This page provides a checklist of the steps required to implement a media recommendations app.

<br />

If you're new to Agent Search, consider following the [Get started
with media recommendations](https://docs.cloud.google.com/generative-ai-app-builder/docs/try-media-recommendations) quickstart
tutorial to create a sample app.


### [Set up a Google Cloud
project](https://docs.cloud.google.com/generative-ai-app-builder/docs/media-recommendations-checklist#set-up-project)

Set up a Google Cloud project, turn on Agent Search, and set up access
control for your project. You can use an existing Google Cloud project if you
have one already.

### Actions

1. Complete the steps in [Before you begin](https://docs.cloud.google.com/generative-ai-app-builder/docs/before-you-begin.md.txt).

### [Prepare your data](https://docs.cloud.google.com/generative-ai-app-builder/docs/media-recommendations-checklist.md.txt#prepare-data)

Prepare your data for importing to Agent Search.

Media recommendations apps require two types of data:

- **Structured media data.** Upload metadata information about your media
  content, such as titles, descriptions, and URIs to the location of your media.
  Agent Search provides a predefined schema for media.
  Alternatively, you can use your own schema.

- **User events.** Recording user events is required for media recommendations.
  User events are required to train your app and to generate recommendations.

### Actions

1. Review information about media data and data stores and prepare your data
   according to the required schemas and fields in [About media documents and
   data stores](https://docs.cloud.google.com/generative-ai-app-builder/docs/media-documents). If you are
   using your own schema, also see [Example schema as a JSON
   object](https://docs.cloud.google.com/generative-ai-app-builder/docs/provide-schema#example-schema) and
   [structured data](https://docs.cloud.google.com/generative-ai-app-builder/docs/prepare-data.md.txt#structured).

2. Review media user event requirements in [About user
   events](https://docs.cloud.google.com/generative-ai-app-builder/docs/media-user-events).

### [Create your app and import
your data](https://docs.cloud.google.com/generative-ai-app-builder/docs/media-recommendations-checklist#import-data)

Create an app and data store and then import your media data and user events.

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

### Actions

1. [Create a media data store](https://docs.cloud.google.com/generative-ai-app-builder/docs/create-data-store-media.md.txt).

2. [Create a media recommendations
   app](https://docs.cloud.google.com/generative-ai-app-builder/docs/create-app-media#recs).

3. [Bulk import historical user events](https://docs.cloud.google.com/generative-ai-app-builder/docs/import-user-events.md.txt) so that
   your app can start training.

4. [Set up real-time user event recording](https://docs.cloud.google.com/generative-ai-app-builder/docs/record-user-events.md.txt).

### [Configure your
recommendations](https://docs.cloud.google.com/generative-ai-app-builder/docs/media-recommendations-checklist#configure-settings)

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

### Actions

1. To let Agent Search use a certain field for filtering
   recommendations, set that field as filterable. See [Configure field
   settings](https://docs.cloud.google.com/generative-ai-app-builder/docs/configure-field-settings).

2. [Filter recommendations](https://docs.cloud.google.com/generative-ai-app-builder/docs/filter-recommendations.md.txt).

3. [Boost and bury recommendations](https://docs.cloud.google.com/generative-ai-app-builder/docs/media-recommendations-boost-bury.md.txt).

4. [Diversify media recommendations](https://docs.cloud.google.com/generative-ai-app-builder/docs/diversify-recommendations.md.txt).

5. Demote content if a user has recently viewed it or if the content is old. See
   [Demote media recommendations](https://docs.cloud.google.com/generative-ai-app-builder/docs/demote-recommendations.md.txt).

### [Preview
recommendations](https://docs.cloud.google.com/generative-ai-app-builder/docs/media-recommendations-checklist#preview-results)

You can preview your recommendations to check if your recommendations are
appearing as expected.

### Actions

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

   - **Console.** Use the console **Preview** page to preview your
     recommendations. See the **Console** instructions for the kind of data that
     your app uses in [Get
     recommendations](https://docs.cloud.google.com/generative-ai-app-builder/docs/preview-recommendations).

   - **API** . If you're integrating API calls into your application, make API
     calls to preview your recommendations. See the **REST**
     instructions for the kind of data that your app uses in [Get
     recommendations](https://docs.cloud.google.com/generative-ai-app-builder/docs/preview-recommendations).

### [Deploy your
recommendations app](https://docs.cloud.google.com/generative-ai-app-builder/docs/media-recommendations-checklist#preview-results)

When you're happy with the preview version of your media recommendations app,
share it with your users by deploying it to your website.

### Actions

1. To deploy your recommendations app, integrate API calls into your server or
   applications. For more information about making API calls, see the **REST**
   instructions for the kind of data that your app uses in [Get
   recommendations](https://docs.cloud.google.com/generative-ai-app-builder/docs/preview-recommendations).

   For client library resources, see [Agent Search client
   libraries](https://docs.cloud.google.com/generative-ai-app-builder/docs/libraries).

### [Maintain your app](https://docs.cloud.google.com/generative-ai-app-builder/docs/media-recommendations-checklist.md.txt#maintain-data)

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

Media recommendations apps are automatically tuned every 3 months. However, if
your data store undergoes significant change or if you do a bulk import of user
events, you should manually retrain your app.

### Actions

1. [Check the quality of your media data](https://docs.cloud.google.com/generative-ai-app-builder/docs/check-media-data-quality.md.txt).

2. [Refresh your structured data](https://docs.cloud.google.com/generative-ai-app-builder/docs/refresh-data.md.txt#refresh-structured).

3. [Train and tune media apps](https://docs.cloud.google.com/generative-ai-app-builder/docs/train-tune-media.md.txt).