Custom recommendations checklist

This page provides a checklist of the steps required to create a genericrecommendations app.

If you're new to Vertex AI Search, consider following theGet startedwith custom recommendations tutorial to create asample app.

Set up a Google Cloud project, turn on Vertex AI Search, and set up accesscontrol for your project. You can use an existing Google Cloud project if youhave one already.

Actions

  1. ReviewBefore you begin and confirm that you have completed the steps.

Prepare your data for importing to Vertex AI Search.

For custom recommendations, you must supplystructured data.This is data provided with a specific schema. For example, youcan provide data in a BigQuery table or as JSON files inCloud Storage.

Actions

  1. Review the information about supported data and the relationship between appsand data stores inAbout apps and datastores.

  2. Prepare your data according to the requirements inPrepare data foringestion.

Create a data store and then import your data into it.

How you import your data depends on where you're importing it from. Forexample, if your data is in Cloud Storage, you can import it using theconsole or the API by providing the bucket location of your data.

Actions

  1. Follow the instructions for your data source inCreate a custom recommendationsdata store.

Create your custom recommendations app and connect it to your new data store.

Actions

  1. Create a custom recommendations app.

You can update field settings to make them filterable and filter yourrecommendations results using those fields.

Actions

  1. Set specific fields as filterable to allow Vertex AI Search to usethose fields for filtering recommendations. SeeConfigure fieldsettings.

  2. Filter recommendations.

You can preview your recommendations to check if your recommendations areappearing as expected.

Actions

  1. To preview your recommendations, use the Vertex AI Search console or the API.

    • Console. Use the consolePreview page to preview yourrecommendations. See theConsole instructions for the kind of data thatyour app uses inGetrecommendations.

    • API. If you're integrating API calls into your application, make APIcalls to preview your recommendations. See theRESTinstructions for the kind of data that your app uses inGetrecommendations.

When you are happy with the previews from your recommendations app, shareit with your users by deploying it to your website.

Actions

  1. To deploy your recommendations app, integrate API calls into your server orapplications. For more information about making API calls, see theRESTinstructions for the kind of data that your app uses inGetrecommendations.

    For client library resources, seeVertex AI Search clientlibraries.

To get personalized recommendation results, you can update the user eventsin your recommendation app. For more information seeAbout user events.

Actions

  1. Import historical user events.
  2. Record real-time user events.

You can maintain your app to ensure that latest and necessary data is availablein your data store.

Actions

  1. Refresh your data.

Except as otherwise noted, the content of this page is licensed under theCreative Commons Attribution 4.0 License, and code samples are licensed under theApache 2.0 License. For details, see theGoogle Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2026-02-19 UTC.