Deploy OpenWebUI on RamNode

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

Knowledge Requirements

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

ssh root@your-server-ip

apt update && apt upgrade -y

adduser openwebui
usermod -aG sudo openwebui
su - openwebui

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

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

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

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

docker --version
docker compose version

mkdir -p ~/openwebui
cd ~/openwebui

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

docker ps
docker logs openwebui

docker stop openwebui

nano ~/openwebui/.env

# 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

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

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

sudo systemctl start ollama
sudo systemctl enable ollama

ollama pull llama2

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

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

sudo apt install nginx -y

sudo nano /etc/nginx/sites-available/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;
 }
}

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

sudo apt install certbot python3-certbot-nginx -y

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

sudo certbot renew --dry-run

First-Time Setup

Access your OpenWebUI instance:

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

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

# 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

# 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

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 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

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

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

sudo systemctl daemon-reload
sudo systemctl restart ollama

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

nano ~/backup-openwebui.sh

#!/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"

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

Cannot Connect to OpenWebUI

Models Not Loading or Slow Response

Poor Performance or Timeouts

SSL Certificate Problems