Google Vertex AI (Gemini)
With Google Vertex AI (Gemini) modules in Make, you can create text prompts (text-bison), chat prompts (chat-bison and gemini-pro), and analyze images and video.
To get started, you must have a Google account and an existing Google Cloud project in the Google Cloud Platform with the Vertex AI Gemini API and billing enabled. For more information on how to enable these items, see the Connect Google Vertex AI (Gemini) to Make section.
You can create a Google account at account.google.com.
Refer to the Vertex AI Gemini API documentation for a list of available endpoints.
Note
Make's use and transfer of information received from Google APIs to any other app will adhere to Google API Services User Data Policy.
Connect Google Vertex AI (Gemini) to Make
To establish the connection, you must
Create a Google Cloud Platform project for Google Vertex AI (Gemini)
To create a Google Cloud Platform project:
Log in to the Google Cloud Platform using your Google credentials.
On the welcome page, click Create or select a project > New project.
Enter a Project name and select the Location for your project.
Click Create.
In the top menu, check if your new project is selected in the Select a project dropdown. If not, select the project you just created.
Note
To create a new project or work in the existing one, you need to have the serviceusage.services.enable permission. If you don’t have this permission, ask the Google Cloud Platform Project Owner or Project IAM Admin to grant it to you.
Enable API for Google Vertex AI (Gemini)
To enable the required API:
Open the left navigation menu and go to APIs & Services > Library.
Search for the following API: Vertex AI Gemini API.
Click Vertex AI Gemini API, then click Enable.
If your project's billing has not yet been enabled, a Billing required prompt will appear. Click the Enable Billing button and complete the enabling process.
As an alternative, you can enable billing in your Google Cloud Platform here.
For more information regarding billing, refer to the Google Cloud Billing guide.
Establish the connection with Google Vertex AI (Gemini) in Make
To establish the connection in Make:
Log in to your Make account, add a Google Vertex AI (Gemini) module to your scenario, and click Create a connection.
Optional: In the Connection name field, enter a name for the connection.
Optional: Switch on the Show advanced settings toggle and enter your Google Cloud Platform project client credentials. For more information, see the Create and configure a Google Cloud Platform project for Google Vertex AI (Gemini) section below.
Click Sign in with Google.
If prompted, authenticate your account and confirm access.
You have successfully established the connection. You can now edit your scenario and add more Google Vertex AI (Gemini) modules. If your connection requires reauthorization at any point, follow the connection renewal steps here.
To connect to Make using your own client credentials, you can create and configure a project in the Google Cloud Platform.
Configure your OAuth consent screen for Google Vertex AI (Gemini)
To configure your OAuth consent screen:
In the left sidebar, click Google Auth Platform.
Note
If you don't see Google Auth Platform in the left sidebar, click View all products at the top of it, then pin Google Auth Platform to the sidebar.
Click Get Started.
In the Overview section, under App information, enter Make as the app name and provide your Gmail address. Click Next.
Under Audience, select External.
For more information regarding user types, refer to Google's Exceptions to verification requirements documentation.
Under Contact Information, enter your Gmail address.
Under Finish, agree to the Google User Data Policy.
Click Continue > Create.
In the Branding section, under Authorized domains, add
make.comandintegromat.com. Click Save.Optional: In the Audience section, add your Gmail address on the Test users page, then click Save and continue if you want the project to remain in the Testing publishing status.
In the Data Access section, click Add or remove scopes, add the following scopes, and click Update:
https://www.googleapis.com/auth/userinfo.emailhttps://www.googleapis.com/auth/cloud-platform
Click Save.
Note
Publishing Status
Testing: If you keep your project in the Testing status, you will be required to reauthorize your connection in Make every week. To avoid weekly reauthorization, update the project status to In production.
In production: If you update your project to the In production status, you will not be required to reauthorize the connection weekly. To update your project's status, go to the OAuth consent screen, the Audience section, and click Publish app. If you see the notice Needs verification, you can choose whether to go through the Google verification process for the app or to connect to your unverified app. Currently connecting to unverified apps works in Make, but we cannot guarantee the Google will allow connections to unverified apps for an indefinite period.
For more information regarding the publishing status, refer to the Publishing status section of Google's Setting up your OAuth consent screen help.
Create your Google Vertex AI (Gemini) client credentials
To create your client credentials:
In Google Auth Platform, click Clients.
Click + Create Client.
In the Application type dropdown, select Web application.
Update the Name of your OAuth client. This will help you identify it in the platform.
In the Authorized redirect URIs section, click + Add URI and enter the following redirect URI:
https://www.make.com/oauth/cb/google-vertex-ai.Click Create.
Click the OAuth 2.0 Client you created, copy your Client ID and Client secret values, and store them in a safe place.
You will use these values in the Client ID and Client Secret fields in Make.
Build Google Vertex AI (Gemini) Scenarios
After connecting the app, you can perform the following actions:
Create a Text Prompt (text-bison)
Create a Chat Prompt (chat-bison)
Analyze Image/Video
Create a Chat Prompt (gemini-pro)
Make an API Call