ollama-setup.sh

#!/bin/bash

# Exit on error
set -e

# Colors for output
RED='\033[0;31m'
GREEN='\033[0;32m'
YELLOW='\033[1;33m'
NC='\033[0m' # No Color

# Logging function
log() {
    echo -e "${GREEN}[$(date '+%Y-%m-%d %H:%M:%S')]${NC} $1"
}

error() {
    echo -e "${RED}[$(date '+%Y-%m-%d %H:%M:%S')] ERROR:${NC} $1" >&2
}

# Start setup
log "Starting Ollama setup on EC2..."

# Install Ollama
log "Installing Ollama..."
curl -fsSL https://ollama.com/install.sh | sh

# Create models directory
log "Creating models directory..."
sudo mkdir -p /opt/dlami/nvme/ollama-models
sudo chown -R ollama:ollama /opt/dlami/nvme/ollama-models

# Configure Ollama service
log "Configuring Ollama service..."
sudo mkdir -p /etc/systemd/system/ollama.service.d
sudo tee /etc/systemd/system/ollama.service.d/override.conf > /dev/null <<EOF
[Service]
Environment="OLLAMA_HOST=0.0.0.0"
Environment="OLLAMA_MODELS=/opt/dlami/nvme/ollama-models"
EOF

# Reload and restart service
log "Restarting Ollama service..."
sudo systemctl daemon-reload
sudo systemctl restart ollama

# Wait for service to be ready
log "Waiting for Ollama service to be ready..."
sleep 5

# Check if Ollama is running
if ! systemctl is-active --quiet ollama; then
    error "Ollama service failed to start"
    exit 1
fi

# Pull the model
log "Pulling models (this may take a while)..."
ollama pull gpt-oss:20b

PRIVATE_IP=$(hostname -I | awk '{print $1}')
sudo apt install btop

# Display results
echo ""
echo -e "${GREEN}========================================${NC}"
echo -e "${GREEN}Ollama Setup Complete!${NC}"
echo -e "${GREEN}========================================${NC}"
echo ""
echo -e "${YELLOW}OpenAI Base URL:${NC} http://${PRIVATE_IP}:11434/v1"
echo ""
echo -e "${GREEN}You can now use this base URL with OpenAI-compatible clients${NC}"
echo -e "${GREEN}Example: export OPENAI_BASE_URL=\"http://${PRIVATE_IP}:11434/v1\"${NC}"
echo ""