    color: white;
+    border: none;
+    border-radius: 8px;
+    padding: 8px 16px;
+    cursor: pointer;
+    font-size: 13px;
+    font-weight: 600;
+    transition: all 0.3s;
+}
+
+.delete-btn:hover {
+    background: #dc2626;
+    transform: scale(1.05);
+}
+
+.empty-state {
+    text-align: center;
+    color: #999;
+    padding: 60px 30px;
+}
+
+.empty-icon {
+    font-size: 64px;
+    margin-bottom: 15px;
+}
+
+.empty-state p {
+    margin-bottom: 5px;
+}
+
+.empty-hint {
+    font-size: 13px;
+    color: #bbb;
+}
+
+.chat-container {
+    display: flex;
+    flex-direction: column;
+    height: 650px;
+}
+
+.chat-messages {
+    flex: 1;
+    overflow-y: auto;
+    padding: 25px;
+    background: white;
+    border-radius: 15px;
+    margin-bottom: 20px;
+    box-shadow: inset 0 2px 4px rgba(0, 0, 0, 0.05);
+}
+
+.message {
+    margin-bottom: 25px;
+    animation: fadeIn 0.3s ease-in;
+}
+
+@keyframes fadeIn {
+    from {
+        opacity: 0;
+        transform: translateY(10px);
+    }
+    to {
+        opacity: 1;
+        transform: translateY(0);
+    }
+}
+
+.message.user {
+    display: flex;
+    justify-content: flex-end;
+}
+
+.message.bot {
+    display: flex;
+    justify-content: flex-start;
+}
+
+.message-content {
+    max-width: 80%;
+    padding: 18px;
+    border-radius: 15px;
+    line-height: 1.7;
+    font-size: 15px;
+}
+
+.message.user .message-content {
+    background: linear-gradient(135deg, #1e3c72 0%, #2a5298 100%);
+    color: white;
+    box-shadow: 0 4px 12px rgba(30, 60, 114, 0.3);
+}
+
+.message.bot .message-content {
+    background: #f0f0f0;
+    color: #333;
+    box-shadow: 0 2px 8px rgba(0, 0, 0, 0.1);
+}
+
+.sources {
+    margin-top: 15px;
+    padding-top: 15px;
+    border-top: 2px solid #e0e0e0;
+}
+
+.sources-title {
+    font-size: 13px;
+    color: #666;
+    margin-bottom: 8px;
+    font-weight: 600;
+}
+
+.source-item {
+    font-size: 13px;
+    color: #1e3c72;
+    margin-bottom: 5px;
+    padding: 5px 10px;
+    background: #e8f0fe;
+    border-radius: 6px;
+    display: inline-block;
+}
+
+.chat-input {
+    display: flex;
+    gap: 15px;
+}
+
+.input-wrapper {
+    flex: 1;
+    position: relative;
+}
+
+.chat-input textarea {
+    width: 100%;
+    padding: 18px;
+    padding-right: 100px;
+    border: 2px solid #e0e0e0;
+    border-radius: 15px;
+    resize: none;
+    font-size: 15px;
+    font-family: inherit;
+    min-height: 80px;
+    transition: all 0.3s;
+}
+
+.chat-input textarea:focus {
+    outline: none;
+    border-color: #1e3c72;
+    box-shadow: 0 0 0 3px rgba(30, 60, 114, 0.1);
+}
+
+.char-count {
+    position: absolute;
+    bottom: 10px;
+    right: 15px;
+    font-size: 12px;
+    color: #999;
+    background: white;
+    padding: 3px 8px;
+    border-radius: 10px;
+}
+
+.send-btn {
+    padding: 18px 35px;
+    background: linear-gradient(135deg, #1e3c72 0%, #2a5298 100%);
+    color: white;
+    border: none;
+    border-radius: 15px;
+    cursor: pointer;
+    font-weight: 600;
+    font-size: 16px;
+    transition: all 0.3s;
+    display: flex;
+    align-items: center;
+    gap: 8px;
+    box-shadow: 0 4px 12px rgba(30, 60, 114, 0.3);
+}
+
+.send-btn:hover {
+    transform: translateY(-2px);
+    box-shadow: 0 6px 16px rgba(30, 60, 114, 0.4);
+}
+
+.send-btn:active {
+    transform: translateY(0);
+}
+
+.send-btn:disabled {
+    background: #ccc;
+    cursor: not-allowed;
+    transform: none;
+    box-shadow: none;
+}
+
+.btn-icon {
+    font-size: 18px;
+}
+
+.clear-btn {
+    background: #f59e0b;
+    color: white;
+    border: none;
+    border-radius: 8px;
+    padding: 8px 16px;
+    cursor: pointer;
+    font-size: 13px;
+    font-weight: 600;
+    transition: all 0.3s;
+}
+
+.clear-btn:hover {
+    background: #d97706;
+    transform: scale(1.05);
+}
+
+.toast {
+    position: fixed;
+    top: 20px;
+    right: 20px;
+    padding: 15px 25px;
+    background: #333;
+    color: white;
+    border-radius: 10px;
+    box-shadow: 0 4px 12px rgba(0, 0, 0, 0.3);
+    transform: translateX(400px);
+    transition: transform 0.3s ease-out;
+    z-index: 1000;
+    font-weight: 600;
+}
+
+.toast.show {
+    transform: translateX(0);
+}
+
+.toast.success {
+    background: #10b981;
+}
+
+.toast.error {
+    background: #ef4444;
+}
+
+.toast.info {
+    background: #3b82f6;
+}
+
+@media (max-width: 1024px) {
+    .main-content {
+        grid-template-columns: 1fr;
+    }
+    
+    .chat-container {
+        height: 550px;
+    }
+    
+    h1 {
+        font-size: 28px;
+    }
+}
+
+@media (max-width: 768px) {
+    body {
+        padding: 10px;
+    }
+    
+    .container {
+        padding: 20px;
+        border-radius: 15px;
+    }
+    
+    h1 {
+        font-size: 24px;
+    }
+    
+    .subtitle {
+        font-size: 13px;
+    }
+    
+    .panel-section {
+        padding: 20px;
+    }
+    
+    .chat-container {
+        height: 500px;
+    }
+    
+    .chat-input {
+        flex-direction: column;
+    }
+    
+    .send-btn {
+        width: 100%;
+        justify-content: center;
+    }
+    
+    .upload-area {
+        padding: 40px 20px;
+    }
+    
+    .upload-icon {
+        font-size: 48px;
+    }
+}
+
+@media (max-width: 480px) {
+    .container {
+        padding: 15px;
+    }
+    
+    h1 {
+        font-size: 20px;
+    }
+    
+    .panel-section {
+        padding: 15px;
+    }
+    
+    .message-content {
+        max-width: 90%;
+        font-size: 14px;
+        padding: 15px;
+    }
+    
+    .chat-messages {
+        padding: 15px;
+    }
+}

templates/index.html

@@ -0,0 +1,80 @@
+<!DOCTYPE html>
+<html lang="zh-CN">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>智能知识库问答</title>
+    <link rel="stylesheet" href="/static/style.css">
+</head>
+<body>
+    <div class="container">
+        <div class="header">
+            <h1>🧠 智能知识库问答</h1>
+            <p class="subtitle">✨ 企业/课程 · 自有文档精准问答，减少人工答疑</p>
+        </div>
+        
+        <div class="main-content">
+            <div class="left-panel">
+                <div class="panel-section">
+                    <h2>📁 文档上传</h2>
+                    <div class="upload-area" id="upload-area">
+                        <input type="file" id="file-input" accept=".txt,.pdf,.docx" hidden>
+                        <div class="upload-icon">📤</div>
+                        <p class="upload-text">点击或拖拽文件到此处</p>
+                        <p class="upload-hint">💡 支持 PDF、Word、TXT 格式（最大 16MB）</p>
+                    </div>
+                </div>
+                
+                <div class="panel-section">
+                    <div class="panel-header">
+                        <h2>📚 知识库</h2>
+                        <span class="doc-count" id="doc-count">0 个文档</span>
+                    </div>
+                    <div class="document-list" id="document-list">
+                        <div class="empty-state">
+                            <div class="empty-icon">📭</div>
+                            <p>暂无文档</p>
+                            <p class="empty-hint">上传文档后即可开始问答</p>
+                        </div>
+                    </div>
+                </div>
+            </div>
+            
+            <div class="right-panel">
+                <div class="panel-section">
+                    <div class="panel-header">
+                        <h2>💬 智能问答</h2>
+                        <button class="clear-btn" onclick="clearHistory()" title="清除对话历史">🗑️ 清空</button>
+                    </div>
+                    <div class="chat-container">
+                        <div class="chat-messages" id="chat-messages">
+                            <div class="message bot">
+                                <div class="message-content">
+                                    <p>👋 您好！我是您的智能知识库助手。</p>
+                                    <p>📋 请先上传文档，然后我可以基于文档内容回答您的问题。</p>
+                                    <p>🎯 支持精准检索，减少人工答疑时间！</p>
+                                </div>
+                            </div>
+                        </div>
+                        
+                        <div class="chat-input">
+                            <div class="input-wrapper">
+                                <textarea id="question-input" placeholder="💭 请输入您的问题...（按 Enter 发送，Shift+Enter 换行）" maxlength="1000"></textarea>
+                                <div class="char-count" id="char-count">0/1000</div>
+                            </div>
+                            <button class="send-btn" onclick="askQuestion()" id="send-btn">
+                                <span class="btn-text">发送</span>
+                                <span class="btn-icon">🚀</span>
+                            </button>
+                        </div>
+                    </div>
+                </div>
+            </div>
+        </div>
+    </div>
+    
+    <div class="toast" id="toast"></div>
+    
+    <script src="/static/script.js"></script>
+</body>
+</html>

test_document_read.py

@@ -0,0 +1,23 @@
+import sys
+import os
+
+sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
+
+from app import read_document_content
+
+doc_id = '3cac70d6-cd02-493e-a08a-c7794927e7b4'
+
+print(f"=== 测试文档读取功能 ===\n")
+print(f"文档ID: {doc_id}\n")
+
+content = read_document_content(doc_id)
+
+if content:
+    print(f"✓ 成功读取文档内容")
+    print(f"内容长度: {len(content)} 字符")
+    print(f"\n前200字符:")
+    print(content[:200])
+    print("\n✓ 文档读取功能正常！")
+else:
+    print("✗ 未能读取文档内容")
+    print("请检查文件是否存在或格式是否正确")

test_output.txt

@@ -0,0 +1,17 @@
+=== 测试文档读取功能 ===
+
+文件: 3cac70d6-cd02-493e-a08a-c7794927e7b4_docx
+文件: 77320887-f79f-48a0-aa20-bea2d9c1f5af_SIT.docx
+类型: DOCX
+段落数: 30
+内容长度: 336 字符
+前100字符: 《长河入海时——致SIT七十一周年》
+
+【第一篇章：长河溯源】
+你从1956年的晨光中启航，
+一捧夯土，铸成应用之学的堤岸。
+工程卷轴在黄浦江畔舒展，
+墨迹里游动着钢铁与代码的基因链。
+
+【第二篇章：...
+

test_read.py

@@ -0,0 +1,39 @@
+import os
+from docx import Document
+
+uploads_folder = 'uploads'
+
+print("=== 测试文档读取功能 ===\n")
+
+for file in os.listdir(uploads_folder):
+    filepath = os.path.join(uploads_folder, file)
+    print(f"文件: {file}")
+    
+    if file.endswith('.txt'):
+        with open(filepath, 'r', encoding='utf-8') as f:
+            content = f.read()
+            print(f"类型: TXT")
+            print(f"内容长度: {len(content)} 字符")
+            print(f"前100字符: {content[:100]}...\n")
+    
+    elif file.endswith('.pdf'):
+        import pypdf
+        with open(filepath, 'rb') as f:
+            reader = pypdf.PdfReader(f)
+            text = ''
+            for page in reader.pages:
+                text += page.extract_text() + '\n'
+            print(f"类型: PDF")
+            print(f"页数: {len(reader.pages)}")
+            print(f"内容长度: {len(text)} 字符")
+            print(f"前100字符: {text[:100]}...\n")
+    
+    elif file.endswith('.docx'):
+        doc = Document(filepath)
+        text = ''
+        for paragraph in doc.paragraphs:
+            text += paragraph.text + '\n'
+        print(f"类型: DOCX")
+        print(f"段落数: {len(doc.paragraphs)}")
+        print(f"内容长度: {len(text)} 字符")
+        print(f"前100字符: {text[:100]}...\n")