Get started with media search

Prepare the dataset

You use the Cloud Shell to import the Movielens dataset and restructure the dataset for Vertex AI Search for media.

Open the Cloud Shell

1. Open Google Cloud console .
2. Select your Google Cloud project.
3. Take note of the project ID in the Project infocard on the dashboard page. You will need the project ID for the following procedures.

4. Click the Activate Cloud Shellbutton at the top of the console. A Cloud Shell session opens inside a new frame at the bottom of the Google Cloud console and displays a command-line prompt.

   

Import the dataset

The Movielens dataset is available in a public Cloud Storage bucket to make it easier to import.

1. Run the following using your project ID to set the default project for the command-line.

    gcloud  
   config  
    set 
     
   project  
    PROJECT_ID 
    
   

2. Create a BigQuery dataset:

    bq  
   mk  
   movielens 
   

3. Load movies.csv into a new movies BigQuery table:

    bq  
   load  
   --skip_leading_rows = 
    1 
     
   movielens.movies  
    \ 
     
   gs://cloud-samples-data/gen-app-builder/media-recommendations/movies.csv  
    \ 
     
   movieId:integer,title,genres 
   

4. Load ratings.csv into a new ratings BigQuery table:

    bq  
   load  
   --skip_leading_rows = 
    1 
     
   movielens.ratings  
    \ 
     
   gs://cloud-samples-data/gen-app-builder/media-recommendations/ratings.csv  
    \ 
     
   userId:integer,movieId:integer,rating:float,time:timestamp 
   

Create BigQuery views

In this step, you will restructure the Movielens dataset so it follows the expected format for media data stores.

For this guide, you will create fake view-item user events during the past 90 days from positive ratings ( < 4 ).

1. Create a view that converts the movies table into the Document schema :

     bq 
     
    mk 
     
    -- 
    project_id 
    = 
     PROJECT_ID 
    
     
   \  
    -- 
    use_legacy_sql 
    = 
    false 
     
   \  
    -- 
    view 
     
    ' 
     
    WITH 
     
    t 
     
    AS 
     
    ( 
     
    SELECT 
     
    CAST 
    ( 
    movieId 
     
    AS 
     
    string 
    ) 
     
    AS 
     
    id 
    , 
     
    SUBSTR 
    ( 
    title 
    , 
     
    0 
    , 
     
    128 
    ) 
     
    AS 
     
    title 
    , 
     
    SPLIT 
    ( 
    genres 
    , 
     
    "|" 
    ) 
     
    AS 
     
    categories 
     
    FROM 
     
    ` 
     PROJECT_ID 
    
    . 
    movielens 
    . 
    movies 
    ` 
    ) 
     
    SELECT 
     
    id 
    , 
     
    "default_schema" 
     
    as 
     
    schemaId 
    , 
     
    null 
     
    as 
     
    parentDocumentId 
    , 
     
    TO_JSON_STRING 
    ( 
    STRUCT 
    ( 
    title 
     
    as 
     
    title 
    , 
     
    categories 
     
    as 
     
    categories 
    , 
     
    CONCAT 
    ( 
    "http://mytestdomain.movie/content/" 
    , 
     
    id 
    ) 
     
    as 
     
    uri 
    , 
     
    "2023-01-01T00:00:00Z" 
     
    as 
     
    available_time 
    , 
     
    "2033-01-01T00:00:00Z" 
     
    as 
     
    expire_time 
    , 
     
    "movie" 
     
    as 
     
    media_type 
    )) 
     
    as 
     
    jsonData 
     
    FROM 
     
    t 
    ; 
    ' 
     
   \ movielens 
    . 
    movies_view 
    
   

   Now the new view has the schema that the Vertex AI Agent Builder API expects.

2. Go to the BigQuerypage in Google Cloud console.

   Go to BigQuery

3. In the Explorerpane, expand your project name, expand the movielens dataset and click movies_view to open the query page for this view.

   

4. Go to the Table explorertab.

5. In the Generated querypane, click the Copy to querybutton. The query editor opens.

6. Click Runto see movie data in the view that you created.

7. Create fictitious user events from movie ratings by running the following Cloud Shell command:

    bq mk --project_id= PROJECT_ID 
   \
    --use_legacy_sql=false \
    --view '
    WITH t AS (
     SELECT
       MIN(UNIX_SECONDS(time)) AS old_start,
       MAX(UNIX_SECONDS(time)) AS old_end,
       UNIX_SECONDS(TIMESTAMP_SUB(
       CURRENT_TIMESTAMP(), INTERVAL 90 DAY)) AS new_start,
       UNIX_SECONDS(CURRENT_TIMESTAMP()) AS new_end
     FROM ` PROJECT_ID 
   .movielens.ratings` 
   )
     SELECT
       CAST(userId AS STRING) AS userPseudoId,
       "view-item" AS eventType,
       FORMAT_TIMESTAMP("%Y-%m-%dT%X%Ez",
       TIMESTAMP_SECONDS(CAST(
         (t.new_start + (UNIX_SECONDS(time) - t.old_start) *
         (t.new_end - t.new_start) / (t.old_end - t.old_start))
       AS int64))) AS eventTime,
       [STRUCT(movieId AS id, null AS name)] AS documents,
     FROM ` PROJECT_ID 
   .movielens.ratings` 
   , t
     WHERE rating >= 4;' \
     movielens.user_events 
   

Activate Vertex AI Agent Builder

1. In the Google Cloud console, go to the Agent Builderpage.

   Agent Builder

2. Read and agree to the Terms of Service, then click Continue and activate the API.

Create an app for media search

The procedures in this section guide you through creating and deploying a media search app.

1. In the Google Cloud console, go to the Agent Builderpage.

   Agent Builder

2. Click Create app .

3. On the Create apppage, select Search.

4. Under Content, click Media.

5. In the Your app namefield, enter a name for your app such as quickstart-media-search . Your app ID appears under the engine name.

6. Click Continue.

7. If you completed the Get started with media recommendations tutorial and you still have the data store (suggested name quickstart-media-data-store ), then select it, click Create, and skip to Preview search .

8. If you don't have a data store that contains the movielens dataset, create a new data store and select it:

   1. On the Data Storespage, click Create data store.

   2. Enter a display name for your data store, such as quickstart-media-data-store , and then click Create.

   3. Select the data store you just created, and then click Createto create your app. You will be redirected to the Select a data sourcepage.

Import data

Next, import the movies and user events data that were formatted earlier.

Import documents

1. If you are not automatically redirected to the Select a data sourcepage:

   • Open the Documentstab.
   • Click Import Data.

2. On the Select a data sourcepage, select BigQuery.

3. Enter the name of the movies BigQuery view you created and click Import.

     PROJECT_ID 
   .movielens.movies_view 
   

4. Wait until all documents have been imported, which should take about 15 minutes. There should be 86537 documents when complete.

   You can check the Activitytab for the import operation status. When the import is complete, the import operation status changes to Completed.

Import user events

1. Open the Eventstab.

2. Click Import Events.

3. Select BigQuery.

4. Enter the name of the user_events BigQuery view you created and click Import.

     PROJECT_ID 
   .movielens.user_events 
   

5. You can proceed to the next step before the events are imported, but the search results won't yet contain the full dataset.

   You can check the Activitytab for the operation status. The process takes about an hour to complete because you are importing millions of rows.

Preview and configure search

1. In the navigation menu, click Configurations .

2. In the Search herebox, type the name of a movie, such as "The Lord of the Rings".

3. Notice that the search results are relevant to the movie title entered.

4. On this page, you can customize how the search widget displays the search result information. See Configure results for the search widget to learn more.

   For media search apps, you can:

   • Configure fields for search
   • Configure autocomplete
   • Configure search results

   After making changes click Save and publishto update the widget.

Deploy the search widget

1. In the navigation menu, click Integration.

2. Make sure the Widgettab is selected.

3. Select JWT or OAuth basedas the widget authorization type.

4. In the Domainfield, enter the domain name for web page where you will put the widget. For example, if you are going to copy the widget to the web page example.com/ai.html , enter example.com as the domain.

5. Click Add, and then click Save.

6. Copy the code snippet provided in the Copy the following code to your web applicationsection.

7. In your codebase, generate an authorization token.

8. To pass the authorization token to your widget, use the "Set authorization token" code snippet provided in the Copy the following code to your web applicationsection and replace the text <JWT or OAuth token provided by you backend> with your authorization token.

9. For help integrating the search app into your web app, see the code samples at Get search results .