import OpenAI from "openai";

const openai = new OpenAI();

async function main() {
    const stream = await openai.chat.completions.create({
        model: "gpt-4o-mini",
        messages: [{ role: "user", content: "Say this is a test" }],
        stream: true,
    });
    for await (const chunk of stream) {
        process.stdout.write(chunk.choices[0]?.delta?.content || "");
    }
}

main();

curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey \
    | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg
    
curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list \
    | sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' \
    | sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list
    
sudo apt-get update

# Configure Docker to use Nvidia driver
sudo apt-get install -y nvidia-container-toolkit  # NVIDIA Container Toolkit 
sudo nvidia-ctk runtime configure --runtime=docker
sudo systemctl restart docker

# Start the container
docker run -d --gpus=all -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama

# Add a UI to your Chat assistant
docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main

  "tabAutocompleteModel": {
    "title": "Codellama",
    "provider": "ollama",
    "model": "codellama:7b-code-q5_K_M"
  },