Skip to main content

Integrating Google Vertex AI with Progress Agentic RAG

This guide provides step-by-step instructions for deploying Google Vertex AI and integrating it with Progress Agentic RAG to enable AI-powered search capabilities using Google's Gemini models.

Prerequisites​

Before beginning the integration process, ensure you have the following:

  • An active Google account
  • Access to the Google Cloud Console
  • A valid billing account configured in Google Cloud Platform
  • Administrative access to Progress Agentic RAG

Integration Steps​

1. Configure Google Cloud Platform​

1.1 Create a Google Cloud Project​

  1. Sign in to the Google Cloud Console
  2. Create a new project or select an existing project
  3. Associate a billing account with your project to enable API usage and track consumption metrics

2. Create and Configure Service Account​

2.1 Create Service Account​

  1. Navigate to IAM & Admin > Service Accounts in the Google Cloud Console
  2. Click Create Service Account Google Vertex Service Account Creation Page
  3. Provide the following information:
    • Service account name: A descriptive name for the service account
    • Service account ID: A unique identifier (auto-generated from the name)
    • Description: Brief description of the service account's purpose
  4. Click Create and Continue

2.2 Assign Permissions​

  1. Grant the necessary roles and permissions required for Vertex AI operations
  2. Configure principals who should have access to this service account (optional)
  3. Click Done to complete the service account creation

2.3 Generate and Download Credentials​

  1. Locate your newly created service account in the service accounts list
  2. Click on the service account to open its details
  3. Navigate to the Keys tab Google Vertex Service Account Details Page
  4. Click Add Key > Create new key
  5. Select JSON as the key type
  6. Click Create to generate and download the JSON key file Vertex JSON Key Generation
  7. Store the downloaded JSON file securely. This file contains sensitive credentials

3. Select Vertex AI Region​

  1. Navigate to Vertex AI > Model Registry in the Google Cloud Console
  2. Review available regions (e.g., us-central1, europe-west4)
  3. Select a region based on your geographic requirements and latency considerations
  4. Note the selected region identifier for use in the configuration step

4. Configure Progress Agentic RAG​

4.1 Access AI Models Configuration​

  1. Log in to the Progress Agentic RAG dashboard
  2. Navigate to the AI Models tab

4.2 Configure Google Gemini Model​

  1. Select your desired Google Gemini model from the available options
  2. Enable the Use your own Google key toggle
  3. In the JSON Credential field, paste the complete contents of the JSON key file downloaded in Step 2.3
  4. Enter your Vertex AI location (region identifier from Step 3) Progress LLM Selection Page
  5. Click Save Changes to apply the configuration

5. Verify Integration​

5.1 Configure Search Settings​

  1. Navigate to the Search tab in Progress Agentic RAG
  2. Verify that the selected search configuration is using the Gemini model you configured

5.2 Test the Integration​

  1. Submit a test query through the search interface
  2. Wait for the response to be generated
  3. A successful response confirms that the Vertex AI integration is functioning correctly

Troubleshooting​

If you encounter issues during the integration process:

  • Authentication errors: Verify that the JSON credentials file is correctly formatted and contains valid credentials
  • Permission errors: Ensure the service account has the necessary Vertex AI permissions
  • Region errors: Confirm that the region specified in Progress Agentic RAG matches your Vertex AI configuration
  • No response: Check your Google Cloud billing account status and API quota limits

Security Best Practices​

  • Store JSON credential files securely.
  • Regularly rotate service account keys according to your organization's security policies
  • Implement principle of least privilege when assigning service account permissions
  • Monitor service account usage through Google Cloud's audit logs

Additional Resources​

For additional support or questions regarding this integration, please contact Progress support team.