Vertex AI V1 API - Class Google::Cloud::AIPlatform::V1::GenAiTuningService::Client (v0.55.0)

Reference documentation and code samples for the Vertex AI V1 API class Google::Cloud::AIPlatform::V1::GenAiTuningService::Client.

Client for the GenAiTuningService service.

A service for creating and managing GenAI Tuning Jobs.

Inherits

  • Object

Includes

Methods

.configure

def self.configure() { |config| ... } -> Client::Configuration

Configure the GenAiTuningService Client class.

See Configuration for a description of the configuration fields.

Yields
  • (config) — Configure the Client client.
Yield Parameter
Returns
Example 
# Modify the configuration for all GenAiTuningService clients
::Google::Cloud::AIPlatform::V1::GenAiTuningService::Client.configure do |config|
  config.timeout = 10.0
end

#cancel_tuning_job

def cancel_tuning_job(request, options = nil) -> ::Google::Protobuf::Empty
def cancel_tuning_job(name: nil) -> ::Google::Protobuf::Empty

Cancels a TuningJob. Starts asynchronous cancellation on the TuningJob. The server makes a best effort to cancel the job, but success is not guaranteed. Clients can use GenAiTuningService.GetTuningJob or other methods to check whether the cancellation succeeded or whether the job completed despite cancellation. On successful cancellation, the TuningJob is not deleted; instead it becomes a job with a TuningJob.error value with a google.rpc.Status.code of 1, corresponding to Code.CANCELLED, and TuningJob.state is set to CANCELLED.

Overloads 
def cancel_tuning_job(request, options = nil) -> ::Google::Protobuf::Empty
Pass arguments to cancel_tuning_job via a request object, either of type CancelTuningJobRequest or an equivalent Hash.
Parameters
  • request (::Google::Cloud::AIPlatform::V1::CancelTuningJobRequest, ::Hash) — A request object representing the call parameters. Required. To specify no parameters, or to keep all the default parameter values, pass an empty Hash.
  • options (::Gapic::CallOptions, ::Hash) — Overrides the default settings for this call, e.g, timeout, retries, etc. Optional. 
def cancel_tuning_job(name: nil) -> ::Google::Protobuf::Empty
Pass arguments to cancel_tuning_job via keyword arguments. Note that at least one keyword argument is required. To specify no parameters, or to keep all the default parameter values, pass an empty Hash as a request object (see above).
Parameter
  • name (::String) — Required. The name of the TuningJob to cancel. Format: projects/{project}/locations/{location}/tuningJobs/{tuning_job}
Yields
  • (response, operation) — Access the result along with the RPC operation
Yield Parameters
Returns
Raises
  • (::Google::Cloud::Error) — if the RPC is aborted.
Example

Basic example

require "google/cloud/ai_platform/v1"

# Create a client object. The client can be reused for multiple calls.
client = Google::Cloud::AIPlatform::V1::GenAiTuningService::Client.new

# Create a request. To set request fields, pass in keyword arguments.
request = Google::Cloud::AIPlatform::V1::CancelTuningJobRequest.new

# Call the cancel_tuning_job method.
result = client.cancel_tuning_job request

# The returned object is of type Google::Protobuf::Empty.
p result

#configure

def configure() { |config| ... } -> Client::Configuration

Configure the GenAiTuningService Client instance.

The configuration is set to the derived mode, meaning that values can be changed, but structural changes (adding new fields, etc.) are not allowed. Structural changes should be made on Client.configure.

See Configuration for a description of the configuration fields.

Yields
  • (config) — Configure the Client client.
Yield Parameter
Returns

#create_tuning_job

def create_tuning_job(request, options = nil) -> ::Google::Cloud::AIPlatform::V1::TuningJob
def create_tuning_job(parent: nil, tuning_job: nil) -> ::Google::Cloud::AIPlatform::V1::TuningJob

Creates a TuningJob. A created TuningJob right away will be attempted to be run.

Overloads 
def create_tuning_job(request, options = nil) -> ::Google::Cloud::AIPlatform::V1::TuningJob
Pass arguments to create_tuning_job via a request object, either of type CreateTuningJobRequest or an equivalent Hash.
Parameters
  • request (::Google::Cloud::AIPlatform::V1::CreateTuningJobRequest, ::Hash) — A request object representing the call parameters. Required. To specify no parameters, or to keep all the default parameter values, pass an empty Hash.
  • options (::Gapic::CallOptions, ::Hash) — Overrides the default settings for this call, e.g, timeout, retries, etc. Optional. 
def create_tuning_job(parent: nil, tuning_job: nil) -> ::Google::Cloud::AIPlatform::V1::TuningJob
Pass arguments to create_tuning_job via keyword arguments. Note that at least one keyword argument is required. To specify no parameters, or to keep all the default parameter values, pass an empty Hash as a request object (see above).
Parameters
  • parent (::String) — Required. The resource name of the Location to create the TuningJob in. Format: projects/{project}/locations/{location}
  • tuning_job (::Google::Cloud::AIPlatform::V1::TuningJob, ::Hash) — Required. The TuningJob to create.
Yields
  • (response, operation) — Access the result along with the RPC operation
Yield Parameters
Returns
Raises
  • (::Google::Cloud::Error) — if the RPC is aborted.
Example

Basic example

require "google/cloud/ai_platform/v1"

# Create a client object. The client can be reused for multiple calls.
client = Google::Cloud::AIPlatform::V1::GenAiTuningService::Client.new

# Create a request. To set request fields, pass in keyword arguments.
request = Google::Cloud::AIPlatform::V1::CreateTuningJobRequest.new

# Call the create_tuning_job method.
result = client.create_tuning_job request

# The returned object is of type Google::Cloud::AIPlatform::V1::TuningJob.
p result

#get_tuning_job

def get_tuning_job(request, options = nil) -> ::Google::Cloud::AIPlatform::V1::TuningJob
def get_tuning_job(name: nil) -> ::Google::Cloud::AIPlatform::V1::TuningJob

Gets a TuningJob.

Overloads 
def get_tuning_job(request, options = nil) -> ::Google::Cloud::AIPlatform::V1::TuningJob
Pass arguments to get_tuning_job via a request object, either of type Google::Cloud::AIPlatform::V1::GetTuningJobRequest or an equivalent Hash.
Parameters
  • request (::Google::Cloud::AIPlatform::V1::GetTuningJobRequest, ::Hash) — A request object representing the call parameters. Required. To specify no parameters, or to keep all the default parameter values, pass an empty Hash.
  • options (::Gapic::CallOptions, ::Hash) — Overrides the default settings for this call, e.g, timeout, retries, etc. Optional. 
def get_tuning_job(name: nil) -> ::Google::Cloud::AIPlatform::V1::TuningJob
Pass arguments to get_tuning_job via keyword arguments. Note that at least one keyword argument is required. To specify no parameters, or to keep all the default parameter values, pass an empty Hash as a request object (see above).
Parameter
  • name (::String) — Required. The name of the TuningJob resource. Format: projects/{project}/locations/{location}/tuningJobs/{tuning_job}
Yields
  • (response, operation) — Access the result along with the RPC operation
Yield Parameters
Returns
Raises
  • (::Google::Cloud::Error) — if the RPC is aborted.
Example

Basic example

require "google/cloud/ai_platform/v1"

# Create a client object. The client can be reused for multiple calls.
client = Google::Cloud::AIPlatform::V1::GenAiTuningService::Client.new

# Create a request. To set request fields, pass in keyword arguments.
request = Google::Cloud::AIPlatform::V1::GetTuningJobRequest.new

# Call the get_tuning_job method.
result = client.get_tuning_job request

# The returned object is of type Google::Cloud::AIPlatform::V1::TuningJob.
p result

#iam_policy_client

def iam_policy_client() -> Google::Iam::V1::IAMPolicy::Client

Get the associated client for mix-in of the IAMPolicy.

Returns
  • (Google::Iam::V1::IAMPolicy::Client)

#initialize

def initialize() { |config| ... } -> Client

Create a new GenAiTuningService client object.

Yields
  • (config) — Configure the GenAiTuningService client.
Yield Parameter
Returns
  • (Client) — a new instance of Client
Example 
# Create a client using the default configuration
client = ::Google::Cloud::AIPlatform::V1::GenAiTuningService::Client.new

# Create a client using a custom configuration
client = ::Google::Cloud::AIPlatform::V1::GenAiTuningService::Client.new do |config|
  config.timeout = 10.0
end

#list_tuning_jobs

def list_tuning_jobs(request, options = nil) -> ::Gapic::PagedEnumerable<::Google::Cloud::AIPlatform::V1::TuningJob>
def list_tuning_jobs(parent: nil, filter: nil, page_size: nil, page_token: nil) -> ::Gapic::PagedEnumerable<::Google::Cloud::AIPlatform::V1::TuningJob>

Lists TuningJobs in a Location.

Overloads 
def list_tuning_jobs(request, options = nil) -> ::Gapic::PagedEnumerable<::Google::Cloud::AIPlatform::V1::TuningJob>
Pass arguments to list_tuning_jobs via a request object, either of type ListTuningJobsRequest or an equivalent Hash.
Parameters
  • request (::Google::Cloud::AIPlatform::V1::ListTuningJobsRequest, ::Hash) — A request object representing the call parameters. Required. To specify no parameters, or to keep all the default parameter values, pass an empty Hash.
  • options (::Gapic::CallOptions, ::Hash) — Overrides the default settings for this call, e.g, timeout, retries, etc. Optional. 
def list_tuning_jobs(parent: nil, filter: nil, page_size: nil, page_token: nil) -> ::Gapic::PagedEnumerable<::Google::Cloud::AIPlatform::V1::TuningJob>
Pass arguments to list_tuning_jobs via keyword arguments. Note that at least one keyword argument is required. To specify no parameters, or to keep all the default parameter values, pass an empty Hash as a request object (see above).
Parameters
  • parent (::String) — Required. The resource name of the Location to list the TuningJobs from. Format: projects/{project}/locations/{location}
  • filter (::String) — Optional. The standard list filter.
  • page_size (::Integer) — Optional. The standard list page size.
  • page_token (::String) — Optional. The standard list page token. Typically obtained via [ListTuningJob.next_page_token][] of the previous GenAiTuningService.ListTuningJob][] call.
Yields
  • (response, operation) — Access the result along with the RPC operation
Yield Parameters
Returns
Raises
  • (::Google::Cloud::Error) — if the RPC is aborted.
Example

Basic example

require "google/cloud/ai_platform/v1"

# Create a client object. The client can be reused for multiple calls.
client = Google::Cloud::AIPlatform::V1::GenAiTuningService::Client.new

# Create a request. To set request fields, pass in keyword arguments.
request = Google::Cloud::AIPlatform::V1::ListTuningJobsRequest.new

# Call the list_tuning_jobs method.
result = client.list_tuning_jobs request

# The returned object is of type Gapic::PagedEnumerable. You can iterate
# over elements, and API calls will be issued to fetch pages as needed.
result.each do |item|
  # Each element is of type ::Google::Cloud::AIPlatform::V1::TuningJob.
  p item
end

#location_client

def location_client() -> Google::Cloud::Location::Locations::Client

Get the associated client for mix-in of the Locations.

Returns
  • (Google::Cloud::Location::Locations::Client)

#operations_client

def operations_client() -> ::Google::Cloud::AIPlatform::V1::GenAiTuningService::Operations

Get the associated client for long-running operations.

Returns

#rebase_tuned_model

def rebase_tuned_model(request, options = nil) -> ::Gapic::Operation
def rebase_tuned_model(parent: nil, tuned_model_ref: nil, tuning_job: nil, artifact_destination: nil, deploy_to_same_endpoint: nil) -> ::Gapic::Operation

Rebase a TunedModel. Creates a LongRunningOperation that takes a legacy Tuned GenAI model Reference and creates a TuningJob based on newly available model.

Overloads 
def rebase_tuned_model(request, options = nil) -> ::Gapic::Operation
Pass arguments to rebase_tuned_model via a request object, either of type RebaseTunedModelRequest or an equivalent Hash.
Parameters
  • request (::Google::Cloud::AIPlatform::V1::RebaseTunedModelRequest, ::Hash) — A request object representing the call parameters. Required. To specify no parameters, or to keep all the default parameter values, pass an empty Hash.
  • options (::Gapic::CallOptions, ::Hash) — Overrides the default settings for this call, e.g, timeout, retries, etc. Optional. 
def rebase_tuned_model(parent: nil, tuned_model_ref: nil, tuning_job: nil, artifact_destination: nil, deploy_to_same_endpoint: nil) -> ::Gapic::Operation
Pass arguments to rebase_tuned_model via keyword arguments. Note that at least one keyword argument is required. To specify no parameters, or to keep all the default parameter values, pass an empty Hash as a request object (see above).
Parameters
  • parent (::String) — Required. The resource name of the Location into which to rebase the Model. Format: projects/{project}/locations/{location}
  • tuned_model_ref (::Google::Cloud::AIPlatform::V1::TunedModelRef, ::Hash) — Required. TunedModel reference to retrieve the legacy model information.
  • tuning_job (::Google::Cloud::AIPlatform::V1::TuningJob, ::Hash) — Optional. The TuningJob to be updated. Users can use this TuningJob field to overwrite tuning configs.
  • artifact_destination (::Google::Cloud::AIPlatform::V1::GcsDestination, ::Hash) — Optional. The Google Cloud Storage location to write the artifacts.
  • deploy_to_same_endpoint (::Boolean) — Optional. By default, bison to gemini migration will always create new model/endpoint, but for gemini-1.0 to gemini-1.5 migration, we default deploy to the same endpoint. See details in this Section.
Yields
  • (response, operation) — Access the result along with the RPC operation
Yield Parameters
  • response (::Gapic::Operation)
  • operation (::GRPC::ActiveCall::Operation)
Returns
  • (::Gapic::Operation)
Raises
  • (::Google::Cloud::Error) — if the RPC is aborted.
Example

Basic example

require "google/cloud/ai_platform/v1"

# Create a client object. The client can be reused for multiple calls.
client = Google::Cloud::AIPlatform::V1::GenAiTuningService::Client.new

# Create a request. To set request fields, pass in keyword arguments.
request = Google::Cloud::AIPlatform::V1::RebaseTunedModelRequest.new

# Call the rebase_tuned_model method.
result = client.rebase_tuned_model request

# The returned object is of type Gapic::Operation. You can use it to
# check the status of an operation, cancel it, or wait for results.
# Here is how to wait for a response.
result.wait_until_done! timeout: 60
if result.response?
  p result.response
else
  puts "No response received."
end

#universe_domain

def universe_domain() -> String

The effective universe domain

Returns
  • (String)