Help for beginner

[Pemcode]

Hello everyone!

First of all, thank you for your work! :)

I would like to try testing the solution available at this address: https://catalog.ngc.nvidia.com/orgs/nvidia/teams/aiworkflows/helm-charts/rag-app-multimodal-chatbot

However, I've been stuck for three days trying to install the Cloud Native Stack locally.
I want to test it on my laptop (16GB RAM, RTX 4070, 16-core AMD Ryzen 7), but I always get stuck at some point during the installation of Kubernetes/containerd or anything else.

Is it an obligation to be connected at a NVidia VMI ?
Do you have a quick tutorial to follow the steps in order ?
Do I need to have a "hosts" file if I'm only using my local machine (running Ubuntu 22.04)?

Thank you in advance for your help.

Wishing the entire team a great day!

[AumGupta]

Hey @Pemcode,

Your question is a bit generic, but I have tried to answer all your ques one by one.

Is it an obligation to be connected at a NVidia VMI ?

No, it's not. You can deploy it on your local machine as long as your machine can run it.

Do you have a quick tutorial to follow the steps in order ?

( To set up Kubernetes and the NVIDIA Cloud Native Stack locally)

• Step 1: Install Docker

  • For Ubuntu 22.04, you can install Docker using the following commands:

    sudo apt update
    sudo apt install docker.io
    sudo systemctl enable --now docker
    sudo usermod -aG docker $USER
    newgrp docker

• Step 2: Install Kubernetes Tools (kubectl, kubelet, kubeadm)

  • You can install these tools with the following commands:

    sudo apt-get update && sudo apt-get install -y apt-transport-https curl
    curl -s https://packages.cloud.google.com/apt/doc/apt-key.gpg | sudo apt-key add -
    echo "deb https://apt.kubernetes.io/ kubernetes-xenial main" | sudo tee -a /etc/apt/sources.list.d/kubernetes.list
    sudo apt-get update
    sudo apt-get install -y kubelet kubeadm kubectl
    sudo apt-mark hold kubelet kubeadm kubectl

• Step 3: Initialize Kubernetes Cluster

  • Initialize the cluster using kubeadm:

    sudo kubeadm init --pod-network-cidr=192.168.0.0/16

  • Set up local kubeconfig:

    mkdir -p $HOME/.kube
    sudo cp -i /etc/kubernetes/admin.conf $HOME/.kube/config
    sudo chown $(id -u):$(id -g) $HOME/.kube/config

• Step 4: Install a Pod Network Add-on (e.g., Calico)

  • Apply Calico CNI plugin:

    kubectl apply -f https://docs.projectcalico.org/manifests/calico.yaml

• Step 5: Deploy NVIDIA GPU Operator

  • First, enable the NVIDIA GPU operator on your cluster:

    helm repo add nvidia https://nvidia.github.io/gpu-operator
    helm repo update
    helm install --wait --generate-name nvidia/gpu-operator

Do I need to have a "hosts" file if I'm only using my local machine (running Ubuntu 22.04)?

If you are only using your local machine, you typically do not need to modify the hosts file for Kubernetes and Docker to work.

---

Hope it helps.

[Pemcode]

Thanks a lot for your complete answer, I will try soon !