Go back

Setup and installation of 'AI Agents using CrewAI Studio & Jupyter with GPU support' on GCP

This section describes how to provision and connect to ‘AI Agents using CrewAI Studio & Jupyter with GPU support’ VM solution on GCP.

  1. Open AI Agents using CrewAI Studio & Jupyter with GPU support listing on GCP Marketplace.

  2. Click Get Started.

/img/gcp/crewai-vm/marketplace.png

It will ask you to enable the API’s if they are not enabled already for your account. Please click on enable as shown in the screenshot.

/img/gcp/nvidia-ubuntu/enable-api.png

  • It will take you to the agreement page. On this page, you can change the project from the project selector on top navigator bar as shown in the below screenshot.

  • Accept the Terms and agreements by ticking the checkbox and clicking on the AGREE button. /img/common/gcp_agreement_page.png

  • It will show you the successfully agreed popup page. Click on Deploy. /img/common/gcp_agreement_accept_page.png

  • On deployment page, give a name to your deployment.

  • In Deployment Service Account section, click on Existing radio button and Choose a service account from the Select a Service Account dropdown.
  • If you don't see any service account in dropdown, then change the radio button to New Account and create the new service account here.
  • If after selecting New Account option, you get below permission error message then please reach out to your GCP admin to create service account by following Step by step guide to create GCP Service Account and then refresh this deployment page once the service account is created, it should be available in the dropdown.

  • You are missing resourcemanager.projects.setIamPolicy permission, which is needed to set the required roles on the created Service Account
  • Select a zone where you want to launch the VM(such as us-east1-a)
  • Optionally change the number of cores and amount of memory. ( This defaults to 2 vCPUs and 7.5 GB RAM)

Minimum VM Specs : 7.5GB Memory /2vCPU

This VM can also be deployed using an NVIDIA T4 GPU instance to execute crewai agents faster. To deploy the VM with a GPU, click on the GPU tab as show in below screenshot and select a NVIDIA T4 GPU instance. Please note that GPU availability is limited to specific regions, zones, and machine types. If you do not see a GPU option for your selected region, zone, or machine type, try adjusting those settings to find available configurations.

/img/gcp/crewai-vm/gpu-instance.png

  • Optionally change the boot disk type and size. (This defaults to ‘Standard Persistent Disk’ and 50GB respectively)
  • Optionally change the network name and subnetwork names. Be sure that whichever network you specify has ports 22 (for ssh), 3389 (for RDP), port 80 (for HTTP) and 443 (for HTTPS) exposed.
  • Click Deploy when you are done.
  • AI Agents using CrewAI Studio & Jupyter with GPU support will begin deploying.

/img/gcp/crewai-vm/deployed-01.png

/img/gcp/crewai-vm/deployed-02.png

/img/gcp/crewai-vm/deployed-03.png

  1. A summary page displays when the compute engine is successfully deployed. Click on the Instance link to go to the instance page .

  2. On the instance page, click on the “SSH” button, select “Open in browser window”.

/img/gcp/puppet-support/ssh-option.png

  1. This will open SSH window in a browser. Switch to ubuntu user and navigate to ubuntu home directory.
sudo su ubuntu
cd /home/ubuntu/

/img/gcp/difyai-vm/switch-user.png

  1. Run below command to set the password for “ubuntu” user
sudo passwd ubuntu

/img/gcp/difyai-vm/update-passwd.png

  1. Now the password for ubuntu user is set, you can connect to the VM’s desktop environment from any local windows machine using RDP or linux machine using Remmina.

  2. To connect using RDP via Windows machine, first note the external IP of the VM from VM details page as highlighted below

/img/gcp/saltstack-semaphore/external-ip.png

  1. Then From your local windows machine, goto “start” menu, in the search box type and select “Remote desktop connection”

  2. In the “Remote Desktop connection” wizard, paste the external ip and click connect

/img/gcp/jupyter-python-notebook/rdp.png

  1. This will connect you to the VM’s desktop environment. Provide “ubuntu” as the userid and the password set in step 6 to authenticate. Click OK

/img/gcp/jupyter-python-notebook/rdp-login.png

  1. Now you are connected to out of box AI Agents using CrewAI Studio & Jupyter with GPU support VM’s desktop environment via Windows machines.

/img/azure/minikube/rdp-desktop.png

  1. To connect using RDP via Linux machine, first note the external IP of the VM from VM details page, then from your local Linux machine, goto menu, in the search box type and select “Remmina”.

Note: If you don’t have Remmina installed on your Linux machine, first Install Remmina as per your linux distribution.

/img/gcp/common/remmina-search.png

  1. In the “Remmina Remote Desktop Client” wizard, select the RDP option from dropdown and paste the external ip and click enter.

/img/gcp/common/remmina-external-ip.png

  1. This will connect you to the VM’s desktop environment. Provide “ubuntu” as the userid and the password set in step 6 to authenticate. Click OK

/img/gcp/common/remmina-rdp-login.png

  1. Now you are connected to out of box AI Agents using CrewAI Studio & Jupyter with GPU support VM’s desktop environment via Linux machine.

/img/azure/minikube/rdp-desktop.png

  1. To access the JupyterHub Web Interface, copy the public IP address of the VM and paste it in the browser as https://public_ip_of_vm.

Browser will display a SSL certificate warning message. Accept the certificate warning and Continue.

/img/azure/difyai-vm/browser-warning.png

  1. Provide the ‘ubuntu’ user and its password set in above steps. ubuntu is configured as an admin user here.

/img/azure/crewai-vm/jupyterhub-login.png

  1. Now you are loggedin to jupyterhub. Here you can see we have setup folder configured with jupyter-venv, jupyterhub_config.py files along with other jupyterhub configuration files. You can use jupyter notebook to run and test your CrewAI projects.

/img/azure/crewai-vm/jupyter-notebook.png

  1. To access CrewAI Studio, copy the public IP address of the VM and paste it in the browser as https://public_ip_of_vm/crewai-studio . Here you can create new tools, agents, crews and kickoff the crews to get the results.

/img/azure/crewai-vm/crewai.png

  1. If you deployed the VM using GPU instance then you can monitor GPU consumption by running below command in terminal. The command will automatically update nvidia-smi output every 1 seconds.
watch -n 1 nvidia-smi

/img/azure/crewai-vm/nvidia-smi.png

To get started with CrewAI Platform please visit CrewAI Quickstart Guide

To run your Crews using GUI please visit CrewAI Studio Quickstart

To Learn more about JupyterHub, multiuser environment and installing new python packages on this VM visit JupterHub Guide

For more details, please visit Official Documentation page

Go back