Revolutionizing AI Workflows: Integrating GCP Vertex AI with Workload Automation

​Let us begin with understanding the GCP Vertex AI plugin and how it benefits our workload automation users.
Use GCP Generative AI on Vertex AI to generate texts in the context of your workflow or based on the analysis of your data.

​To empower your Workload Automation environment, download the GCP Vertex AI plug-in available on Automation Hub.
 
The GCP Vertex AI plugin is a valuable addition to Workload Automation, designed to integrate with GCP Vertex AI and automate the development, deployment, and management of AI models. By leveraging the power of Vertex AI, you can harness the benefits of machine learning to drive innovation and improve your business processes.
 
Key Features:

• Vertex AI Integration: Seamlessly integrate Workload Automation with GCP Vertex AI to orchestrate AI workflows.
• Model Development and Deployment: Automate the training, deployment, and management of machine learning models.
• Model Serving: Serve your trained models as APIs for real-time predictions.
• Hyperparameter Tuning: Optimize your models using automated hyper parameter tuning.
• Integration with Other Google Cloud Services: Easily connect your AI models with other Google Cloud services, such as Data flow, Big Query, and Cloud Storage.

 
Use Cases:

• Predictive Analytics: Build and deploy predictive models to forecast future trends and make informed decisions.
• Recommendation Systems: Develop personalized recommendations for your customers.
• Natural Language Processing: Process and understand natural language text.
• Image and Video Analysis: Analyze images and videos to extract valuable insights.
• Anomaly Detection: Identify unusual patterns or outliers in your data.

 
Example Workflow:
This business scenario demonstrates how Workload Automation can effectively orchestrate GCP Vertex AI for customer churn prediction. By automating the training, deployment, and prediction process, the retailer can gain valuable insights into customer behavior and proactively address churn risks. This can lead to improved customer retention and increased revenue.

Perform GCP Vertex AI plugin with Workload Automation
Log in to the Dynamic Workload Console and open the Workload Designer. Choose to create a new job and select “GCP Vertex AI” job type in the other section. 

General Tab:
Name: User can provide any name in name field
Workstation: You need to choose the workstation

Connection:
In the Action tab you must enter all information required both for carrying out a test connection:

• IBM WatsonX Api Key: the API key that you can generate on your IBM WatsonX personal profile.

●        GCP Default Credentials: Select this option if the system has to fetch default credentials from system configuration.
 
Note: Environment variable has to be configured for default access GOOGLE_APPLICATION_CREDENTIALS.
 
To configure the default access do the following:
-          Stop the Dynamic Agent
 
-          Edit the configuration file
<TWSDATA_INST_FOLDER>/ITA/cpa/config/JobManager.ini
      In the [ITA Env] section enter the variable

GOOGLE_APPLICATION_CREDENTIALS=/TestTools/executors/GCF/hclsw-gcp-common-876d729a6a30.json

SHLIB_PATH = $SHLIB_PATH:.:

LIBPATH = $LIBPATH:/opt/IBM/TWA_ITAuser/TWS/JavaExt/jre/jre/lib/ppc641e/j9vm:/opt/IBM/TWA_ITAuser/TWS/JavaExt/jre/jre/lib/ppc641e/j9vm/../../ppc64:LD_LIBRARY_PATH = $LD_LIBRARY_PATH:.

-          Restart the Dynamic Agent

• Project ID: The project ID is a unique number associated with each project.

●        GCP Server Credentials: Select this option to enter the GCP credentials manually.

• Service account: The service account associated to your Google Cloud Platfom account. Click the Select button to choose the service account in the cloud console. Select an item from the list, the selected item is displayed in the Service Account field.

Note: This attribute is required. The service account is the identity of the service, and the service account's permissions control which resources the service can access.

• Location: Associated location area. This attribute is required.
• Model: the model used to generate the output message. This attribute is required.
  
  

Action:
In the Action tab you must enter all information required for executing the plug-in:

• User message: the message you want to send to the assistant. The attribute is required

Submitting your job:

It is time to Submit your job to the current plan. You can add your job to the job stream that automates your business process flow. Select the action menu in the top-left corner of the job definition panel and click on Submit Job into Current Plan. A confirmation message is displayed, and you can switch to the Monitoring view to see what is going on. 

​Monitor Page:
Users can track the jobs in the monitor page. If the job completes successfully in the backend GCP Vertex AI, the status should be changed to successful.

Job Log Details:

Output Properties:

​In Conclusion:
The GCP Vertex AI plugin is a powerful tool that enables you to leverage the benefits of AI within your Workload Automation environment. By integrating with Vertex AI, you can build and deploy AI models more efficiently, drive innovation, and gain a competitive advantage.

Authors Bio

---

​Jossef Alabyad - 
Software Engineer at HCL Software
Works as a Plug-in developer in the Workload Automation Plug-in factory team.                            
​Acquired skills on Java, Microservices, Docker.

---

Ernesto Carrabba, Product Manager, HCL Clara, HCL HERO and HCL Workload Automation 
 
Ernesto Carrabba is the Product Manager for HCL Clara, HCL HERO and HCL Workload Automation. Ernesto is a very dynamic product manager with experience in building and launching IoT products, combined with a master's degree in mechanical engineering and study researches on Augmented and Virtual Reality