To set up online serving, you need to first create an online store instance forBigtable online serving or Optimized online serving.To understand the differences between Bigtable online serving and Optimized online serving,seeOnline serving types.

Note that you can't change the type of online serving after you chooseBigtable online serving or Optimized online serving while creatingyour online store. However, you can change the serving endpoint configurationfor an online store instance created for Optimized online serving.

After you create the online store, you canadd feature viewsand associate those feature views with feature data sources in BigQuery.

You can encrypt your online store instance by specifying acustomer-managed encryption key (CMEK)when you create your online store instance.Only Bigtable online serving supports encryption using a CMEK.To learn more about the benefits of using a CMEK and to understand whethera CMEK is useful for your online store, seeBenefits of CMEK.

Using a CMEK can involve additional usage costs, depending on thetype of key being used. For more information about pricing, refer toCloud Key Management Service pricing.

Before you begin

Authenticate toVertex AI, unless you've done so already.

Select the tab for how you plan to use the samples on this page:

Create an online store for Bigtable online serving

When you use Bigtable online serving, you have the option to encrypt the online store using aCMEK.

Create an online store for Bigtable online serving without CMEK

To create an online store instance forBigtable online serving with autoscaling, without specifying a CMEK, usethe Google Cloud console or the REST API.

fromgoogle.cloudimportaiplatformfromvertexai.resources.previewimportfeature_storedefcreate_bigtable_feature_online_store_sample(project:str,location:str,feature_online_store_id:str,):aiplatform.init(project=project,location=location)fos=feature_store.FeatureOnlineStore.create_bigtable_store(feature_online_store_id)returnfos

POST https://LOCATION_ID-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION_ID/featureOnlineStores?feature_online_store_id=FEATUREONLINESTORE_NAME

{  "bigtable": {    "auto_scaling": {      "min_node_count": 1,      "max_node_count": 3,      "cpu_utilization_target": 50    }  }}

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://LOCATION_ID-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION_ID/featureOnlineStores?feature_online_store_id=FEATUREONLINESTORE_NAME"

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://LOCATION_ID-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION_ID/featureOnlineStores?feature_online_store_id=FEATUREONLINESTORE_NAME" | Select-Object -Expand Content

{  "name": "projects/PROJECT_NUMBER/locations/LOCATION_ID/featureOnlineStores/FEATUREONLINESTORE_NAME/operations/OPERATION_ID",  "metadata": {    "@type": "type.googleapis.com/google.cloud.aiplatform.v1.CreateFeatureOnlineStoreOperationMetadata",    "genericMetadata": {      "createTime": "2023-09-18T17:49:23.847496Z",      "updateTime": "2023-09-18T17:49:23.847496Z"    }  }}

Create an online store that uses a CMEK

Use the following steps to create an online store instance forBigtable online serving that's encrypted with a CMEK.

Using a CMEK encryption can involve additional usage costs, depending on thetype of key being used. For more information about pricing, refer toCloud Key Management Service pricing.

1. Use Cloud Key Management Service to configure a customer-managed encryptionkey.

2. To create aFeatureOnlineStoreresource, send the followingPOST request by using thefeatureOnlineStores.createmethod and specifying the CMEK.

   Before using any of the request data, make the following replacements:

   • LOCATION_ID: Region where you want to create the online store, such asus-central1.
   • PROJECT_ID: Your project ID.
   • FEATUREONLINESTORE_NAME: The name of the new online store instance.
   • BOOLEAN: Optional: To create an online store that supports embedding management, entertrue. The default value isfalse.
   • KEY_NAME: The name of the encryption key that you want to use for this metadata store.

   HTTP method and URL:

   POST https://LOCATION_ID-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION_ID/featureOnlineStores?feature_online_store_id=FEATUREONLINESTORE_NAME

   Request JSON body:

   {  "bigtable": {    "auto_scaling": {      "min_node_count": 1,      "max_node_count": 3,      "cpu_utilization_target": 50    }  },  "encryption_spec": {    "kms_key_name": "KEY_NAME"  }}

   To send your request, choose one of these options:

   curl

   Note: The following command assumes that you have logged in to thegcloud CLI with your user account by runninggcloud init orgcloud auth login , or by usingCloud Shell, which automatically logs you into thegcloud CLI . You can check the currently active account by runninggcloud auth list.

   Save the request body in a file namedrequest.json, and execute the following command:

   curl -X POST \
        -H "Authorization: Bearer $(gcloud auth print-access-token)" \
        -H "Content-Type: application/json; charset=utf-8" \
        -d @request.json \
        "https://LOCATION_ID-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION_ID/featureOnlineStores?feature_online_store_id=FEATUREONLINESTORE_NAME"

   PowerShell

   Note: The following command assumes that you have logged in to thegcloud CLI with your user account by runninggcloud init orgcloud auth login . You can check the currently active account by runninggcloud auth list.

   Save the request body in a file namedrequest.json, and execute the following command:

   $cred = gcloud auth print-access-token
   $headers = @{ "Authorization" = "Bearer $cred" }
   
   Invoke-WebRequest `
       -Method POST `
       -Headers $headers `
       -ContentType: "application/json; charset=utf-8" `
       -InFile request.json `
       -Uri "https://LOCATION_ID-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION_ID/featureOnlineStores?feature_online_store_id=FEATUREONLINESTORE_NAME" | Select-Object -Expand Content

   You should receive a JSON response similar to the following:

   {  "name": "projects/PROJECT_NUMBER/locations/LOCATION_ID/featureOnlineStores/FEATUREONLINESTORE_NAME/operations/OPERATION_ID",  "metadata": {    "@type": "type.googleapis.com/google.cloud.aiplatform.v1.CreateFeatureOnlineStoreOperationMetadata",    "genericMetadata": {      "createTime": "2023-09-18T17:49:23.847496Z",      "updateTime": "2023-09-18T17:49:23.847496Z"    }  }}

Create an online store for Optimized online serving

When you use Optimized online serving, you can configure the online storeto serve features from either a public endpoint or a dedicatedPrivate Service Connect endpoint. Use aPrivate Service Connect endpoint if you want to serve featureswithin a VPC network at lower latencies than a public endpoint.

Create an online store for Optimized online serving with a public endpoint

Use the following samples to create an online store for Optimized online serving with a public endpoint.

fromgoogle.cloudimportaiplatformfromvertexai.resources.previewimportfeature_storedefcreate_optimized_public_feature_online_store_sample(project:str,location:str,feature_online_store_id:str,):aiplatform.init(project=project,location=location)fos=feature_store.FeatureOnlineStore.create_optimized_store(feature_online_store_id)returnfos

POST https://LOCATION_ID-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION_ID/featureOnlineStores?feature_online_store_id=FEATUREONLINESTORE_NAME

{  "optimized": {}}

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://LOCATION_ID-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION_ID/featureOnlineStores?feature_online_store_id=FEATUREONLINESTORE_NAME"

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://LOCATION_ID-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION_ID/featureOnlineStores?feature_online_store_id=FEATUREONLINESTORE_NAME" | Select-Object -Expand Content

{  "name": "projects/PROJECT_NUMBER/locations/LOCATION_ID/featureOnlineStores/FEATUREONLINESTORE_NAME/operations/OPERATION_ID",  "metadata": {    "@type": "type.googleapis.com/google.cloud.aiplatform.v1.CreateFeatureOnlineStoreOperationMetadata",    "genericMetadata": {      "createTime": "2023-09-18T17:49:23.847496Z",      "updateTime": "2023-09-18T17:49:23.847496Z"    }  }}

Create an online store for Optimized online serving with a Private Service Connect endpoint

Use the following samples to create an online store for Optimized online serving withPrivate Service Connect.

fromtypingimportListfromgoogle.cloudimportaiplatformfromvertexai.resources.previewimportfeature_storedefcreate_optimized_private_feature_online_store_sample(project:str,location:str,feature_online_store_id:str,project_allowlist:List[str],):aiplatform.init(project=project,location=location)fos=feature_store.FeatureOnlineStore.create_optimized_store(name=feature_online_store_id,enable_private_service_connect=True,project_allowlist=project_allowlist,)returnfos

POST https://LOCATION_ID-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION_ID/featureOnlineStores?feature_online_store_id=FEATUREONLINESTORE_NAME

{  "optimized": {},  "dedicated_serving_endpoint": {    "private_service_connect_config": {      "enable_private_service_connect": true,      "project_allowlist": ["PROJECT_NAMES"]    }  }}

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://LOCATION_ID-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION_ID/featureOnlineStores?feature_online_store_id=FEATUREONLINESTORE_NAME"

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://LOCATION_ID-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION_ID/featureOnlineStores?feature_online_store_id=FEATUREONLINESTORE_NAME" | Select-Object -Expand Content

{  "name": "projects/PROJECT_NUMBER/locations/LOCATION_ID/featureOnlineStores/FEATUREONLINESTORE_NAME/operations/OPERATION_ID",  "metadata": {    "@type": "type.googleapis.com/google.cloud.aiplatform.v1.CreateFeatureOnlineStoreOperationMetadata",    "genericMetadata": {      "createTime": "2023-09-18T17:49:23.847496Z",      "updateTime": "2023-09-18T17:49:23.847496Z"    }  }}

What's next

• Learn how tocreate a feature view.

• Learn how toupdate an online store.