Deploy and manage index endpoints in a VPC network

Deploying an index to an endpoint includes the following three tasks:

Create an IndexEndpoint if needed, or reuse an existing IndexEndpoint.
Get the IndexEndpoint ID.
Deploy the index to the IndexEndpoint.

Create an `IndexEndpoint` within your VPC network

If you are deploying an Index to an existing IndexEndpoint, you can skip this step.

Before you use an index to serve online vector matching queries, you must deploy the Index to an IndexEndpoint within your VPC Network Peering network. The first step is to create an IndexEndpoint. You can deploy more than one index to an IndexEndpoint that shares the same VPC network.

gcloud

The following example uses the gcloud ai index-endpoints create command.

Before using any of the command data below, make the following replacements:

INDEX_ENDPOINT_NAME: Display name of the index endpoint.
VPC_NETWORK_NAME: The Google Compute Engine network name to which the index endpoint should be peered.
LOCATION: The region where you are using Vertex AI.
PROJECT_ID: Your Google Cloud project ID.

Execute the following command:

Linux, macOS, or Cloud Shell

gcloud ai index-endpoints create \
    --display-name=INDEX_ENDPOINT_NAME \
    --network=VPC_NETWORK_NAME \
    --region=LOCATION \
    --project=PROJECT_ID

Windows (PowerShell)

gcloud ai index-endpoints create `
    --display-name=INDEX_ENDPOINT_NAME `
    --network=VPC_NETWORK_NAME `
    --region=LOCATION `
    --project=PROJECT_ID

Windows (cmd.exe)

gcloud ai index-endpoints create ^
    --display-name=INDEX_ENDPOINT_NAME ^
    --network=VPC_NETWORK_NAME ^
    --region=LOCATION ^
    --project=PROJECT_ID

You should receive a response similar to the following:

The Google Cloud CLI tool might take a few minutes to create the IndexEndpoint.

REST

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

INDEX_ENDPOINT_NAME: Display name of the index endpoint.
VPC_NETWORK_NAME: The Google Compute Engine network name to which the index endpoint should be peered.
LOCATION: The region where you are using Vertex AI.
PROJECT_ID: Your Google Cloud project ID.
PROJECT_NUMBER: Your project's automatically generated project number.

HTTP method and URL:

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/indexEndpoints

Request JSON body:

{
  "display_name": "INDEX_ENDPOINT_NAME",
  "network": "VPC_NETWORK_NAME"
}

To send your request, expand one of these options:

curl (Linux, macOS, or Cloud Shell)

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

Save the request body in a file named request.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-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/indexEndpoints"

PowerShell (Windows)

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

Save the request body in a file named request.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-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/indexEndpoints" | Select-Object -Expand Content

You should receive a JSON response similar to the following:

{
  "name": "projects/PROJECT_NUMBER/locations/LOCATION/indexEndpoints/INDEX_ENDPOINT_ID/operations/OPERATION_ID",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.aiplatform.v1.CreateIndexEndpointOperationMetadata",
    "genericMetadata": {
      "createTime": "2022-01-13T04:09:56.641107Z",
      "updateTime": "2022-01-13T04:09:56.641107Z"
    }
  }
}

You can poll for the status of the operation until the response includes "done": true.

Python

To learn how to install or update the Vertex AI SDK for Python, see Install the Vertex AI SDK for Python. For more information, see the Python API reference documentation.

def vector_search_create_index_endpoint_vpc(
    project: str, location: str, display_name: str, network: str
) -> aiplatform.MatchingEngineIndexEndpoint:
    """Create a vector search index endpoint within a VPC network.

    Args:
        project (str): Required. Project ID
        location (str): Required. The region name
        display_name (str): Required. The index endpoint display name
        network(str): Required. The VPC network name, in the format of
            projects/{project number}/global/networks/{network name}.

    Returns:
        aiplatform.MatchingEngineIndexEndpoint - The created index endpoint.
    """
    # Initialize the Vertex AI client
    aiplatform.init(project=project, location=location)

    # Create Index Endpoint
    index_endpoint = aiplatform.MatchingEngineIndexEndpoint.create(
        display_name=display_name,
        network=network,
        description="Matching Engine VPC Index Endpoint",
    )

    return index_endpoint

Console

Use these instructions to create an index endpoint.

In the Vertex AI section of the Google Cloud console, go to the Deploy and Use section. Select Vector Search
Go to Vector Search
A list of your active indexes is displayed.
On the top of the page, select the Index endpoints tab. Your index endpoints are displayed.
Click Create new index endpoint. The Create a new index endpoint panel opens.
Enter a display name for the index endpoint.
In the Region field, select a region from the drop-down.
In the Access field, select Private.
Enter your peered VPC network details. Enter the full name of the Compute Engine network to which the job should be peered. The format should be projects/{project_num}/global/networks/{network_id}
Click Create.

Deploy an index

gcloud

This example uses the gcloud ai index-endpoints deploy-index command.

Before using any of the command data below, make the following replacements:

INDEX_ENDPOINT_ID: The ID of the index endpoint.
DEPLOYED_INDEX_ID: A user specified string to uniquely identify the deployed index. It must start with a letter and contain only letters, numbers or underscores. See DeployedIndex.id for format guidelines.
DEPLOYED_INDEX_ENDPOINT_NAME: Display name of the deployed index endpoint.
INDEX_ID: The ID of the index.
LOCATION: The region where you are using Vertex AI.
PROJECT_ID: Your Google Cloud project ID.

Execute the following command:

Linux, macOS, or Cloud Shell

gcloud ai index-endpoints deploy-index INDEX_ENDPOINT_ID \
    --deployed-index-id=DEPLOYED_INDEX_ID \
    --display-name=DEPLOYED_INDEX_ENDPOINT_NAME \
    --index=INDEX_ID \
    --region=LOCATION \
    --project=PROJECT_ID

Windows (PowerShell)

gcloud ai index-endpoints deploy-index INDEX_ENDPOINT_ID `
    --deployed-index-id=DEPLOYED_INDEX_ID `
    --display-name=DEPLOYED_INDEX_ENDPOINT_NAME `
    --index=INDEX_ID `
    --region=LOCATION `
    --project=PROJECT_ID

Windows (cmd.exe)

gcloud ai index-endpoints deploy-index INDEX_ENDPOINT_ID ^
    --deployed-index-id=DEPLOYED_INDEX_ID ^
    --display-name=DEPLOYED_INDEX_ENDPOINT_NAME ^
    --index=INDEX_ID ^
    --region=LOCATION ^
    --project=PROJECT_ID

You should receive a response similar to the following:

The Google Cloud CLI tool might take a few minutes to create the IndexEndpoint.

REST

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

INDEX_ENDPOINT_ID: The ID of the index endpoint.
DEPLOYED_INDEX_ID: A user specified string to uniquely identify the deployed index. It must start with a letter and contain only letters, numbers or underscores. See DeployedIndex.id for format guidelines.
DEPLOYED_INDEX_ENDPOINT_NAME: Display name of the deployed index endpoint.
INDEX_ID: The ID of the index.
LOCATION: The region where you are using Vertex AI.
PROJECT_ID: Your Google Cloud project ID.
PROJECT_NUMBER: Your project's automatically generated project number.

HTTP method and URL:

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/indexEndpoints/INDEX_ENDPOINT_ID:deployIndex

Request JSON body:

{
 "deployedIndex": {
   "id": "DEPLOYED_INDEX_ID",
   "index": "projects/PROJECT_ID/locations/LOCATION/indexes/INDEX_ID",
   "displayName": "DEPLOYED_INDEX_ENDPOINT_NAME"
 }
}

To send your request, expand one of these options:

curl (Linux, macOS, or Cloud Shell)

Save the request body in a file named request.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-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/indexEndpoints/INDEX_ENDPOINT_ID:deployIndex"

PowerShell (Windows)

Save the request body in a file named request.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-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/indexEndpoints/INDEX_ENDPOINT_ID:deployIndex" | Select-Object -Expand Content

You should receive a JSON response similar to the following:

{
 "name": "projects/PROJECT_NUMBER/locations/LOCATION/indexEndpoints/INDEX_ENDPOINT_ID/operations/OPERATION_ID",
 "metadata": {
   "@type": "type.googleapis.com/google.cloud.aiplatform.v1.DeployIndexOperationMetadata",
   "genericMetadata": {
     "createTime": "2022-10-19T17:53:16.502088Z",
     "updateTime": "2022-10-19T17:53:16.502088Z"
   },
   "deployedIndexId": "DEPLOYED_INDEX_ID"
 }
}

Python

To learn how to install or update the Vertex AI SDK for Python, see Install the Vertex AI SDK for Python. For more information, see the Python API reference documentation.

def vector_search_deploy_index(
    project: str,
    location: str,
    index_name: str,
    index_endpoint_name: str,
    deployed_index_id: str,
) -> None:
    """Deploy a vector search index to a vector search index endpoint.

    Args:
        project (str): Required. Project ID
        location (str): Required. The region name
        index_name (str): Required. The index to update. A fully-qualified index
          resource name or a index ID.  Example:
          "projects/123/locations/us-central1/indexes/my_index_id" or
          "my_index_id".
        index_endpoint_name (str): Required. Index endpoint to deploy the index
          to.
        deployed_index_id (str): Required. The user specified ID of the
          DeployedIndex.
    """
    # Initialize the Vertex AI client
    aiplatform.init(project=project, location=location)

    # Create the index instance from an existing index
    index = aiplatform.MatchingEngineIndex(index_name=index_name)

    # Create the index endpoint instance from an existing endpoint.
    index_endpoint = aiplatform.MatchingEngineIndexEndpoint(
        index_endpoint_name=index_endpoint_name
    )

    # Deploy Index to Endpoint
    index_endpoint = index_endpoint.deploy_index(
        index=index, deployed_index_id=deployed_index_id
    )

    print(index_endpoint.deployed_indexes)

Console

Use these instructions to deploy your index to an endpoint.

In the Vertex AI section of the Google Cloud console, go to the Deploy and Use section. Select Vector Search
Go to Vector Search
A list of your active indexes is displayed.
Select the name of the index you want to deploy. The index details page opens.
From the index details page, click Deploy to endpoint. The index deployment panel opens.
Enter a display name - this name acts as an ID and can't be updated.
From the Endpoint drop-down, select the endpoint you want to deploy this index to. Note: The endpoint is unavailable if the index is already deployed to it.
Optional: In the Machine type field, select either standard or high-memory.
Optional. Select Enable autoscaling to automatically resize the number of nodes based on the demands of your workloads. The default number of replicas is 2 if autoscaling is disabled.
Click Deploy to deploy your index to the endpoint. Note: It takes around 30 minutes to be deployed.

Enable autoscaling

Vector Search supports autoscaling, which can automatically resize the number of nodes based on the demands of your workloads. When demand is high, nodes are added to the node pool, which won't exceed the maximum size you designate. When demand is low, the node pool scales back down to a minimum size that you designate. You can check the actual nodes in use and the changes by monitoring the current replicas.

To enable autoscaling, specify the maxReplicaCount and minReplicaCount when you deploy your index:

gcloud

The following example uses the gcloud ai index-endpoints deploy-index command.

Before using any of the command data below, make the following replacements:

INDEX_ENDPOINT_ID: The ID of the index endpoint.
DEPLOYED_INDEX_ID: A user specified string to uniquely identify the deployed index. It must start with a letter and contain only letters, numbers or underscores. See DeployedIndex.id for format guidelines.
DEPLOYED_INDEX_NAME: Display name of the deployed index.
INDEX_ID: The ID of the index.
MIN_REPLICA_COUNT: Minimum number of machine replicas the deployed index will be always deployed on. If specified, the value must be equal to or larger than 1.
MAX_REPLICA_COUNT: Maximum number of machine replicas the deployed index could be deployed on.
LOCATION: The region where you are using Vertex AI.
PROJECT_ID: Your Google Cloud project ID.

Execute the following command:

Linux, macOS, or Cloud Shell

gcloud ai index-endpoints deploy-index INDEX_ENDPOINT_ID \
    --deployed-index-id=DEPLOYED_INDEX_ID \
    --display-name=DEPLOYED_INDEX_NAME \
    --index=INDEX_ID \
    --min-replica-count=MIN_REPLICA_COUNT \
    --max-replica-count=MAX_REPLICA_COUNT \
    --region=LOCATION \
    --project=PROJECT_ID

Windows (PowerShell)

gcloud ai index-endpoints deploy-index INDEX_ENDPOINT_ID `
    --deployed-index-id=DEPLOYED_INDEX_ID `
    --display-name=DEPLOYED_INDEX_NAME `
    --index=INDEX_ID `
    --min-replica-count=MIN_REPLICA_COUNT `
    --max-replica-count=MAX_REPLICA_COUNT `
    --region=LOCATION `
    --project=PROJECT_ID

Windows (cmd.exe)

gcloud ai index-endpoints deploy-index INDEX_ENDPOINT_ID ^
    --deployed-index-id=DEPLOYED_INDEX_ID ^
    --display-name=DEPLOYED_INDEX_NAME ^
    --index=INDEX_ID ^
    --min-replica-count=MIN_REPLICA_COUNT ^
    --max-replica-count=MAX_REPLICA_COUNT ^
    --region=LOCATION ^
    --project=PROJECT_ID

REST

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

INDEX_ENDPOINT_ID: The ID of the index endpoint.
DEPLOYED_INDEX_ID: A user specified string to uniquely identify the deployed index. It must start with a letter and contain only letters, numbers or underscores. See DeployedIndex.id for format guidelines.
DEPLOYED_INDEX_NAME: Display name of the deployed index.
INDEX_ID: The ID of the index.
MIN_REPLICA_COUNT: Minimum number of machine replicas the deployed index will be always deployed on. If specified, the value must be equal to or larger than 1.
MAX_REPLICA_COUNT: Maximum number of machine replicas the deployed index could be deployed on.
LOCATION: The region where you are using Vertex AI.
PROJECT_ID: Your Google Cloud project ID.
PROJECT_NUMBER: Your project's automatically generated project number.

HTTP method and URL:

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/indexEndpoints/INDEX_ENDPOINT_ID:deployIndex

Request JSON body:

{
 "deployedIndex": {
   "id": "DEPLOYED_INDEX_ID",
   "index": "projects/PROJECT_NUMBER/locations/LOCATION/indexes/INDEX_ID",
   "displayName": "DEPLOYED_INDEX_NAME",
   "automaticResources": {
     "minReplicaCount": MIN_REPLICA_COUNT,
     "maxReplicaCount": MAX_REPLICA_COUNT
   }
 }
}

To send your request, expand one of these options:

curl (Linux, macOS, or Cloud Shell)

Save the request body in a file named request.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-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/indexEndpoints/INDEX_ENDPOINT_ID:deployIndex"

PowerShell (Windows)

Save the request body in a file named request.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-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/indexEndpoints/INDEX_ENDPOINT_ID:deployIndex" | Select-Object -Expand Content

You should receive a JSON response similar to the following:

{
 "name": "projects/PROJECT_NUMBER/locations/LOCATION/indexEndpoints/INDEX_ENDPOINT_ID/operations/OPERATION_ID",
 "metadata": {
   "@type": "type.googleapis.com/google.cloud.aiplatform.v1.DeployIndexOperationMetadata",
   "genericMetadata": {
     "createTime": "2023-10-19T17:53:16.502088Z",
     "updateTime": "2023-10-19T17:53:16.502088Z"
   },
   "deployedIndexId": "DEPLOYED_INDEX_ID"
 }
}

Python

To learn how to install or update the Vertex AI SDK for Python, see Install the Vertex AI SDK for Python. For more information, see the Python API reference documentation.

def vector_search_deploy_autoscaling_index(
    project: str,
    location: str,
    index_name: str,
    index_endpoint_name: str,
    deployed_index_id: str,
    min_replica_count: int,
    max_replica_count: int,
) -> None:
    """Deploy a vector search index to a vector search index endpoint.

    Args:
        project (str): Required. Project ID
        location (str): Required. The region name
        index_name (str): Required. The index to update. A fully-qualified index
          resource name or a index ID.  Example:
          "projects/123/locations/us-central1/indexes/my_index_id" or
          "my_index_id".
        index_endpoint_name (str): Required. Index endpoint to deploy the index
          to.
        deployed_index_id (str): Required. The user specified ID of the
          DeployedIndex.
        min_replica_count (int): Required. The minimum number of replicas to
          deploy.
        max_replica_count (int): Required. The maximum number of replicas to
          deploy.
    """
    # Initialize the Vertex AI client
    aiplatform.init(project=project, location=location)

    # Create the index instance from an existing index
    index = aiplatform.MatchingEngineIndex(index_name=index_name)

    # Create the index endpoint instance from an existing endpoint.
    index_endpoint = aiplatform.MatchingEngineIndexEndpoint(
        index_endpoint_name=index_endpoint_name
    )

    # Deploy Index to Endpoint. Specifying min and max replica counts will
    # enable autoscaling.
    index_endpoint.deploy_index(
        index=index,
        deployed_index_id=deployed_index_id,
        min_replica_count=min_replica_count,
        max_replica_count=max_replica_count,
    )

Console

You can only enable autoscaling from the console during index deployment.

In the Vertex AI section of the Google Cloud console, go to the Deploy and Use section. Select Vector Search
Go to Vector Search
A list of your active indexes is displayed.
Select the name of the index you want to deploy. The index details page opens.
From the index details page, click Deploy to endpoint. The index deployment panel opens.
Enter a display name - this name acts as an ID and can't be updated.
From the Endpoint drop-down, select the endpoint you want to deploy this index to. Note: The endpoint is unavailable if the index is already deployed to it.
Optional: In the Machine type field, select either standard or high-memory.
Optional. Select Enable autoscaling to automatically resize the number of nodes based on the demands of your workloads. The default number of replicas is 2 if autoscaling is disabled.

If both minReplicaCount and maxReplicaCount are not set, they are set to 2 by default.
If only maxReplicaCount is set, minReplicaCount is set to 2 by default.
If only minReplicaCount is set, maxReplicaCount is set to equal minReplicaCount.

Mutate a `DeployedIndex`

You can use MutateDeployedIndex API to update the deployment resources (for example, minReplicaCount and maxReplicaCount) of an already deployed index.

Users are not allowed to change the machineType after the index is deployed.
If maxReplicaCount is not specified in the request, the DeployedIndex will keep using the existing maxReplicaCount.

gcloud

The following example uses the gcloud ai index-endpoints mutate-deployed-index command.

Before using any of the command data below, make the following replacements:

INDEX_ENDPOINT_ID: The ID of the index endpoint.
DEPLOYED_INDEX_ID: A user specified string to uniquely identify the deployed index. It must start with a letter and contain only letters, numbers or underscores. See DeployedIndex.id for format guidelines.
MIN_REPLICA_COUNT: Minimum number of machine replicas the deployed index will be always deployed on. If specified, the value must be equal to or larger than 1.
MAX_REPLICA_COUNT: Maximum number of machine replicas the deployed index could be deployed on.
LOCATION: The region where you are using Vertex AI.
PROJECT_ID: Your Google Cloud project ID.

Execute the following command:

Linux, macOS, or Cloud Shell

gcloud ai index-endpoints mutate-deployed-index INDEX_ENDPOINT_ID \
    --deployed-index-id=DEPLOYED_INDEX_ID \
    --min-replica-count=MIN_REPLICA_COUNT \
    --max-replica-count=MAX_REPLICA_COUNT \
    --region=LOCATION \
    --project=PROJECT_ID

Windows (PowerShell)

gcloud ai index-endpoints mutate-deployed-index INDEX_ENDPOINT_ID `
    --deployed-index-id=DEPLOYED_INDEX_ID `
    --min-replica-count=MIN_REPLICA_COUNT `
    --max-replica-count=MAX_REPLICA_COUNT `
    --region=LOCATION `
    --project=PROJECT_ID

Windows (cmd.exe)

gcloud ai index-endpoints mutate-deployed-index INDEX_ENDPOINT_ID ^
    --deployed-index-id=DEPLOYED_INDEX_ID ^
    --min-replica-count=MIN_REPLICA_COUNT ^
    --max-replica-count=MAX_REPLICA_COUNT ^
    --region=LOCATION ^
    --project=PROJECT_ID

REST

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

INDEX_ENDPOINT_ID: The ID of the index endpoint.
DEPLOYED_INDEX_ID: A user specified string to uniquely identify the deployed index. It must start with a letter and contain only letters, numbers or underscores. See DeployedIndex.id for format guidelines.
MIN_REPLICA_COUNT: Minimum number of machine replicas the deployed index will be always deployed on. If specified, the value must be equal to or larger than 1.
MAX_REPLICA_COUNT: Maximum number of machine replicas the deployed index could be deployed on.
LOCATION: The region where you are using Vertex AI.
PROJECT_ID: Your Google Cloud project ID.
PROJECT_NUMBER: Your project's automatically generated project number.

HTTP method and URL:

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/indexEndpoints/INDEX_ENDPOINT_ID:mutateDeployedIndex

Request JSON body:

{
"deployedIndex": {
  "id": "DEPLOYED_INDEX_ID",
  "index": "projects/PROJECT_ID/locations/LOCATION/indexes/INDEX_ID",
  "displayName": "DEPLOYED_INDEX_NAME"
}
}

To send your request, expand one of these options:

curl (Linux, macOS, or Cloud Shell)

Save the request body in a file named request.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-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/indexEndpoints/INDEX_ENDPOINT_ID:mutateDeployedIndex"

PowerShell (Windows)

Save the request body in a file named request.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-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/indexEndpoints/INDEX_ENDPOINT_ID:mutateDeployedIndex" | Select-Object -Expand Content

You should receive a JSON response similar to the following:

{
"name": "projects/PROJECT_NUMBER/locations/LOCATION/indexEndpoints/INDEX_ENDPOINT_ID/operations/OPERATION_ID",
"metadata": {
  "@type": "type.googleapis.com/google.cloud.aiplatform.v1.DeployIndexOperationMetadata",
  "genericMetadata": {
    "createTime": "2020-10-19T17:53:16.502088Z",
    "updateTime": "2020-10-19T17:53:16.502088Z"
  },
  "deployedIndexId": "DEPLOYED_INDEX_ID"
}
}

Python

To learn how to install or update the Vertex AI SDK for Python, see Install the Vertex AI SDK for Python. For more information, see the Python API reference documentation.

def vector_search_mutate_deployed_index(
    project: str,
    location: str,
    index_endpoint_name: str,
    deployed_index_id: str,
    min_replica_count: int,
    max_replica_count: int,
) -> None:
    """Mutate the deployment resources of an already deployed index.

    Args:
        project (str): Required. Project ID
        location (str): Required. The region name
        index_endpoint_name (str): Required. Index endpoint to run the query
          against.
        deployed_index_id (str): Required. The ID of the DeployedIndex to run
          the queries against.
        min_replica_count (int): Required. The minimum number of replicas to
          deploy.
        max_replica_count (int): Required. The maximum number of replicas to
          deploy.
    """
    # Initialize the Vertex AI client
    aiplatform.init(project=project, location=location)

    # Create the index endpoint instance from an existing endpoint
    index_endpoint = aiplatform.MatchingEngineIndexEndpoint(
        index_endpoint_name=index_endpoint_name
    )

    # Mutate the deployed index
    index_endpoint.mutate_deployed_index(
        deployed_index_id=deployed_index_id,
        min_replica_count=min_replica_count,
        max_replica_count=max_replica_count,
    )

Deployment settings that impact performance

The following deployment settings can affect latency, availability, and cost when using Vector Search. This guidance applies to most cases. However, always experiment with your configurations to make sure that they work for your use case.

Setting Performance impact

Machine type

Setting	Performance impact
Machine type	The hardware selection has a direct interaction with the shard size selected. Depending on shard choices you specified at index creation time, each machine type offers a tradeoff between performance and cost. Reference the pricing page to determine the hardware available and pricing. In general, performance increases in the following order: E2 standard E2 highmem N1 standard N2D standard
Minimum replica count	`minReplicaCount` reserves a minimum capacity for availability and latency to ensure that the system doesn't have cold start issues when traffic scales up quickly from low levels. If you have workloads that drop to low levels and then quickly increase to higher levels, consider setting `minReplicaCount` to a number that can accommodate the initial bursts of traffic.
Maximum replica count	`maxReplicaCount` primarily lets you control usage cost. You can choose to prevent increasing costs beyond a certain threshold, with the tradeoff of allowing increased latency and reducing availability.

The hardware selection has a direct interaction with the shard size selected. Depending on shard choices you specified at index creation time, each machine type offers a tradeoff between performance and cost.

Reference the pricing page to determine the hardware available and pricing. In general, performance increases in the following order:

E2 standard
E2 highmem
N1 standard
N2D standard

Minimum replica count

minReplicaCount reserves a minimum capacity for availability and latency to ensure that the system doesn't have cold start issues when traffic scales up quickly from low levels.

If you have workloads that drop to low levels and then quickly increase to higher levels, consider setting minReplicaCount to a number that can accommodate the initial bursts of traffic.

Maximum replica count maxReplicaCount primarily lets you control usage cost. You can choose to prevent increasing costs beyond a certain threshold, with the tradeoff of allowing increased latency and reducing availability.

List `IndexEndpoints`

To list your IndexEndpoint resources and view the information of any associated DeployedIndex instances, run the following code:

gcloud

The following example uses the gcloud ai index-endpoints list command.

Before using any of the command data below, make the following replacements:

LOCATION: The region where you are using Vertex AI.
PROJECT_ID: Your Google Cloud project ID.

Execute the following command:

Linux, macOS, or Cloud Shell

gcloud ai index-endpoints list \
    --region=LOCATION \
    --project=PROJECT_ID

Windows (PowerShell)

gcloud ai index-endpoints list `
    --region=LOCATION `
    --project=PROJECT_ID

Windows (cmd.exe)

gcloud ai index-endpoints list ^
    --region=LOCATION ^
    --project=PROJECT_ID

REST

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

LOCATION: The region where you are using Vertex AI.
PROJECT_ID: Your Google Cloud project ID.
PROJECT_NUMBER: Your project's automatically generated project number.

HTTP method and URL:

GET https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/indexEndpoints

To send your request, expand one of these options:

curl (Linux, macOS, or Cloud Shell)

Execute the following command:

curl -X GET \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/indexEndpoints"

PowerShell (Windows)

Execute the following command:

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

Invoke-WebRequest `
    -Method GET `
    -Headers $headers `
    -Uri "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/indexEndpoints" | Select-Object -Expand Content

You should receive a JSON response similar to the following:

{
 "indexEndpoints": [
   {
     "name": "projects/PROJECT_NUMBER/locations/LOCATION/indexEndpoints/INDEX_ENDPOINT_ID",
     "displayName": "INDEX_ENDPOINT_DISPLAY_NAME",
     "deployedIndexes": [
       {
         "id": "DEPLOYED_INDEX_ID",
         "index": "projects/PROJECT_NUMBER/locations/LOCATION/indexes/INDEX_ID",
         "displayName": "DEPLOYED_INDEX_DISPLAY_NAME",
         "createTime": "2021-06-04T02:23:40.178286Z",
         "privateEndpoints": {
           "matchGrpcAddress": "GRPC_ADDRESS"
         },
         "indexSyncTime": "2022-01-13T04:22:00.151916Z",
         "automaticResources": {
           "minReplicaCount": 2,
           "maxReplicaCount": 10
         }
       }
     ],
     "etag": "AMEw9yP367UitPkLo-khZ1OQvqIK8Q0vLAzZVF7QjdZ5O3l7Zow-mzBo2l6xmiuuMljV",
     "createTime": "2021-03-17T04:47:28.460373Z",
     "updateTime": "2021-06-04T02:23:40.930513Z",
     "network": "VPC_NETWORK_NAME"
   }
 ]
}

Python

To learn how to install or update the Vertex AI SDK for Python, see Install the Vertex AI SDK for Python. For more information, see the Python API reference documentation.

def vector_search_list_index_endpoint(
    project: str, location: str
) -> List[aiplatform.MatchingEngineIndexEndpoint]:
    """List vector search index endpoints.

    Args:
        project (str): Required. Project ID
        location (str): Required. The region name

    Returns:
        List of aiplatform.MatchingEngineIndexEndpoint
    """
    # Initialize the Vertex AI client
    aiplatform.init(project=project, location=location)

    # List Index Endpoints
    return aiplatform.MatchingEngineIndexEndpoint.list()

Console

Use these instructions to view a list of your index endpoints.

In the Vertex AI section of the Google Cloud console, go to the Deploy and Use section. Select Vector Search
Go to Vector Search
On the top of the page, select the Index endpoint tab.
All of the existing index endpoints are displayed.

For more information, see the reference documentation for IndexEndpoint.

Undeploy an index

To undeploy an index, run the following code:

gcloud

The following example uses the gcloud ai index-endpoints undeploy-index command.

Before using any of the command data below, make the following replacements:

INDEX_ENDPOINT_ID: The ID of the index endpoint.
DEPLOYED_INDEX_ID: A user specified string to uniquely identify the deployed index. It must start with a letter and contain only letters, numbers or underscores. See DeployedIndex.id for format guidelines.
LOCATION: The region where you are using Vertex AI.
PROJECT_ID: Your Google Cloud project ID.

Execute the following command:

Linux, macOS, or Cloud Shell

gcloud ai index-endpoints undeploy-index INDEX_ENDPOINT_ID \
    --deployed-index-id=DEPLOYED_INDEX_ID \
    --region=LOCATION \
    --project=PROJECT_ID

Windows (PowerShell)

gcloud ai index-endpoints undeploy-index INDEX_ENDPOINT_ID `
    --deployed-index-id=DEPLOYED_INDEX_ID `
    --region=LOCATION `
    --project=PROJECT_ID

Windows (cmd.exe)

gcloud ai index-endpoints undeploy-index INDEX_ENDPOINT_ID ^
    --deployed-index-id=DEPLOYED_INDEX_ID ^
    --region=LOCATION ^
    --project=PROJECT_ID

REST

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

INDEX_ENDPOINT_ID: The ID of the index endpoint.
DEPLOYED_INDEX_ID: A user specified string to uniquely identify the deployed index. It must start with a letter and contain only letters, numbers or underscores. See DeployedIndex.id for format guidelines.
LOCATION: The region where you are using Vertex AI.
PROJECT_ID: Your Google Cloud project ID.
PROJECT_NUMBER: Your project's automatically generated project number.

HTTP method and URL:

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/indexEndpoints/INDEX_ENDPOINT_ID:undeployIndex

Request JSON body:

{
 "deployed_index_id": "DEPLOYED_INDEX_ID"
}

To send your request, expand one of these options:

curl (Linux, macOS, or Cloud Shell)

Save the request body in a file named request.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-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/indexEndpoints/INDEX_ENDPOINT_ID:undeployIndex"

PowerShell (Windows)

Save the request body in a file named request.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-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/indexEndpoints/INDEX_ENDPOINT_ID:undeployIndex" | Select-Object -Expand Content

You should receive a JSON response similar to the following:

{
 "name": "projects/PROJECT_NUMBER/locations/LOCATION/indexEndpoints/INDEX_ENDPOINT_ID/operations/OPERATION_ID",
 "metadata": {
   "@type": "type.googleapis.com/google.cloud.aiplatform.v1.UndeployIndexOperationMetadata",
   "genericMetadata": {
     "createTime": "2022-01-13T04:09:56.641107Z",
     "updateTime": "2022-01-13T04:09:56.641107Z"
   }
 }
}

Python

To learn how to install or update the Vertex AI SDK for Python, see Install the Vertex AI SDK for Python. For more information, see the Python API reference documentation.

def vector_search_undeploy_index(
    project: str,
    location: str,
    index_endpoint_name: str,
    deployed_index_id: str,
) -> None:
    """Mutate the deployment resources of an already deployed index.

    Args:
        project (str): Required. Project ID
        location (str): Required. The region name
        index_endpoint_name (str): Required. Index endpoint to run the query
          against.
        deployed_index_id (str): Required. The ID of the DeployedIndex to run
          the queries against.
    """
    # Initialize the Vertex AI client
    aiplatform.init(project=project, location=location)

    # Create the index endpoint instance from an existing endpoint
    index_endpoint = aiplatform.MatchingEngineIndexEndpoint(
        index_endpoint_name=index_endpoint_name
    )

    # Undeploy the index
    index_endpoint.undeploy_index(
        deployed_index_id=deployed_index_id,
    )

Console

Use these instructions to undeploy an index.

In the Vertex AI section of the Google Cloud console, go to the Deploy and Use section. Select Vector Search
Go to Vector Search
A list of your active indexes is displayed.
Select the index you want to undeploy. The index details page opens.
Under the Deployed indexes section, identify the index endpoint you want to undeploy.
Click the options menu that is in the same row as the index endpoint and select Undeploy.
A confirmation screen opens. Click Undeploy. Note: It can take up to 30 minutes to be undeployed.

Delete an `IndexEndpoint`

Before you delete an IndexEndpoint, you must undeploy all indexes deploy to the endpoint.

gcloud

The following example uses the gcloud ai index-endpoints delete command.

Before using any of the command data below, make the following replacements:

INDEX_ENDPOINT_ID: The ID of the index endpoint.
LOCATION: The region where you are using Vertex AI.
PROJECT_ID: Your Google Cloud project ID.

Execute the following command:

Linux, macOS, or Cloud Shell

gcloud ai index-endpoints delete INDEX_ENDPOINT_ID \
    --region=LOCATION \
    --project=PROJECT_ID

Windows (PowerShell)

gcloud ai index-endpoints delete INDEX_ENDPOINT_ID `
    --region=LOCATION `
    --project=PROJECT_ID

Windows (cmd.exe)

gcloud ai index-endpoints delete INDEX_ENDPOINT_ID ^
    --region=LOCATION ^
    --project=PROJECT_ID

REST

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

INDEX_ENDPOINT_ID: The ID of the index endpoint.
LOCATION: The region where you are using Vertex AI.
PROJECT_ID: Your Google Cloud project ID.
PROJECT_NUMBER: Your project's automatically generated project number.

HTTP method and URL:

DELETE https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/indexEndpoints/INDEX_ENDPOINT_ID

To send your request, expand one of these options:

curl (Linux, macOS, or Cloud Shell)

Execute the following command:

curl -X DELETE \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/indexEndpoints/INDEX_ENDPOINT_ID"

PowerShell (Windows)

Execute the following command:

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

Invoke-WebRequest `
    -Method DELETE `
    -Headers $headers `
    -Uri "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/indexEndpoints/INDEX_ENDPOINT_ID" | Select-Object -Expand Content

You should receive a JSON response similar to the following:

{
 "name": "projects/PROJECT_NUMBER/locations/LOCATION/indexEndpoints/INDEX_ENDPOINT_ID/operations/OPERATION_ID",
 "metadata": {
   "@type": "type.googleapis.com/google.cloud.aiplatform.v1.DeleteOperationMetadata",
   "genericMetadata": {
     "createTime": "2022-01-13T04:36:19.142203Z",
     "updateTime": "2022-01-13T04:36:19.142203Z"
   }
 },
 "done": true,
 "response": {
   "@type": "type.googleapis.com/google.protobuf.Empty"
 }
}

Python

To learn how to install or update the Vertex AI SDK for Python, see Install the Vertex AI SDK for Python. For more information, see the Python API reference documentation.

def vector_search_delete_index_endpoint(
    project: str, location: str, index_endpoint_name: str, force: bool = False
) -> None:
    """Delete a vector search index endpoint.

    Args:
        project (str): Required. Project ID
        location (str): Required. The region name
        index_endpoint_name (str): Required. Index endpoint to run the query
          against.
        force (bool): Required. If true, undeploy any deployed indexes on this
          endpoint before deletion.
    """
    # Initialize the Vertex AI client
    aiplatform.init(project=project, location=location)

    # Create the index endpoint instance from an existing endpoint
    index_endpoint = aiplatform.MatchingEngineIndexEndpoint(
        index_endpoint_name=index_endpoint_name
    )

    # Delete the index endpoint
    index_endpoint.delete(force=force)

Console

Use these instructions to delete an index endpoint.

In the Vertex AI section of the Google Cloud console, go to the Deploy and Use section. Select Vector Search
Go to Vector Search
On the top of the page, select the Index endpoints tab.
All of the existing index endpoints are displayed.
Click the options menu that is in the same row as the index endpoint you want to delete and select Delete.
A confirmation screen opens. Click Delete. Your index endpoint is now deleted.

Deploy and manage index endpoints in a VPC network

Create an IndexEndpoint within your VPC network

gcloud

Linux, macOS, or Cloud Shell

Windows (PowerShell)

Windows (cmd.exe)

REST

curl (Linux, macOS, or Cloud Shell)

PowerShell (Windows)

Python

Console

Deploy an index

gcloud

Linux, macOS, or Cloud Shell

Windows (PowerShell)

Windows (cmd.exe)

REST

curl (Linux, macOS, or Cloud Shell)

PowerShell (Windows)

Python

Console

Enable autoscaling

gcloud

Linux, macOS, or Cloud Shell

Windows (PowerShell)

Windows (cmd.exe)

REST

curl (Linux, macOS, or Cloud Shell)

PowerShell (Windows)

Python

Console

Mutate a DeployedIndex

gcloud

Linux, macOS, or Cloud Shell

Windows (PowerShell)

Windows (cmd.exe)

REST

curl (Linux, macOS, or Cloud Shell)

PowerShell (Windows)

Python

Deployment settings that impact performance

List IndexEndpoints

gcloud

Linux, macOS, or Cloud Shell

Windows (PowerShell)

Windows (cmd.exe)

REST

curl (Linux, macOS, or Cloud Shell)

PowerShell (Windows)

Python

Console

Undeploy an index

gcloud

Linux, macOS, or Cloud Shell

Windows (PowerShell)

Windows (cmd.exe)

REST

curl (Linux, macOS, or Cloud Shell)

PowerShell (Windows)

Python

Console

Delete an IndexEndpoint

gcloud

Linux, macOS, or Cloud Shell

Windows (PowerShell)

Windows (cmd.exe)

REST

curl (Linux, macOS, or Cloud Shell)

PowerShell (Windows)

Python

Console

Create an `IndexEndpoint` within your VPC network

Mutate a `DeployedIndex`

List `IndexEndpoints`

Delete an `IndexEndpoint`