Open WebUI Setup Guide on RamNode VPS | Self-Hosted AI Chat Interface

Prerequisites

Before starting, ensure you have:

Server Requirements

• RamNode VPS (2GB+ RAM recommended)
• Ubuntu 20.04/22.04 or Debian 11+
• 1+ CPU cores
• 10GB+ disk space
• SSH access to your VPS

→ View Recommended Premium VPS Plans

Knowledge Requirements

• Basic Linux command line
• Understanding of Docker
• Basic networking knowledge
• Domain name (optional)

Initial Server Setup

Connect to your RamNode VPS and prepare the environment:

Connect via SSH

ssh root@your-server-ip

Update System Packages

apt update && apt upgrade -y

Create OpenWebUI User for Security

adduser openwebui
usermod -aG sudo openwebui
su - openwebui

💡 Security Tip: Running OpenWebUI as a dedicated user improves security by limiting permissions and isolating the application.

Install Docker

OpenWebUI runs in Docker containers for easy deployment and management:

Install Docker Dependencies

sudo apt install -y apt-transport-https ca-certificates curl gnupg lsb-release

Add Docker Repository

curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo gpg --dearmor -o /usr/share/keyrings/docker-archive-keyring.gpg
echo "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/docker-archive-keyring.gpg] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable" | sudo tee /etc/apt/sources.list.d/docker.list > /dev/null

Install Docker

sudo apt update
sudo apt install -y docker-ce docker-ce-cli containerd.io docker-compose-plugin

Configure Docker for User

sudo systemctl start docker
sudo systemctl enable docker
sudo usermod -aG docker $USER

Verify Docker Installation

docker --version
docker compose version

✅ Docker is now installed and ready for OpenWebUI deployment!

Deploy OpenWebUI

Deploy OpenWebUI using Docker:

Create OpenWebUI Directory

mkdir -p ~/openwebui
cd ~/openwebui

Pull and Run OpenWebUI

docker run -d \
  --name openwebui \
  -p 3000:8080 \
  -v openwebui:/app/backend/data \
  --restart unless-stopped \
  ghcr.io/open-webui/open-webui:main

Verify OpenWebUI is Running

docker ps
docker logs openwebui

What is OpenWebUI?

OpenWebUI is a feature-rich, self-hosted web interface for large language models. It provides a ChatGPT-like experience while giving you complete control over your data, conversations, and AI models. It supports multiple models, user management, and extensive customization options.

Basic Configuration

Configure OpenWebUI settings and environment:

Stop OpenWebUI Container

docker stop openwebui

Create Environment File

nano ~/openwebui/.env

Add these environment variables:

OpenWebUI Environment Configuration

# Basic Configuration
WEBUI_SECRET_KEY=your-secret-key-here
WEBUI_NAME="Your OpenWebUI Instance"

# Security Settings
ENABLE_SIGNUP=false
DEFAULT_USER_ROLE=pending

# Model Settings
OLLAMA_BASE_URL=http://localhost:11434

# Optional: OpenAI API Integration
OPENAI_API_KEY=your-openai-key-here
OPENAI_API_BASE_URL=https://api.openai.com/v1

Restart OpenWebUI with Environment

docker run -d \
  --name openwebui \
  -p 3000:8080 \
  -v openwebui:/app/backend/data \
  --env-file ~/openwebui/.env \
  --restart unless-stopped \
  ghcr.io/open-webui/open-webui:main

🔐 Security: Replace "your-secret-key-here" with a strong, unique secret key. Keep your environment file secure!

Install Ollama (Local Models)

Install Ollama to run local AI models with OpenWebUI:

Install Ollama

curl -fsSL https://ollama.ai/install.sh | sh

Start Ollama Service

sudo systemctl start ollama
sudo systemctl enable ollama

Download Your First Model

ollama pull llama2

Test Ollama Installation

ollama list
ollama run llama2 "Hello, how are you?"

Connect OpenWebUI to Ollama

docker stop openwebui
docker rm openwebui
docker run -d \
  --name openwebui \
  --network=host \
  -v openwebui:/app/backend/data \
  --env-file ~/openwebui/.env \
  --restart unless-stopped \
  ghcr.io/open-webui/open-webui:main

🧠 Local AI: You now have local AI models running on your server! Ollama provides privacy and control over your AI interactions.

Set Up Nginx Reverse Proxy

Configure Nginx as a reverse proxy for OpenWebUI:

Install Nginx

sudo apt install nginx -y

Create Nginx Configuration

sudo nano /etc/nginx/sites-available/openwebui

Add the following Nginx configuration:

Nginx Configuration for OpenWebUI

server {
    listen 80;
    server_name your-domain.com;  # Replace with your domain

    client_max_body_size 100M;

    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;
        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
        proxy_set_header X-Forwarded-Proto $scheme;
        proxy_cache_bypass $http_upgrade;
        proxy_read_timeout 86400;
        proxy_send_timeout 86400;
    }
}

Enable the Site

sudo ln -s /etc/nginx/sites-available/openwebui /etc/nginx/sites-enabled/
sudo nginx -t
sudo systemctl restart nginx

Set Up SSL with Let's Encrypt

Secure your OpenWebUI installation with SSL certificate:

Install Certbot

sudo apt install certbot python3-certbot-nginx -y

Obtain SSL Certificate

sudo certbot --nginx -d your-domain.com

Test Auto-Renewal

sudo certbot renew --dry-run

🔒 SSL Enabled: Your OpenWebUI instance is now secured with HTTPS!

User Management

Configure user access and permissions in OpenWebUI:

First-Time Setup

Access your OpenWebUI instance:

1. Open your browser and go to https://your-domain.com
2. Create your admin account (first user is automatically admin)
3. Sign in with your new account
4. Go to Settings → Admin Settings

User Management Options

• Disable Signup: Prevent new user registrations
• User Roles: Set default roles for new users
• Model Access: Control which models users can access
• Chat History: Enable/disable conversation persistence

Configure Firewall

sudo ufw allow ssh
sudo ufw allow 80
sudo ufw allow 443
sudo ufw --force enable

Model Management

Manage AI models in your OpenWebUI installation:

Popular Ollama Models

Download Recommended Models

# Lightweight models (good for 2-4GB RAM)
ollama pull llama2:7b
ollama pull mistral:7b
ollama pull codellama:7b

# Larger models (requires 8GB+ RAM)
ollama pull llama2:13b
ollama pull vicuna:13b

# Specialized models
ollama pull deepseek-coder:6.7b  # Code generation
ollama pull dolphin-mixtral:8x7b  # Advanced reasoning

Model Management Commands

Ollama Management

# List installed models
ollama list

# Remove unused models
ollama rm model-name

# Update a model
ollama pull model-name

# Check model info
ollama show model-name

💡 Resource Tip: Start with smaller 7B models and upgrade to larger ones based on your VPS capacity and performance needs.

Performance Optimization

Optimize OpenWebUI and Ollama for your RamNode VPS:

System Optimization

Increase System Limits

echo "* soft nofile 65536" | sudo tee -a /etc/security/limits.conf
echo "* hard nofile 65536" | sudo tee -a /etc/security/limits.conf
echo "vm.max_map_count=262144" | sudo tee -a /etc/sysctl.conf
sudo sysctl -p

Docker Resource Limits

Update OpenWebUI with Resource Limits

docker stop openwebui
docker rm openwebui
docker run -d \
  --name openwebui \
  --network=host \
  -v openwebui:/app/backend/data \
  --env-file ~/openwebui/.env \
  --memory="1g" \
  --cpus="1.0" \
  --restart unless-stopped \
  ghcr.io/open-webui/open-webui:main

Ollama Configuration

Optimize Ollama Settings

# Create Ollama configuration
sudo mkdir -p /etc/systemd/system/ollama.service.d
sudo nano /etc/systemd/system/ollama.service.d/override.conf

Ollama Service Override

[Service]
Environment="OLLAMA_MAX_LOADED_MODELS=2"
Environment="OLLAMA_NUM_PARALLEL=2"
Environment="OLLAMA_FLASH_ATTENTION=1"

Restart Ollama with New Settings

sudo systemctl daemon-reload
sudo systemctl restart ollama

⚡ Performance Tip: Monitor resource usage with htop and docker stats to fine-tune these settings.

Backup Strategy

Implement automated backups for your OpenWebUI installation:

Create Backup Directory

mkdir -p ~/backups/openwebui
chmod 755 ~/backups

Create Backup Script

nano ~/backup-openwebui.sh

OpenWebUI Backup Script

#!/bin/bash
DATE=$(date +%Y%m%d_%H%M%S)
BACKUP_DIR="/home/openwebui/backups"

# Create backup directory
mkdir -p $BACKUP_DIR

# Backup OpenWebUI data
docker run --rm -v openwebui:/source -v $BACKUP_DIR:/backup alpine tar czf /backup/openwebui_data_$DATE.tar.gz -C /source .

# Backup Ollama models
tar -czf $BACKUP_DIR/ollama_models_$DATE.tar.gz /usr/share/ollama/.ollama/models

# Backup configuration
cp ~/openwebui/.env $BACKUP_DIR/env_$DATE.bak
cp /etc/nginx/sites-available/openwebui $BACKUP_DIR/nginx_$DATE.conf

# Clean old backups (keep 7 days)
find $BACKUP_DIR -name "openwebui_data_*.tar.gz" -mtime +7 -delete
find $BACKUP_DIR -name "ollama_models_*.tar.gz" -mtime +7 -delete
find $BACKUP_DIR -name "env_*.bak" -mtime +7 -delete
find $BACKUP_DIR -name "nginx_*.conf" -mtime +7 -delete

echo "Backup completed: $DATE"

Make Script Executable and Schedule

chmod +x ~/backup-openwebui.sh
crontab -e
# Add: 0 2 * * * /home/openwebui/backup-openwebui.sh >> /var/log/openwebui-backup.log

💾 Backup Tip: Test your backup restoration process periodically to ensure your backups are working correctly.

Troubleshooting

Common issues and solutions:

🛠️ Support: For additional help, check the OpenWebUI GitHub repository, Discord community, or contact RamNode support for VPS-specific issues.

🎉 OpenWebUI Successfully Deployed!

Your private AI chat interface is now running on RamNode VPS. You have full control over your conversations, data, and AI models with a ChatGPT-like experience.

Self-Hosted AI

Private & Secure

Local Models

Deploy OpenWebUI on RamNode

📋 Guide Contents

Prerequisites

Server Requirements

Knowledge Requirements

Initial Server Setup

Install Docker

Deploy OpenWebUI

What is OpenWebUI?

Basic Configuration

Install Ollama (Local Models)

Set Up Nginx Reverse Proxy

Set Up SSL with Let's Encrypt

User Management

First-Time Setup

User Management Options

Model Management

Popular Ollama Models

Model Management Commands

Performance Optimization

System Optimization

Docker Resource Limits

Ollama Configuration

Backup Strategy

Troubleshooting

🎉 OpenWebUI Successfully Deployed!

Deploy OpenWebUI on RamNode

Prerequisites

Server Requirements

Knowledge Requirements

Initial Server Setup

Install Docker

Deploy OpenWebUI

What is OpenWebUI?

Basic Configuration

Install Ollama (Local Models)

Set Up Nginx Reverse Proxy

Set Up SSL with Let's Encrypt

User Management

First-Time Setup

User Management Options

Model Management

Popular Ollama Models

Model Management Commands

Performance Optimization

System Optimization

Docker Resource Limits

Ollama Configuration

Backup Strategy

Troubleshooting

Cannot Connect to OpenWebUI

Models Not Loading or Slow Response

Poor Performance or Timeouts

SSL Certificate Problems

🎉 OpenWebUI Successfully Deployed!