Ubuntu系统安装部署Pandawiki智能知识库

一、系统环境准备
bash
# 更新系统
sudo apt update && sudo apt upgrade -y
sudo apt install -y git python3-pip python3-venv nginx ufw certbot
 
# 安装PostgreSQL数据库
sudo apt install -y postgresql postgresql-contrib
sudo -u postgres psql -c "CREATE DATABASE pandawiki;"
sudo -u postgres psql -c "CREATE USER wikiadmin WITH PASSWORD 'YourStrongPassword!';"
sudo -u postgres psql -c "GRANT ALL PRIVILEGES ON DATABASE pandawiki TO wikiadmin;"
 
# 创建应用目录
mkdir -p /opt/pandawiki && cd /opt/pandawiki

---

二、Pandawiki部署流程
1. 获取源代码
bash
git clone https://github.com/pandawiki/pandawiki.git
cd pandawiki
 
# 创建虚拟环境
python3 -m venv venv
source venv/bin/activate
2. 安装依赖
bash
pip install --upgrade pip
pip install -r requirements.txt
pip install gunicorn gevent psycopg2-binary
3. 配置应用
bash
# 创建配置文件
cp config.example.py config.py
nano config.py
python
# 关键配置修改
SQLALCHEMY_DATABASE_URI = 'postgresql+psycopg2://wikiadmin:YourStrongPassword!@localhost/pandawiki'
SECRET_KEY = '生成32位密钥(openssl rand -hex 32)'
ALLOW_REGISTRATION = False  # 生产环境禁用开放注册
UPLOAD_FOLDER = '/opt/pandawiki/uploads'  # 上传目录
4. 初始化数据库
bash
flask db upgrade
flask init-data
 
# 创建上传目录
sudo mkdir -p /opt/pandawiki/uploads
sudo chown -R $USERUSER /opt/pandawiki
5. 测试运行
bash
gunicorn --bind 0.0.0.0:8000 app:app
# 访问 http://:8000 验证

---

三、生产环境部署
1. 创建系统服务
bash
sudo nano /etc/systemd/system/pandawiki.service
ini
[Unit]
Description=Pandawiki Gunicorn Service
After=network.target postgresql.service
 
[Service]
User=ubuntu
Group=www-data
WorkingDirectory=/opt/pandawiki/pandawiki
Environment="ATH=/opt/pandawiki/pandawiki/venv/bin"
ExecStart=/opt/pandawiki/pandawiki/venv/bin/gunicorn \
  --worker-class gevent \
  --workers 5 \
  --bind unix:/run/pandawiki.sock \
  --timeout 300 \
  --log-level warning \
  app:app
 
Restart=always
RestartSec=3
 
[Install]
WantedBy=multi-user.target
bash
sudo systemctl daemon-reload
sudo systemctl start pandawiki
sudo systemctl enable pandawiki
2. Nginx配置
bash
sudo nano /etc/nginx/sites-available/pandawiki
nginx
server {
    listen 80;
    server_name wiki.yourdomain.com;
    client_max_body_size 100M;  # 允许大文件上传
 
    location / {
        include proxy_params;
        proxy_pass http://unix:/run/pandawiki.sock;
        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
        proxy_set_header Host $host;
        proxy_connect_timeout 300s;
        proxy_read_timeout 300s;
    }
 
    location /static {
        alias /opt/pandawiki/pandawiki/static;
        expires 30d;
    }
 
    location /uploads {
        alias /opt/pandawiki/uploads;
        expires 30d;
        add_header Cache-Control "public";
    }
}
bash
sudo ln -s /etc/nginx/sites-available/pandawiki /etc/nginx/sites-enabled/
sudo nginx -t && sudo systemctl reload nginx
3. 启用HTTPS
bash
sudo ufw allow 'Nginx Full'
sudo certbot --nginx -d wiki.yourdomain.com

---

四、监控平台集成
1. 安装Prometheus+Grafana
bash
# 添加仓库
sudo apt-get install -y apt-transport-https software-properties-common wget
wget -q -O - https://packages.grafana.com/gpg.key | sudo apt-key add -
echo "deb https://packages.grafana.com/oss/deb stable main" | sudo tee /etc/apt/sources.list.d/grafana.list
sudo apt update
 
# 安装组件
sudo apt install -y prometheus prometheus-node-exporter grafana
2. 配置Prometheus监控Pandawiki
bash
sudo nano /etc/prometheus/prometheus.yml
yaml
scrape_configs:
  # 添加Pandawiki监控
  - job_name: 'pandawiki'
    metrics_path: '/metrics'
    static_configs:
      - targets: ['localhost:8000']  # Gunicorn暴露的指标端口
    relabel_configs:
      - source_labels: [__address__]
        target_label: instance
        replacement: 'pandawiki-primary'
3. 添加Pandawiki专属仪表板

• 访问Grafana：http://:3000 (admin/admin)
  
• 添加Prometheus数据源：http://localhost:9090
  
• 导入仪表板：
  
  
  
  • 使用JSON文件：pandawiki-grafana-dashboard.json
    
  • 或创建自定义仪表板监控：
    
    
    
    • 请求速率
      
    • 错误率(4xx/5xx)
      
    • 响应延迟(P95)
      
    • 数据库查询性能
      
    • 内存/CPU使用率
      
    
    
  
  

4. 关键监控指标配置
bash
sudo nano /etc/prometheus/alert_rules.yml
yaml
groups:
- name: pandawiki
  rules:
  - alert: HighErrorRate
    expr: sum(rate(http_requests_total{status=~"5.."}[5m]) / sum(rate(http_requests_total[5m])) * 100 > 5
    for: 10m
    labels:
      severity: critical
    annotations:
      summary: "高错误率 {{ $labels.instance }}"
      description: "5xx错误率超过5% (当前值: {{ $value }}%)"
     
  - alert: SlowResponse
    expr: histogram_quantile(0.95, sum(rate(http_request_duration_seconds_bucket[5m])) > 3
    for: 15m
    labels:
      severity: warning
    annotations:
      summary: "响应延迟过高 {{ $labels.instance }}"
      description: "95响应延迟超过3秒 (当前值: {{ $value }}s)"

---

五、数据备份与恢复
1. 自动化备份脚本
bash
sudo nano /usr/local/bin/pandawiki-backup
bash
#!/bin/bash
# 备份数据库、上传文件和配置
BACKUP_DIR="/backup/pandawiki/$(date +%Y%m%d)"
mkdir -p $BACKUP_DIR
 
# 数据库备份
sudo -u postgres pg_dump pandawiki > $BACKUP_DIR/pandawiki.sql
gzip $BACKUP_DIR/pandawiki.sql
 
# 文件备份
tar -czf $BACKUP_DIR/uploads.tar.gz /opt/pandawiki/uploads
tar -czf $BACKUP_DIR/config.tar.gz /opt/pandawiki/pandawiki/config.py
 
# 备份监控数据
tar -czf $BACKUP_DIR/prometheus.tar.gz /var/lib/prometheus
 
# 加密备份
gpg --batch --passphrase "YourEncryptionKey" --symmetric $BACKUP_DIR/*.gz
 
# 保留最近30天备份
find /backup/pandawiki -type d -mtime +30 -exec rm -rf {} \;
bash
sudo chmod +x /usr/local/bin/pandawiki-backup
sudo crontab -e
cron
# 每天凌晨2点备份
0 2 * * * /usr/local/bin/pandawiki-backup
2. 云存储备份（AWS S3示例）
bash
# 安装AWS CLI
sudo apt install awscli -y
aws configure
 
# 添加备份脚本末尾
aws s3 sync --delete /backup/pandawiki s3://your-bucket/pandawiki-backups
3. 灾难恢复流程
bash
# 1. 恢复数据库
gunzip -c pandawiki.sql.gz | sudo -u postgres psql pandawiki
 
# 2. 恢复文件
sudo tar -xzf uploads.tar.gz -C /
sudo tar -xzf config.tar.gz -C /
 
# 3. 重启服务
sudo systemctl restart pandawiki postgresql nginx

---

六、日常运维管理
1. 每日检查清单
bash
# 服务状态检查
sudo systemctl status pandawiki nginx postgresql prometheus
 
# 日志检查
journalctl -u pandawiki --since "today" | grep -E 'ERROR|CRITICAL'
tail -100 /var/log/nginx/error.log
 
# 存储检查
df -h / /opt /backup
du -sh /opt/pandawiki/uploads
 
# 性能检查
pg_top -d pandawiki  # 数据库性能
htop  # 系统资源
2. 自动化维护脚本
bash
sudo nano /usr/local/bin/pandawiki-maintenance
bash
#!/bin/bash
# 每周维护任务
source /opt/pandawiki/pandawiki/venv/bin/activate
cd /opt/pandawiki/pandawiki
 
# 1. 更新代码
git fetch origin
git checkout main
git reset --hard origin/main
 
# 2. 更新依赖
pip install -r requirements.txt --upgrade
 
# 3. 数据库迁移
flask db upgrade
 
# 4. 清理缓存
find /tmp -name "pandawiki_cache_*" -mtime +7 -delete
 
# 5. 重启服务
sudo systemctl restart pandawiki
3. 智能问答增强
bash
# 安装AI插件
pip install openai faiss-cpu
 
# 配置智能问答
nano config.py
python
# 添加AI配置
AI_ENABLED = True
OPENAI_API_KEY = 'sk-xxx'
AI_INDEX_PATH = '/opt/pandawiki/faiss_index'
bash
# 创建知识索引
flask ai build-index

---

七、安全加固措施
1. 网络安全
bash
# 防火墙配置
sudo ufw default deny incoming
sudo ufw allow ssh
sudo ufw allow https
sudo ufw enable
 
# 安装Fail2Ban
sudo apt install fail2ban
sudo cp /etc/fail2ban/jail.conf /etc/fail2ban/jail.local
sudo nano /etc/fail2ban/jail.local
ini
[pandawiki]
enabled = true
port = http,https
filter = pandawiki
logpath = /var/log/nginx/access.log
maxretry = 5
findtime = 600
bantime = 86400
2. 文件安全
bash
# 设置目录权限
sudo chown -R ubuntu:www-data /opt/pandawiki
sudo find /opt/pandawiki/uploads -type f -exec chmod 640 {} \;
sudo find /opt/pandawiki/pandawiki -type d -exec chmod 750 {} \;
 
# 配置文件完整性监控
sudo apt install aide
sudo aideinit
sudo cp /var/lib/aide/aide.db.new /var/lib/aide/aide.db
sudo crontab -e
cron
# 每天检查文件完整性
0 3 * * * /usr/bin/aide --check
3. 数据库安全
sql
-- 限制连接数
ALTER SYSTEM SET max_connections = 100;
-- 禁用远程访问
sudo nano /etc/postgresql/14/main/pg_hba.conf
# 修改为：
host    all             all             127.0.0.1/32            md5

---

八、注意事项
1. 升级策略

• 测试环境先行：先在测试环境验证升级
  
• 备份优先：升级前执行完整备份
  
• 分阶段升级：
  

bash
# 1. 停用负载
sudo systemctl stop pandawiki
 
# 2. 更新代码
git pull origin main
 
# 3. 数据库迁移
flask db upgrade
 
# 4. 重启服务
sudo systemctl start pandawiki
2. 性能优化
python
# config.py 性能优化配置
CACHE_TYPE = "RedisCache"
CACHE_REDIS_URL = "redis://localhost:6379/0"
SQLALCHEMY_ENGINE_OPTIONS = {
    "pool_pre_ping": True,
    "pool_recycle": 300,
    "pool_size": 20,
    "max_overflow": 10
}
3. 灾备恢复计划

故障类型	恢复时间目标(RTO)	恢复点目标(RPO)	恢复方案
应用故障	15分钟	5分钟	从备份恢复服务配置
数据库损坏	1小时	1小时	从SQL备份恢复
服务器宕机	2小时	24小时	云镜像恢复 + 最新数据备份
数据中心故障	4小时	24小时	跨区域备份恢复

4. 智能知识库优化

• 知识图谱集成：
  

bash
pip install py2neo
flask knowledge-graph build

• 问答质量监控：
  
  
  
  • 记录用户问答满意度
    
  • 定期优化AI模型
    
  • 设置未知问题报警
    
  
  

5. 合规性要求

• GDPR合规：
  
  
  
  • 用户数据加密存储
    
  • 提供数据导出接口
    
  • 自动删除90天未活跃用户
    
  
  
• 操作审计：
  

sql
CREATE TABLE audit_log (
  id SERIAL PRIMARY KEY,
  user_id INT,
  action VARCHAR(50),
  target VARCHAR(100),
  timestamp TIMESTAMP DEFAULT NOW()
);
通过以上完整流程，您将获得一个安全、高效、可监控的智能知识库系统。建议每月执行一次安全审计，每季度进行恢复演练，确保系统持续稳定运行。

来源：豆瓜网用户自行投稿发布，如果侵权，请联系站长删除