ProjectsLocationsEndpoints
class ProjectsLocationsEndpoints extends Resource (View source)
The "endpoints" collection of methods.
Typical usage is:
$aiplatformService = new Google\Service\Aiplatform(...);
$endpoints = $aiplatformService->projects_locations_endpoints;
Methods
Return a list of tokens based on the input text. (endpoints.computeTokens)
Perform a token counting. (endpoints.countTokens)
Creates an Endpoint. (endpoints.create)
Deletes an Endpoint. (endpoints.delete)
Deploys a Model into this Endpoint, creating a DeployedModel within it.
Perform an unary online prediction request to a gRPC model server for Vertex first-party products and frameworks. (endpoints.directPredict)
Perform an unary online prediction request to a gRPC model server for custom containers. (endpoints.directRawPredict)
Perform an online explanation. If deployed_model_id is specified, the corresponding DeployModel must have explanation_spec populated. If deployed_model_id is not specified, all DeployedModels must have explanation_spec populated. (endpoints.explain)
Generate content with multimodal inputs. (endpoints.generateContent)
Gets an Endpoint. (endpoints.get)
Lists Endpoints in a Location. (endpoints.listProjectsLocationsEndpoints)
Updates an existing deployed model. Updatable fields include
min_replica_count
, max_replica_count
, autoscaling_metric_specs
,
disable_container_logging
(v1 only), and enable_container_logging
(v1beta1 only). (endpoints.mutateDeployedModel)
Updates an Endpoint. (endpoints.patch)
Perform an online prediction. (endpoints.predict)
Perform an online prediction with an arbitrary HTTP payload. The response
includes the following HTTP headers: X-Vertex-AI-Endpoint-Id
: ID of the
Endpoint that served this prediction. X-Vertex-AI-Deployed-Model-Id
: ID
of the Endpoint's DeployedModel that served this prediction.
Perform a server-side streaming online prediction request for Vertex LLM streaming. (endpoints.serverStreamingPredict)
Generate content with multimodal inputs with streaming support.
Perform a streaming online prediction with an arbitrary HTTP payload.
Undeploys a Model from an Endpoint, removing a DeployedModel from it, and freeing all resources it's using. (endpoints.undeployModel)
Details
GoogleCloudAiplatformV1ComputeTokensResponse
computeTokens(string $endpoint, GoogleCloudAiplatformV1ComputeTokensRequest $postBody, array $optParams = [])
Return a list of tokens based on the input text. (endpoints.computeTokens)
GoogleCloudAiplatformV1CountTokensResponse
countTokens(string $endpoint, GoogleCloudAiplatformV1CountTokensRequest $postBody, array $optParams = [])
Perform a token counting. (endpoints.countTokens)
GoogleLongrunningOperation
create(string $parent, GoogleCloudAiplatformV1Endpoint $postBody, array $optParams = [])
Creates an Endpoint. (endpoints.create)
GoogleLongrunningOperation
delete(string $name, array $optParams = [])
Deletes an Endpoint. (endpoints.delete)
GoogleLongrunningOperation
deployModel(string $endpoint, GoogleCloudAiplatformV1DeployModelRequest $postBody, array $optParams = [])
Deploys a Model into this Endpoint, creating a DeployedModel within it.
(endpoints.deployModel)
GoogleCloudAiplatformV1DirectPredictResponse
directPredict(string $endpoint, GoogleCloudAiplatformV1DirectPredictRequest $postBody, array $optParams = [])
Perform an unary online prediction request to a gRPC model server for Vertex first-party products and frameworks. (endpoints.directPredict)
GoogleCloudAiplatformV1DirectRawPredictResponse
directRawPredict(string $endpoint, GoogleCloudAiplatformV1DirectRawPredictRequest $postBody, array $optParams = [])
Perform an unary online prediction request to a gRPC model server for custom containers. (endpoints.directRawPredict)
GoogleCloudAiplatformV1ExplainResponse
explain(string $endpoint, GoogleCloudAiplatformV1ExplainRequest $postBody, array $optParams = [])
Perform an online explanation. If deployed_model_id is specified, the corresponding DeployModel must have explanation_spec populated. If deployed_model_id is not specified, all DeployedModels must have explanation_spec populated. (endpoints.explain)
GoogleCloudAiplatformV1GenerateContentResponse
generateContent(string $model, GoogleCloudAiplatformV1GenerateContentRequest $postBody, array $optParams = [])
Generate content with multimodal inputs. (endpoints.generateContent)
GoogleCloudAiplatformV1Endpoint
get(string $name, array $optParams = [])
Gets an Endpoint. (endpoints.get)
GoogleCloudAiplatformV1ListEndpointsResponse
listProjectsLocationsEndpoints(string $parent, array $optParams = [])
Lists Endpoints in a Location. (endpoints.listProjectsLocationsEndpoints)
GoogleLongrunningOperation
mutateDeployedModel(string $endpoint, GoogleCloudAiplatformV1MutateDeployedModelRequest $postBody, array $optParams = [])
Updates an existing deployed model. Updatable fields include
min_replica_count
, max_replica_count
, autoscaling_metric_specs
,
disable_container_logging
(v1 only), and enable_container_logging
(v1beta1 only). (endpoints.mutateDeployedModel)
GoogleCloudAiplatformV1Endpoint
patch(string $name, GoogleCloudAiplatformV1Endpoint $postBody, array $optParams = [])
Updates an Endpoint. (endpoints.patch)
GoogleCloudAiplatformV1PredictResponse
predict(string $endpoint, GoogleCloudAiplatformV1PredictRequest $postBody, array $optParams = [])
Perform an online prediction. (endpoints.predict)
GoogleApiHttpBody
rawPredict(string $endpoint, GoogleCloudAiplatformV1RawPredictRequest $postBody, array $optParams = [])
Perform an online prediction with an arbitrary HTTP payload. The response
includes the following HTTP headers: X-Vertex-AI-Endpoint-Id
: ID of the
Endpoint that served this prediction. X-Vertex-AI-Deployed-Model-Id
: ID
of the Endpoint's DeployedModel that served this prediction.
(endpoints.rawPredict)
GoogleCloudAiplatformV1StreamingPredictResponse
serverStreamingPredict(string $endpoint, GoogleCloudAiplatformV1StreamingPredictRequest $postBody, array $optParams = [])
Perform a server-side streaming online prediction request for Vertex LLM streaming. (endpoints.serverStreamingPredict)
GoogleCloudAiplatformV1GenerateContentResponse
streamGenerateContent(string $model, GoogleCloudAiplatformV1GenerateContentRequest $postBody, array $optParams = [])
Generate content with multimodal inputs with streaming support.
(endpoints.streamGenerateContent)
GoogleApiHttpBody
streamRawPredict(string $endpoint, GoogleCloudAiplatformV1StreamRawPredictRequest $postBody, array $optParams = [])
Perform a streaming online prediction with an arbitrary HTTP payload.
(endpoints.streamRawPredict)
GoogleLongrunningOperation
undeployModel(string $endpoint, GoogleCloudAiplatformV1UndeployModelRequest $postBody, array $optParams = [])
Undeploys a Model from an Endpoint, removing a DeployedModel from it, and freeing all resources it's using. (endpoints.undeployModel)