Skip to content

11. Deploy and Serve a Feature List

You'll designate features as Production-Ready, navigate FeatureByte's Approval Flow, and once all features in your list receive approval, deploy it for both online and batch serving.

Step 1: Mark a Feature as Production-Ready

Navigate to the Feature catalog from the Experiment section of the menu.

Name

Locate the most predictive feature by sorting based on the predictive score, here "CUSTOMER_Count_of_invoices_4w."

Name

Click the three dots next to the feature's current status (e.g., DRAFT) and change its readiness to "Production-Ready".

Name

Confirm.

Name

Note

If your catalog has an Approval Flow enabled, upgrading features to "Production-Ready" requires approval.

Step 2: Enable Approval Flow

Click on the settings icon located next to the Catalog name at the top of the screen.

Name

Inside the catalog settings, locate and enable the 'Approval Flow' option.

Name

Look for a validation mark next to the Catalog name. This indicates the Approval Flow is enabled.

Name

Step 3: Request Production-Ready Upgrade

Search "CUSTOMER_Entropy_of_items_TotalCosts_by_product_ProductGroup_4w" feature, click 'Upgrade to Production Ready' and confirm you want to change its readiness.

Name

This initiates an approval request. Click 'View' to see the request.

Name

The request is listed for Production-Ready upgrade.

Name

Step 4: Review Checks

Click on the request to view details and checks.

Note

Checks include several evaluations, such as checking the feature's compliance with default cleaning operations and the feature job setting of its source tables. It also involves confirming the status of these tables and backtesting the feature job setting to prevent future training-serving inconsistencies.

Name

If any checks fail, resolve them. In our case, a check is failing because no backtest has been run to assess the feature job setting.

Click 'Run Backtest'. This should turn the check green.

Name

Step 5: Review Feature

Review the feature details, including its definition and use of tiles (partial aggregations).

Name

Name

Step 6: Request Review

Once the request is ready for review, request it.

Name

The request is now awaiting approval.

Name

Step 7: Approve and Merge Request

After review, approve.

Name

Name

Confirm the merge.

Name

Step 8: Audit Merged Request

Click 'Merged' to see details of merged requests.

Name

Step 9: Requests by batch

To mark all features in a feature list as "Production-Ready",

  1. Go to the Feature List Catalog.
  2. Click on the check icon next to the calculator button of the feature list you want to update.

Name

Name

Confirm.

Name

Navigate to 'New Production-Ready Feature' under 'Feature Requests' of the 'Approve' section of the menu.

Name

Since all checks passed, select all requests by checking the box next to 'Name', and then request reviews in batches.

Name

Approve.

Name

Merge requests.

Name

The merged requests can be found in the Merged tab.

Name

Step 10: Deploy

Now that all features in our feature list are "Production-Ready," we can deploy it.

Click the rocket icon to initiate deployment.

Name

Provide a name (e.g. "Top10+entropy list for Customer Activity next Week @ store") and associate the deployment with your Use Case for tracking.

Name

Click 'View Deployment' to access the deployment in the Deployment Catalog.

Name

Step 11: Enable Deployment

In the Deployment Catalog (under the 'Manage' Section), locate the new deployment and select it.

Name

Name

Click the three dots next to the 'NEW' label and choose 'Enable.'

Name

Name

Name

Step 12: Online Serving

In the 'Online Serving' tab, find Python or shell script templates for REST API services.

Name

Name

Go to the 'Preview' tab to see examples of feature values that will be served.

Name

Use the SDK for batch serving if needed.