Setup and installation of 'LangFlow & LangChain' on GCP

This section describes how to provision and connect to AI App Development using LangChain & LangFlow VM solution on GCP.

1. Open AI App Development using LangChain & LangFlow listing on GCP Marketplace
2. Click Get Started.

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.

• 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.

• It will show you the successfully agreed popup page. Click on Deploy.

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

• Tick the existing account radio button and select your existing service account from the "Select a service account" dropdown as shown below.

• If you don't see the service account in "Select a service account" drop down, then please follow the below steps to add one. if you can see a service account in the dropdown, skip ahead to the next step to select the region for your deployment.
below steps are one time only and you need appropriate IAM permissions to execute these steps. If you encounter IAM permission errors, reach out to your organization's IAM admin to execute these steps :
1. Note Project id : First note down the project-id of the project where you are deploying our solution . Project id can be found by clicking on the project dropdown and copying id from the poped up window.


2. Activate cloud shell by clicking the shell icon at the top right corner.

3. In the cloud shell, run below command to switch to the project where you are deploying this solution , replace PROJECT_ID with the actual project id copied in step a.

gcloud config set project "PROJECT_ID"

4. Then run below command to create new service account, replace highlighted bold text with suitable values.

gcloud iam service-accounts create "your-service-account-name" --description="service account for your-google-cloud-login-emailid " --display-name="your-service-account-name"

5. Then run below command to associate the newly created service account with your google cloud login id, replace highlighted bold text with values provided in above steps

gcloud iam service-accounts add-iam-policy-binding your-service-account-name@projectid-copied-in-step-a.iam.gserviceaccount.com --member="user:your-google-cloud-login-emailid" --role="roles/iam.serviceAccountUser"

6. Then run below 3 commands one after the other , replace highlighted bold text with your service account name provided in previous steps.

gcloud projects add-iam-policy-binding tcw-project-381520 --member=serviceAccount:your-service-account-name@projectid-copied-in-step-a.iam.gserviceaccount.com --role=roles/config.agent

gcloud projects add-iam-policy-binding tcw-project-381520 --member=serviceAccount:your-service-account-name@projectid-copied-in-step-a.am.gserviceaccount.com --role=roles/compute.admin

gcloud projects add-iam-policy-binding tcw-project-381520 --member=serviceAccount:your-service-account-name@projectid-copied-in-step-a.iam.gserviceaccount.com --role=roles/iam.serviceAccountUser

7. Once the above steps are done, wait for 60 seconds then refresh the deployment page and you should see the newly created service account in "Select a service account". Continue with the next steps below.

• 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)
• Optionally change the boot disk type and size. (This defaults to ‘Standard Persistent Disk’ and 15 GB respectively)
• Optionally change the network name and subnetwork names. Be sure that whichever network you specify has ports 22 (for ssh), 3389 (for RDP) , 80 (for HTTP) and 443 (for HTTPS) exposed.
• Click Deploy when you are done.
• AI App Development using LangChain & LangFlow will begin deploying.

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

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

5. This will open SSH window in a browser.
6. Run below command to set the password for “ubuntu” user

sudo passwd ubuntu

7. 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.

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

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

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

11. 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

12. Now you are connected to out of box AI App Development using LangChain & LangFlow environment via Windows machines.

13. 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, firstInstall Remmina as per your linux distribution.

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

15. 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

16. Now you are connected to out of box AI App Development using LangChain & LangFlow environment via Linux machine.

17. To access the Langflow User interface, open the terminal and run below command to create LangFlow superuser and provide the username and password for super user. This will be used for logging in to langflow.

sudo langflow superuser

18. Once Superuser is created, open https://vm-public-ip in your local browser, accept the SSL warning by clicking advanced and login using the superuser credentials used in above step.

19. Now you are logged in to LangFlow user interface using superuser.

20. On the home page, click on key icon at the top right to generate the new API keys.

21. On this page, click on “Create new secret key”.

22. A pop up will appear, provide a name to your secret key and hit “Create secret key”

23. It will generate a secret key for you. Make sure to copy and save it somewhere.

24. You can also create new user and make them active/superuser from this UI. To do so click on the circle icon at the top right of this page and select Admin page.

25. On Admin Page, click on New User. A pop up will appear, enter the details of the new user. You can also make it active or superuser from this page.

26. New user can also signup on their own by clicking on “Signup link” on login page. Provide the details on this page and it will create new user but admin/superuser has to activate the newly created user.

27. To activate the new user, Login with superuser, go to Admin page and check the activate checkbox or superuser checkbox if you want to make this user as superuser. Click confirm on the Confirmation popup. Now your new user is active. You can login and use LangFlow UI with this user.

• Please refer to our LangChain-LangFlow udemy course to get the hands on experience

• Follow the Official LangChain and LangFlow Documentation for more details