공개 색인 엔드포인트 배포 및 관리

컬렉션을 사용해 정리하기 내 환경설정을 기준으로 콘텐츠를 저장하고 분류하세요.

resource "google_vertex_ai_index_endpoint" "default" {
  display_name            = "sample-endpoint"
  description             = "A sample index endpoint with a public endpoint"
  region                  = "us-central1"
  public_endpoint_enabled = true
}

# Cloud Storage bucket name must be unique
resource "random_id" "default" {
  byte_length = 8
}

# Create a Cloud Storage bucket
resource "google_storage_bucket" "bucket" {
  name                        = "vertex-ai-index-bucket-${random_id.default.hex}"
  location                    = "us-central1"
  uniform_bucket_level_access = true
}

# Create index content
resource "google_storage_bucket_object" "data" {
  name    = "contents/data.json"
  bucket  = google_storage_bucket.bucket.name
  content = <<EOF
{"id": "42", "embedding": [0.5, 1.0], "restricts": [{"namespace": "class", "allow": ["cat", "pet"]},{"namespace": "category", "allow": ["feline"]}]}
{"id": "43", "embedding": [0.6, 1.0], "restricts": [{"namespace": "class", "allow": ["dog", "pet"]},{"namespace": "category", "allow": ["canine"]}]}
EOF
}

resource "google_vertex_ai_index" "default" {
  region       = "us-central1"
  display_name = "sample-index-batch-update"
  description  = "A sample index for batch update"
  labels = {
    foo = "bar"
  }

  metadata {
    contents_delta_uri = "gs://${google_storage_bucket.bucket.name}/contents"
    config {
      dimensions                  = 2
      approximate_neighbors_count = 150
      distance_measure_type       = "DOT_PRODUCT_DISTANCE"
      algorithm_config {
        tree_ah_config {
          leaf_node_embedding_count    = 500
          leaf_nodes_to_search_percent = 7
        }
      }
    }
  }
  index_update_method = "BATCH_UPDATE"

  timeouts {
    create = "2h"
    update = "1h"
  }
}

def vector_search_create_index_endpoint(
    project: str, location: str, display_name: str
) -> None:
    """Create a vector search index endpoint.

    Args:
        project (str): Required. Project ID
        location (str): Required. The region name
        display_name (str): Required. The index endpoint display name
    """
    # Initialize the Vertex AI client
    aiplatform.init(project=project, location=location)

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

    print(index_endpoint.name)

provider "google" {
  region = "us-central1"
}

resource "google_vertex_ai_index_endpoint_deployed_index" "default" {
  depends_on        = [google_vertex_ai_index_endpoint.default]
  index_endpoint    = google_vertex_ai_index_endpoint.default.id
  index             = google_vertex_ai_index.default.id
  deployed_index_id = "deployed_index_id"
}

resource "google_vertex_ai_index_endpoint" "default" {
  display_name            = "sample-endpoint"
  description             = "A sample index endpoint with a public endpoint"
  region                  = "us-central1"
  public_endpoint_enabled = true
}

# Cloud Storage bucket name must be unique
resource "random_id" "default" {
  byte_length = 8
}

# Create a Cloud Storage bucket
resource "google_storage_bucket" "bucket" {
  name                        = "vertex-ai-index-bucket-${random_id.default.hex}"
  location                    = "us-central1"
  uniform_bucket_level_access = true
}

# Create index content
resource "google_storage_bucket_object" "data" {
  name    = "contents/data.json"
  bucket  = google_storage_bucket.bucket.name
  content = <<EOF
{"id": "42", "embedding": [0.5, 1.0], "restricts": [{"namespace": "class", "allow": ["cat", "pet"]},{"namespace": "category", "allow": ["feline"]}]}
{"id": "43", "embedding": [0.6, 1.0], "restricts": [{"namespace": "class", "allow": ["dog", "pet"]},{"namespace": "category", "allow": ["canine"]}]}
EOF
}

resource "google_vertex_ai_index" "default" {
  region       = "us-central1"
  display_name = "sample-index-batch-update"
  description  = "A sample index for batch update"
  labels = {
    foo = "bar"
  }

  metadata {
    contents_delta_uri = "gs://${google_storage_bucket.bucket.name}/contents"
    config {
      dimensions                  = 2
      approximate_neighbors_count = 150
      distance_measure_type       = "DOT_PRODUCT_DISTANCE"
      algorithm_config {
        tree_ah_config {
          leaf_node_embedding_count    = 500
          leaf_nodes_to_search_percent = 7
        }
      }
    }
  }
  index_update_method = "BATCH_UPDATE"

  timeouts {
    create = "2h"
    update = "1h"
  }
}

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)

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,
    )

provider "google" {
  region = "us-central1"
}

resource "google_vertex_ai_index_endpoint_deployed_index" "default" {
  depends_on        = [google_vertex_ai_index_endpoint.default]
  index_endpoint    = google_vertex_ai_index_endpoint.default.id
  index             = google_vertex_ai_index.default.id
  deployed_index_id = "deployed_index_for_mutate"
  # This example assumes the deployed index endpoint's resources configuration
  # differs from the values specified below. Terraform will mutate the deployed
  # index endpoint's resource configuration to match.
  automatic_resources {
    min_replica_count = 3
    max_replica_count = 5
  }
}

resource "google_vertex_ai_index_endpoint" "default" {
  display_name            = "sample-endpoint"
  description             = "A sample index endpoint with a public endpoint"
  region                  = "us-central1"
  public_endpoint_enabled = true
}

# Cloud Storage bucket name must be unique
resource "random_id" "default" {
  byte_length = 8
}

# Create a Cloud Storage bucket
resource "google_storage_bucket" "bucket" {
  name                        = "vertex-ai-index-bucket-${random_id.default.hex}"
  location                    = "us-central1"
  uniform_bucket_level_access = true
}

# Create index content
resource "google_storage_bucket_object" "data" {
  name    = "contents/data.json"
  bucket  = google_storage_bucket.bucket.name
  content = <<EOF
{"id": "42", "embedding": [0.5, 1.0], "restricts": [{"namespace": "class", "allow": ["cat", "pet"]},{"namespace": "category", "allow": ["feline"]}]}
{"id": "43", "embedding": [0.6, 1.0], "restricts": [{"namespace": "class", "allow": ["dog", "pet"]},{"namespace": "category", "allow": ["canine"]}]}
EOF
}

resource "google_vertex_ai_index" "default" {
  region       = "us-central1"
  display_name = "sample-index-batch-update"
  description  = "A sample index for batch update"
  labels = {
    foo = "bar"
  }

  metadata {
    contents_delta_uri = "gs://${google_storage_bucket.bucket.name}/contents"
    config {
      dimensions                  = 2
      approximate_neighbors_count = 150
      distance_measure_type       = "DOT_PRODUCT_DISTANCE"
      algorithm_config {
        tree_ah_config {
          leaf_node_embedding_count    = 500
          leaf_nodes_to_search_percent = 7
        }
      }
    }
  }
  index_update_method = "BATCH_UPDATE"

  timeouts {
    create = "2h"
    update = "1h"
  }
}

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,
    )

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()

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,
    )

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)