Skip to main content

Google Vertex AI Integration with Orkes Conductor

To use system AI tasks in Orkes Conductor, you must integrate your Conductor cluster with the necessary AI/LLM providers. This guide explains how to integrate Google Vertex AI with Orkes Conductor. Here’s an overview:

  1. Get the required credentials from Google Vertex AI.
  2. Configure a new Google Vertex AI integration in Orkes Conductor.
  3. Add models to the integration.
  4. Set access limits to the AI model to govern which applications or groups can use them.

Step 1: Get the Google Vertex AI credentials​

To integrate Google Vertex AI with Orkes Conductor, retrieve the project ID and service account JSON from the Google Cloud console.

Get the project ID​

To get the project ID:

  1. Sign in to the Google Cloud Console.
  2. Create a new project or select an existing one.
  3. Get the Project ID from the dashboard.

Get project ID from Google Cloud Console

For more information, refer to the official documentation on creating and managing projects in GCP.

Get the service account JSON​

To get the service account JSON:

  1. Go to IAM & Admin > Service Accounts from the left menu on your GCP console.
  2. Create a new service or select an existing one.
  3. In the KEYS tab, select ADD KEY > Create new key.

Get Service Account JSON from Google Cloud Console

  1. Select the key type as JSON.
  2. Select Create to download the JSON file.

Get Service Account JSON key from Google Cloud Console

To use Google Vertex AI with Orkes Conductor, you must enable the Vertex AI API from the GCP console.

Enable Vertex AI API​

To enable Vertex AI API:

  1. Go to APIs & Services > Enabled APIs & services from the left menu on your GCP console.
  2. Select + ENABLE APIS AND SERVICES.

Enabling APIs and services from GCP console

  1. In the API Library, search for Vertex AI API.

Searching for Vertex AI API in API Library

  1. Select ENABLE.

Enabling Vertex AI API

Once enabled, the Vertex AI API is ready for use with your GCP project.

Step 2: Add an integration for Google Vertex AI​

After obtaining the credentials, add a Google Vertex AI integration to your Conductor cluster.

To create a Google Vertex AI integration:

  1. Go to Integrations from the left navigation menu on your Conductor cluster.
  2. Select + New integration.
  3. In the AI/LLM section, choose Google Vertex AI.
  4. Select + Add and enter the following parameters:
ParametersDescription
Integration nameA name for the integration.
Project IDThe Project ID retrieved from the GCP console.
LocationThe Google Cloud region of your GCP account.
PublisherThe publisher’s name in GCP. By default, this is set to google.
Choose Service account credentials JSONUpload the service account JSON file, which is a key file containing the credentials for authenticating the Orkes Conductor cluster with the GCP services.
DescriptionA description of the integration.

Google Vertex AI Integration with Orkes Conductor

  1. (Optional) Toggle the Active button off if you don’t want to activate the integration instantly.
  2. Select Save.

Step 3: Add Google Vertex AI models​

Once you’ve integrated Google Vertex AI, the next step is to configure specific models.

Google Vertex AI has different models, such as Bison, Gecko, and more, each designed for various use cases. Choose the model that best fits your use case.

To add a model to the Google Vertex AI integration:

  1. Go to the Integrations page and select the + button next to the integration created.

Create new model for Vertex AI Integration

  1. Select + New model.
  2. Enter the Model name and a Description. Get the complete list of Vertex AI models.

Creating new model for Vertex AI Integration

  1. (Optional) Toggle the Active button off if you don’t want to activate the model instantly.
  2. Select Save.

This saves the model for future use in AI tasks within Orkes Conductor.

Step 4: Set access limits to integration​

Once the integration is configured, set access controls to manage which applications or groups can use the models.

To provide access to an application or group:

  1. Go to Access Control > Applications or Groups from the left navigation menu on your Conductor cluster.
  2. Create a new group/application or select an existing one.
  3. In the Permissions section, select + Add Permission.
  4. In the Integration tab, select the required AI models and toggle the necessary permissions.
  5. Select Add Permissions.

Add Permissions for Vertex AI Integration

The group or application can now access the AI model according to the configured permissions.

With the integration in place, you can now create workflows using AI/LLM tasks.

More resources​