Skip to main content
Find answers to commonly asked questions about Flowise. If you don’t find what you’re looking for, visit our Community channels or GitHub Discussions.

General Questions

Flowise is an open-source visual tool for building AI agents and LLM (Large Language Model) applications. It provides a drag-and-drop interface to create complex AI workflows without extensive coding.Key features include:
  • Visual chatflow builder
  • Pre-built components and integrations
  • Support for multiple LLM providers
  • Agent and chain configurations
  • Self-hosting capabilities
Yes! Flowise is open-source and free to use under the Apache License Version 2.0. You can:
  • Self-host on your own infrastructure
  • Modify the source code
  • Use it for commercial purposes
We also offer Flowise Cloud for managed hosting with additional enterprise features.
Flowise (Open Source):
  • Self-hosted on your infrastructure
  • Full control over data and deployment
  • Requires setup and maintenance
  • Free and open-source
Flowise Cloud:
  • Managed hosting
  • No infrastructure setup required
  • Enterprise features and support
  • Automatic updates
  • Pay-as-you-go pricing
Flowise supports numerous LLM providers including:
  • OpenAI (GPT-3.5, GPT-4, etc.)
  • Azure OpenAI
  • Anthropic Claude
  • Google PaLM/Gemini
  • Hugging Face models
  • AWS Bedrock
  • Cohere
  • Local models via Ollama
  • And many more through the components library

Installation & Setup

Minimum Requirements:
  • Node.js >= 18.15.0 (< 19.0.0 or ^20)
  • PNPM v10.26.0 (for development)
  • 2GB RAM minimum
  • Modern web browser (Chrome, Firefox, Safari, Edge)
Recommended:
  • 4GB+ RAM for better performance
  • SSD storage
  • Stable internet connection for LLM API calls
Quick Start (NPM):
npm install -g flowise
npx flowise start
Docker:
docker run -d -p 3000:3000 flowiseai/flowise
From Source:
git clone https://github.com/FlowiseAI/Flowise.git
cd Flowise
pnpm install
pnpm build
pnpm start
See Quickstart for detailed instructions.
Flowise supports multiple databases:
  • SQLite (default) - No setup required, ideal for development
  • PostgreSQL - Recommended for production
  • MySQL - Alternative for production
Configure via the DATABASE_TYPE environment variable. See Environment Variables for details.
Yes! Flowise works well behind reverse proxies like Nginx, Apache, or Caddy. Make sure to:
  1. Configure CORS_ORIGINS environment variable
  2. Set TRUST_PROXY appropriately
  3. Forward WebSocket connections for real-time features
See Deployment guides for proxy configuration examples.

Development & Customization

Custom components are created in the packages/components directory:
  1. Create a new TypeScript file for your component
  2. Implement the component interface
  3. Define inputs, outputs, and logic
  4. Rebuild the project: pnpm build
  5. Restart Flowise to see your component
See the existing components for examples and patterns.
Yes, configure these environment variables:
  • TOOL_FUNCTION_BUILTIN_DEP - Node.js built-in modules
  • TOOL_FUNCTION_EXTERNAL_DEP - External npm packages
  • ALLOW_BUILTIN_DEP - Allow project dependencies
Example:
TOOL_FUNCTION_EXTERNAL_DEP=axios,lodash
Set the DEBUG environment variable:
DEBUG=true npx flowise start
Or in your .env file:
DEBUG=true
LOG_LEVEL=debug
This will print detailed logs from components and help troubleshoot issues.
Yes, use the DISABLED_NODES environment variable:
DISABLED_NODES=node1,node2,node3
This is useful for enterprise deployments where you want to limit available components.

Deployment & Production

Flowise can be deployed on various platforms:
  • Cloud Providers: AWS, Azure, GCP, Digital Ocean, Alibaba Cloud
  • Platform Services: Railway, Render, Northflank, HuggingFace Spaces
  • Containers: Docker, Kubernetes
  • VPS: Any Linux server with Node.js
See Deployment Guides for platform-specific instructions.
Security best practices:
  1. Use HTTPS: Deploy behind SSL/TLS
  2. Environment Variables: Store sensitive data in env vars, not code
  3. CORS Configuration: Set CORS_ORIGINS to restrict access
  4. Database Security: Use strong passwords, restrict network access
  5. Regular Updates: Keep Flowise and dependencies updated
  6. Firewall: Restrict access to necessary ports only
For security issues, see our Security Policy.
Chatflows are stored in your database. To backup:SQLite:
# Copy the database file
cp ~/.flowise/database.sqlite ~/backups/
PostgreSQL/MySQL: Use standard database backup tools (pg_dump, mysqldump)Manual Export: Export individual chatflows as JSON from the UI and store them in version control.
Scaling strategies:
  1. Database: Use PostgreSQL instead of SQLite
  2. Storage: Use S3 or GCS for file uploads (STORAGE_TYPE)
  3. Load Balancing: Deploy multiple instances behind a load balancer
  4. Caching: Implement caching for frequently accessed data
  5. Monitoring: Set up logging and monitoring (CloudWatch, Datadog, etc.)
Consider Flowise Cloud for managed scaling.

Troubleshooting

The default port (3000) is occupied. Solutions:
  1. Change the port:
PORT=3001 npx flowise start
  1. Kill the process using port 3000:
# Linux/Mac
lsof -ti:3000 | xargs kill -9

# Windows
netstat -ano | findstr :3000
taskkill /PID <PID> /F
Increase Node.js memory limit:
# macOS / Linux / Git Bash
export NODE_OPTIONS="--max-old-space-size=4096"

# Windows PowerShell
$env:NODE_OPTIONS="--max-old-space-size=4096"

# Windows CMD
set NODE_OPTIONS=--max-old-space-size=4096
Then rebuild:
pnpm build
If community nodes or custom components aren’t appearing:
  1. Enable community nodes:
SHOW_COMMUNITY_NODES=true
  1. Rebuild the project:
pnpm build
  1. Clear cache and restart:
pnpm clean
pnpm build
pnpm start
This usually indicates an issue with the encryption key:
  1. Check that SECRETKEY_PATH is writable
  2. Verify the encryption key file exists
  3. If using FLOWISE_SECRETKEY_OVERWRITE, ensure it’s consistent across restarts
  4. Check file permissions on the database

Still Need Help?

Troubleshooting Guide

Detailed solutions for common issues

Community Support

Get help from the community

GitHub Discussions

Search discussions or ask questions

Report a Bug

File an issue on GitHub

Build docs developers (and LLMs) love