Flowise: 52K+ Stars 可视化拖拽构建 AI Agent — 2026 5分钟快速上手指南

# 全局安装 Flowise
npm install -g flowise

# 或安装指定版本
npm install -g flowise@3.1.2

# 启动 Flowise
npx flowise start

# 拉取并运行官方镜像
docker run -d -p 3000:3000 \
  --name flowise \
  -e FLOWISE_USERNAME=admin \
  -e FLOWISE_PASSWORD=secure-password \
  flowiseai/flowise:latest

# docker-compose.yml
version: '3.8'
services:
  flowise:
    image: flowiseai/flowise:latest
    ports:
      - "3000:3000"
    environment:
      - PORT=3000
      - DATABASE_TYPE=postgres
      - DATABASE_HOST=postgres
      - DATABASE_PORT=5432
      - DATABASE_NAME=flowise
      - DATABASE_USER=flowise
      - DATABASE_PASSWORD=${DB_PASSWORD:-changeme}
      - FLOWISE_USERNAME=${FLOWISE_USER:-admin}
      - FLOWISE_PASSWORD=${FLOWISE_PASS:-changeme}
      - SECRETKEY_PATH=/root/.flowise
      - JWT_AUTH_TOKEN_SECRET=${JWT_SECRET:-random-secret-change-in-prod}
      - JWT_REFRESH_TOKEN_SECRET=${JWT_REFRESH:-another-random-secret}
    volumes:
      - flowise_data:/root/.flowise
    depends_on:
      - postgres
    restart: unless-stopped

  postgres:
    image: postgres:16-alpine
    environment:
      - POSTGRES_USER=flowise
      - POSTGRES_PASSWORD=${DB_PASSWORD:-changeme}
      - POSTGRES_DB=flowise
    volumes:
      - postgres_data:/var/lib/postgresql/data
    restart: unless-stopped

volumes:
  flowise_data:
  postgres_data:

docker compose up -d

# 在全新的 Ubuntu 24.04 服务器上（2 vCPU / 2GB RAM / $12/月）
apt update && apt install -y docker.io docker-compose

# 克隆 Flowise 仓库
git clone https://github.com/FlowiseAI/Flowise.git
cd Flowise/docker

# 复制环境变量模板
cp .env.example .env

# 编辑配置文件
nano .env

PORT=3000
DATABASE_TYPE=sqlite
DATABASE_PATH=/root/.flowise
SECRETKEY_PATH=/root/.flowise
LOG_PATH=/root/.flowise/logs
BLOB_STORAGE_PATH=/root/.flowise/storage
FLOWISE_USERNAME=admin
FLOWISE_PASSWORD=your-secure-password-here
JWT_AUTH_TOKEN_SECRET=$(openssl rand -hex 32)
JWT_REFRESH_TOKEN_SECRET=$(openssl rand -hex 32)

docker compose up -d

# 可选：将 OpenAI API Key 设置为环境变量
export OPENAI_API_KEY=sk-your-key-here

# docker-compose-ollama.yml
version: '3.8'
services:
  ollama:
    image: ollama/ollama:latest
    ports:
      - "11434:11434"
    volumes:
      - ollama_data:/root/.ollama
    restart: unless-stopped

  flowise:
    image: flowiseai/flowise:latest
    ports:
      - "3000:3000"
    environment:
      - PORT=3000
      - OLLAMA_BASE_URL=http://ollama:11434
    depends_on:
      - ollama
    restart: unless-stopped

volumes:
  ollama_data:

# 拉取轻量级测试模型
docker exec -it ollama ollama pull qwen2:7b

# 或拉取 Llama 3
docker exec -it ollama ollama pull llama3.1:8b

# 添加到 docker-compose.yml
  chroma:
    image: chromadb/chroma:latest
    ports:
      - "8000:8000"
    volumes:
      - chroma_data:/chroma/chroma
    restart: unless-stopped

# 在 compose 文件中添加 Qdrant
  qdrant:
    image: qdrant/qdrant:latest
    ports:
      - "6333:6333"
      - "6334:6334"
    volumes:
      - qdrant_data:/qdrant/storage
    restart: unless-stopped

  weaviate:
    image: semitechnologies/weaviate:latest
    ports:
      - "8080:8080"
    environment:
      QUERY_DEFAULTS_LIMIT: 25
      AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED: 'true'
      PERSISTENCE_DATA_PATH: '/var/lib/weaviate'
    volumes:
      - weaviate_data:/var/lib/weaviate
    restart: unless-stopped

# 使用 curl 测试已部署的 Flow
curl -X POST "http://localhost:3000/api/v1/prediction/your-chatflow-id" \
  -H "Content-Type: application/json" \
  -d '{
    "question": "退货政策是什么？",
    "overrideConfig": {
      "sessionId": "user_001"
    }
  }'

{
  "text": "根据我们的文档，退货政策允许在购买后 30 天内凭原始收据退货。",
  "sourceDocuments": [
    {
      "pageContent": "购买后 30 天内接受退货...",
      "metadata": { "source": "return-policy.pdf", "page": 3 }
    }
  ]
}

import requests

FLOWISE_API = "http://localhost:3000/api/v1/prediction/your-chatflow-id"

def ask(question, session_id="user_001"):
    resp = requests.post(FLOWISE_API, json={
        "question": question,
        "overrideConfig": {"sessionId": session_id}
    })
    return resp.json()["text"]

answer = ask("你们有哪些配送方式？")
print(answer)

<script type="module">
  import Chatbot from 'https://cdn.jsdelivr.net/npm/flowise-embed/dist/web.js';
  Chatbot.init({
    chatflowid: 'your-chatflow-id',
    apiHost: 'https://your-flowise-server.com',
    theme: {
      button: {
        backgroundColor: '#3B81F6',
        right: 20,
        bottom: 20,
        size: 'medium'
      },
      chatWindow: {
        title: '客服助手',
        welcomeMessage: '你好！有什么可以帮您的？',
        backgroundColor: '#ffffff',
        height: 700,
        width: 400
      }
    }
  });
</script>

# 1. 启用身份验证（必须）
FLOWISE_USERNAME=admin
FLOWISE_PASSWORD=$(openssl rand -base64 24)

# 2. 设置强 JWT 密钥
JWT_AUTH_TOKEN_SECRET=$(openssl rand -hex 64)
JWT_REFRESH_TOKEN_SECRET=$(openssl rand -hex 64)

# 3. 使用反向代理启用 HTTPS
# Nginx 配置片段：
server {
    listen 443 ssl http2;
    server_name flowise.yourdomain.com;

    ssl_certificate /path/to/cert.pem;
    ssl_certificate_key /path/to/key.pem;

    location / {
        proxy_pass http://localhost:3000;
        proxy_http_version 1.1;
        proxy_set_header Upgrade $http_upgrade;
        proxy_set_header Connection "upgrade";
        proxy_set_header Host $host;
        proxy_set_header X-Real-IP $remote_addr;
    }
}

# 4. 如需要可关闭遥测
DISABLE_FLOWISE_TELEMETRY=true

# 5. 为嵌入组件设置 CORS
CORS_ORIGINS=https://yourdomain.com,https://app.yourdomain.com

# docker-compose-queue.yml
version: '3.8'
services:
  redis:
    image: redis:alpine
    restart: unless-stopped

  flowise:
    image: flowiseai/flowise:latest
    ports:
      - "3000:3000"
    environment:
      - PORT=3000
      - QUEUE_NAME=flowise-queue
      - QUEUE_REDIS_URL=redis://redis:6379
    restart: unless-stopped

  flowise-worker:
    image: flowiseai/flowise-worker:latest
    environment:
      - QUEUE_NAME=flowise-queue
      - QUEUE_REDIS_URL=redis://redis:6379
    restart: unless-stopped

docker compose -f docker-compose-queue.yml up -d --scale flowise-worker=3

# 备份 SQLite 数据库
docker exec flowise tar czf /tmp/backup.tar.gz /root/.flowise
docker cp flowise:/tmp/backup.tar.gz ./flowise-backup-$(date +%Y%m%d).tar.gz

# 备份 PostgreSQL
docker exec flowise-postgres pg_dump -U flowise flowise > flowise-db-$(date +%Y%m%d).sql

# 通过 cron 实现每日自动备份（添加到 crontab）
0 2 * * * /usr/local/bin/backup-flowise.sh >> /var/log/flowise-backup.log 2>&1

# 查看实时日志
docker compose logs -f flowise

# 检查资源使用
docker stats flowise

# 健康检查端点
curl http://localhost:3000/api/v1/ping

docker pull flowiseai/flowise:latest
docker compose up -d