Class: Google::Cloud::GkeRecommender::V1::GkeInferenceQuickstart::Rest::Client

Inherits:
Object
  • Object
show all
Defined in:
lib/google/cloud/gke_recommender/v1/gke_inference_quickstart/rest/client.rb

Overview

REST client for the GkeInferenceQuickstart service.

GKE Inference Quickstart (GIQ) service provides profiles with performance metrics for popular models and model servers across multiple accelerators. These profiles help generate optimized best practices for running inference on GKE.

Defined Under Namespace

Classes: Configuration

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize {|config| ... } ⇒ Client

Create a new GkeInferenceQuickstart REST client object.

Examples:


# Create a client using the default configuration
client = ::Google::Cloud::GkeRecommender::V1::GkeInferenceQuickstart::Rest::Client.new

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

Yields:

  • (config) —

    Configure the GkeInferenceQuickstart client.

Yield Parameters:



139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
 
# File 'lib/google/cloud/gke_recommender/v1/gke_inference_quickstart/rest/client.rb', line 139

def initialize
  # Create the configuration object
  @config = Configuration.new Client.configure

  # Yield the configuration if needed
  yield @config if block_given?

  # Create credentials
  credentials = @config.credentials
  # Use self-signed JWT if the endpoint is unchanged from default,
  # but only if the default endpoint does not have a region prefix.
  enable_self_signed_jwt = @config.endpoint.nil? ||
                           (@config.endpoint == Configuration::DEFAULT_ENDPOINT &&
                           !@config.endpoint.split(".").first.include?("-"))
  credentials ||= Credentials.default scope: @config.scope,
                                      enable_self_signed_jwt: enable_self_signed_jwt
  if credentials.is_a?(::String) || credentials.is_a?(::Hash)
    credentials = Credentials.new credentials, scope: @config.scope
  end

  @quota_project_id = @config.quota_project
  @quota_project_id ||= credentials.quota_project_id if credentials.respond_to? :quota_project_id

  @gke_inference_quickstart_stub = ::Google::Cloud::GkeRecommender::V1::GkeInferenceQuickstart::Rest::ServiceStub.new(
    endpoint: @config.endpoint,
    endpoint_template: DEFAULT_ENDPOINT_TEMPLATE,
    universe_domain: @config.universe_domain,
    credentials: credentials,
    logger: @config.logger
  )

  @gke_inference_quickstart_stub.logger(stub: true)&.info do |entry|
    entry.set_system_name
    entry.set_service
    entry.message = "Created client for #{entry.service}"
    entry.set_credentials_fields credentials
    entry.set "customEndpoint", @config.endpoint if @config.endpoint
    entry.set "defaultTimeout", @config.timeout if @config.timeout
    entry.set "quotaProject", @quota_project_id if @quota_project_id
  end
end

Class Method Details

.configure {|config| ... } ⇒ Client::Configuration

Configure the GkeInferenceQuickstart Client class.

See Configuration for a description of the configuration fields.

Examples:


# Modify the configuration for all GkeInferenceQuickstart clients
::Google::Cloud::GkeRecommender::V1::GkeInferenceQuickstart::Rest::Client.configure do |config|
  config.timeout = 10.0
end

Yields:

  • (config) —

    Configure the Client client.

Yield Parameters:

Returns:



65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
 
# File 'lib/google/cloud/gke_recommender/v1/gke_inference_quickstart/rest/client.rb', line 65

def self.configure
  @configure ||= begin
    namespace = ["Google", "Cloud", "GkeRecommender", "V1"]
    parent_config = while namespace.any?
                      parent_name = namespace.join "::"
                      parent_const = const_get parent_name
                      break parent_const.configure if parent_const.respond_to? :configure
                      namespace.pop
                    end
    default_config = Client::Configuration.new parent_config

    default_config.rpcs.fetch_models.timeout = 60.0

    default_config.rpcs.fetch_model_servers.timeout = 60.0

    default_config.rpcs.fetch_model_server_versions.timeout = 60.0

    default_config.rpcs.fetch_profiles.timeout = 60.0

    default_config.rpcs.generate_optimized_manifest.timeout = 60.0

    default_config.rpcs.fetch_benchmarking_data.timeout = 60.0

    default_config
  end
  yield @configure if block_given?
  @configure
end

Instance Method Details

#configure {|config| ... } ⇒ Client::Configuration

Configure the GkeInferenceQuickstart 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 configure.

See Configuration for a description of the configuration fields.

Yields:

  • (config) —

    Configure the Client client.

Yield Parameters:

Returns:



109
110
111
112
 
# File 'lib/google/cloud/gke_recommender/v1/gke_inference_quickstart/rest/client.rb', line 109

def configure
  yield @config if block_given?
  @config
end

#fetch_benchmarking_data(request, options = nil) ⇒ ::Google::Cloud::GkeRecommender::V1::FetchBenchmarkingDataResponse #fetch_benchmarking_data(model_server_info: nil, instance_type: nil, pricing_model: nil) ⇒ ::Google::Cloud::GkeRecommender::V1::FetchBenchmarkingDataResponse

Fetches all of the benchmarking data available for a profile. Benchmarking data returns all of the performance metrics available for a given model server setup on a given instance type.

Examples:

Basic example

require "google/cloud/gke_recommender/v1"

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

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

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

# The returned object is of type Google::Cloud::GkeRecommender::V1::FetchBenchmarkingDataResponse.
p result

Overloads:

  • #fetch_benchmarking_data(request, options = nil) ⇒ ::Google::Cloud::GkeRecommender::V1::FetchBenchmarkingDataResponse

    Pass arguments to fetch_benchmarking_data via a request object, either of type FetchBenchmarkingDataRequest or an equivalent Hash.

    Parameters:

    • request (::Google::Cloud::GkeRecommender::V1::FetchBenchmarkingDataRequest, ::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) (defaults to: nil) —

      Overrides the default settings for this call, e.g, timeout, retries etc. Optional.

  • #fetch_benchmarking_data(model_server_info: nil, instance_type: nil, pricing_model: nil) ⇒ ::Google::Cloud::GkeRecommender::V1::FetchBenchmarkingDataResponse

    Pass arguments to fetch_benchmarking_data 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:

    • model_server_info (::Google::Cloud::GkeRecommender::V1::ModelServerInfo, ::Hash) (defaults to: nil) —

      Required. The model server configuration to get benchmarking data for. Use GkeInferenceQuickstart.FetchProfiles to find valid configurations.

    • instance_type (::String) (defaults to: nil) —

      Optional. The instance type to filter benchmarking data. Instance types are in the format a2-highgpu-1g. If not provided, all instance types for the given profile's model_server_info will be returned. Use GkeInferenceQuickstart.FetchProfiles to find available instance types.

    • pricing_model (::String) (defaults to: nil) —

      Optional. The pricing model to use for the benchmarking data. Defaults to spot.

Yields:

  • (result, operation) —

    Access the result along with the TransportOperation object

Yield Parameters:

Returns:

Raises:

  • (::Google::Cloud::Error) —

    if the REST call is aborted.



771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
 
# File 'lib/google/cloud/gke_recommender/v1/gke_inference_quickstart/rest/client.rb', line 771

def fetch_benchmarking_data request, options = nil
  raise ::ArgumentError, "request must be provided" if request.nil?

  request = ::Gapic::Protobuf.coerce request, to: ::Google::Cloud::GkeRecommender::V1::FetchBenchmarkingDataRequest

  # Converts hash and nil to an options object
  options = ::Gapic::CallOptions.new(**options.to_h) if options.respond_to? :to_h

  # Customize the options with defaults
  call_metadata = @config.rpcs.fetch_benchmarking_data.metadata.to_h

  # Set x-goog-api-client, x-goog-user-project and x-goog-api-version headers
  call_metadata[:"x-goog-api-client"] ||= ::Gapic::Headers.x_goog_api_client \
    lib_name: @config.lib_name, lib_version: @config.lib_version,
    gapic_version: ::Google::Cloud::GkeRecommender::V1::VERSION,
    transports_version_send: [:rest]

  call_metadata[:"x-goog-api-version"] = API_VERSION unless API_VERSION.empty?
  call_metadata[:"x-goog-user-project"] = @quota_project_id if @quota_project_id

  options.apply_defaults timeout:      @config.rpcs.fetch_benchmarking_data.timeout,
                         metadata:     call_metadata,
                         retry_policy: @config.rpcs.fetch_benchmarking_data.retry_policy

  options.apply_defaults timeout:      @config.timeout,
                         metadata:     @config.metadata,
                         retry_policy: @config.retry_policy

  @gke_inference_quickstart_stub.fetch_benchmarking_data request, options do |result, operation|
    yield result, operation if block_given?
  end
rescue ::Gapic::Rest::Error => e
  raise ::Google::Cloud::Error.from_error(e)
end

#fetch_model_server_versions(request, options = nil) ⇒ ::Google::Cloud::GkeRecommender::V1::FetchModelServerVersionsResponse #fetch_model_server_versions(model: nil, model_server: nil, page_size: nil, page_token: nil) ⇒ ::Google::Cloud::GkeRecommender::V1::FetchModelServerVersionsResponse

Fetches available model server versions. Open-source servers use their own versioning schemas (e.g., vllm uses semver like v1.0.0).

Some model servers have different versioning schemas depending on the accelerator. For example, vllm uses semver on GPUs, but returns nightly build tags on TPUs. All available versions will be returned when different schemas are present.

Examples:

Basic example

require "google/cloud/gke_recommender/v1"

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

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

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

# The returned object is of type Google::Cloud::GkeRecommender::V1::FetchModelServerVersionsResponse.
p result

Overloads:

  • #fetch_model_server_versions(request, options = nil) ⇒ ::Google::Cloud::GkeRecommender::V1::FetchModelServerVersionsResponse

    Pass arguments to fetch_model_server_versions via a request object, either of type FetchModelServerVersionsRequest or an equivalent Hash.

    Parameters:

    • request (::Google::Cloud::GkeRecommender::V1::FetchModelServerVersionsRequest, ::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) (defaults to: nil) —

      Overrides the default settings for this call, e.g, timeout, retries etc. Optional.

  • #fetch_model_server_versions(model: nil, model_server: nil, page_size: nil, page_token: nil) ⇒ ::Google::Cloud::GkeRecommender::V1::FetchModelServerVersionsResponse

    Pass arguments to fetch_model_server_versions 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:

    • model (::String) (defaults to: nil) —

      Required. The model for which to list model server versions. Open-source models follow the Huggingface Hub owner/model_name format. Use GkeInferenceQuickstart.FetchModels to find available models.

    • model_server (::String) (defaults to: nil) —

      Required. The model server for which to list versions. Open-source model servers use simplified, lowercase names (e.g., vllm). Use GkeInferenceQuickstart.FetchModelServers to find available model servers.

    • page_size (::Integer) (defaults to: nil) —

      Optional. The target number of results to return in a single response. If not specified, a default value will be chosen by the service. Note that the response may include a partial list and a caller should only rely on the response's next_page_token to determine if there are more instances left to be queried.

    • page_token (::String) (defaults to: nil) —

      Optional. The value of next_page_token received from a previous FetchModelServerVersionsRequest call. Provide this to retrieve the subsequent page in a multi-page list of results. When paginating, all other parameters provided to FetchModelServerVersionsRequest must match the call that provided the page token.

Yields:

  • (result, operation) —

    Access the result along with the TransportOperation object

Yield Parameters:

Returns:

Raises:

  • (::Google::Cloud::Error) —

    if the REST call is aborted.



452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
 
# File 'lib/google/cloud/gke_recommender/v1/gke_inference_quickstart/rest/client.rb', line 452

def fetch_model_server_versions request, options = nil
  raise ::ArgumentError, "request must be provided" if request.nil?

  request = ::Gapic::Protobuf.coerce request, to: ::Google::Cloud::GkeRecommender::V1::FetchModelServerVersionsRequest

  # Converts hash and nil to an options object
  options = ::Gapic::CallOptions.new(**options.to_h) if options.respond_to? :to_h

  # Customize the options with defaults
  call_metadata = @config.rpcs.fetch_model_server_versions.metadata.to_h

  # Set x-goog-api-client, x-goog-user-project and x-goog-api-version headers
  call_metadata[:"x-goog-api-client"] ||= ::Gapic::Headers.x_goog_api_client \
    lib_name: @config.lib_name, lib_version: @config.lib_version,
    gapic_version: ::Google::Cloud::GkeRecommender::V1::VERSION,
    transports_version_send: [:rest]

  call_metadata[:"x-goog-api-version"] = API_VERSION unless API_VERSION.empty?
  call_metadata[:"x-goog-user-project"] = @quota_project_id if @quota_project_id

  options.apply_defaults timeout:      @config.rpcs.fetch_model_server_versions.timeout,
                         metadata:     call_metadata,
                         retry_policy: @config.rpcs.fetch_model_server_versions.retry_policy

  options.apply_defaults timeout:      @config.timeout,
                         metadata:     @config.metadata,
                         retry_policy: @config.retry_policy

  @gke_inference_quickstart_stub.fetch_model_server_versions request, options do |result, operation|
    yield result, operation if block_given?
  end
rescue ::Gapic::Rest::Error => e
  raise ::Google::Cloud::Error.from_error(e)
end

#fetch_model_servers(request, options = nil) ⇒ ::Google::Cloud::GkeRecommender::V1::FetchModelServersResponse #fetch_model_servers(model: nil, page_size: nil, page_token: nil) ⇒ ::Google::Cloud::GkeRecommender::V1::FetchModelServersResponse

Fetches available model servers. Open-source model servers use simplified, lowercase names (e.g., vllm).

Examples:

Basic example

require "google/cloud/gke_recommender/v1"

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

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

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

# The returned object is of type Google::Cloud::GkeRecommender::V1::FetchModelServersResponse.
p result

Overloads:

  • #fetch_model_servers(request, options = nil) ⇒ ::Google::Cloud::GkeRecommender::V1::FetchModelServersResponse

    Pass arguments to fetch_model_servers via a request object, either of type FetchModelServersRequest or an equivalent Hash.

    Parameters:

    • request (::Google::Cloud::GkeRecommender::V1::FetchModelServersRequest, ::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) (defaults to: nil) —

      Overrides the default settings for this call, e.g, timeout, retries etc. Optional.

  • #fetch_model_servers(model: nil, page_size: nil, page_token: nil) ⇒ ::Google::Cloud::GkeRecommender::V1::FetchModelServersResponse

    Pass arguments to fetch_model_servers 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:

    • model (::String) (defaults to: nil) —

      Required. The model for which to list model servers. Open-source models follow the Huggingface Hub owner/model_name format. Use GkeInferenceQuickstart.FetchModels to find available models.

    • page_size (::Integer) (defaults to: nil) —

      Optional. The target number of results to return in a single response. If not specified, a default value will be chosen by the service. Note that the response may include a partial list and a caller should only rely on the response's next_page_token to determine if there are more instances left to be queried.

    • page_token (::String) (defaults to: nil) —

      Optional. The value of next_page_token received from a previous FetchModelServersRequest call. Provide this to retrieve the subsequent page in a multi-page list of results. When paginating, all other parameters provided to FetchModelServersRequest must match the call that provided the page token.

Yields:

  • (result, operation) —

    Access the result along with the TransportOperation object

Yield Parameters:

Returns:

Raises:

  • (::Google::Cloud::Error) —

    if the REST call is aborted.



345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
 
# File 'lib/google/cloud/gke_recommender/v1/gke_inference_quickstart/rest/client.rb', line 345

def fetch_model_servers request, options = nil
  raise ::ArgumentError, "request must be provided" if request.nil?

  request = ::Gapic::Protobuf.coerce request, to: ::Google::Cloud::GkeRecommender::V1::FetchModelServersRequest

  # Converts hash and nil to an options object
  options = ::Gapic::CallOptions.new(**options.to_h) if options.respond_to? :to_h

  # Customize the options with defaults
  call_metadata = @config.rpcs.fetch_model_servers.metadata.to_h

  # Set x-goog-api-client, x-goog-user-project and x-goog-api-version headers
  call_metadata[:"x-goog-api-client"] ||= ::Gapic::Headers.x_goog_api_client \
    lib_name: @config.lib_name, lib_version: @config.lib_version,
    gapic_version: ::Google::Cloud::GkeRecommender::V1::VERSION,
    transports_version_send: [:rest]

  call_metadata[:"x-goog-api-version"] = API_VERSION unless API_VERSION.empty?
  call_metadata[:"x-goog-user-project"] = @quota_project_id if @quota_project_id

  options.apply_defaults timeout:      @config.rpcs.fetch_model_servers.timeout,
                         metadata:     call_metadata,
                         retry_policy: @config.rpcs.fetch_model_servers.retry_policy

  options.apply_defaults timeout:      @config.timeout,
                         metadata:     @config.metadata,
                         retry_policy: @config.retry_policy

  @gke_inference_quickstart_stub.fetch_model_servers request, options do |result, operation|
    yield result, operation if block_given?
  end
rescue ::Gapic::Rest::Error => e
  raise ::Google::Cloud::Error.from_error(e)
end

#fetch_models(request, options = nil) ⇒ ::Google::Cloud::GkeRecommender::V1::FetchModelsResponse #fetch_models(page_size: nil, page_token: nil) ⇒ ::Google::Cloud::GkeRecommender::V1::FetchModelsResponse

Fetches available models. Open-source models follow the Huggingface Hub owner/model_name format.

Examples:

Basic example

require "google/cloud/gke_recommender/v1"

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

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

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

# The returned object is of type Google::Cloud::GkeRecommender::V1::FetchModelsResponse.
p result

Overloads:

  • #fetch_models(request, options = nil) ⇒ ::Google::Cloud::GkeRecommender::V1::FetchModelsResponse

    Pass arguments to fetch_models via a request object, either of type FetchModelsRequest or an equivalent Hash.

    Parameters:

    • request (::Google::Cloud::GkeRecommender::V1::FetchModelsRequest, ::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) (defaults to: nil) —

      Overrides the default settings for this call, e.g, timeout, retries etc. Optional.

  • #fetch_models(page_size: nil, page_token: nil) ⇒ ::Google::Cloud::GkeRecommender::V1::FetchModelsResponse

    Pass arguments to fetch_models 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:

    • page_size (::Integer) (defaults to: nil) —

      Optional. The target number of results to return in a single response. If not specified, a default value will be chosen by the service. Note that the response may include a partial list and a caller should only rely on the response's next_page_token to determine if there are more instances left to be queried.

    • page_token (::String) (defaults to: nil) —

      Optional. The value of next_page_token received from a previous FetchModelsRequest call. Provide this to retrieve the subsequent page in a multi-page list of results. When paginating, all other parameters provided to FetchModelsRequest must match the call that provided the page token.

Yields:

  • (result, operation) —

    Access the result along with the TransportOperation object

Yield Parameters:

Returns:

Raises:

  • (::Google::Cloud::Error) —

    if the REST call is aborted.



248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
 
# File 'lib/google/cloud/gke_recommender/v1/gke_inference_quickstart/rest/client.rb', line 248

def fetch_models request, options = nil
  raise ::ArgumentError, "request must be provided" if request.nil?

  request = ::Gapic::Protobuf.coerce request, to: ::Google::Cloud::GkeRecommender::V1::FetchModelsRequest

  # Converts hash and nil to an options object
  options = ::Gapic::CallOptions.new(**options.to_h) if options.respond_to? :to_h

  # Customize the options with defaults
  call_metadata = @config.rpcs.fetch_models.metadata.to_h

  # Set x-goog-api-client, x-goog-user-project and x-goog-api-version headers
  call_metadata[:"x-goog-api-client"] ||= ::Gapic::Headers.x_goog_api_client \
    lib_name: @config.lib_name, lib_version: @config.lib_version,
    gapic_version: ::Google::Cloud::GkeRecommender::V1::VERSION,
    transports_version_send: [:rest]

  call_metadata[:"x-goog-api-version"] = API_VERSION unless API_VERSION.empty?
  call_metadata[:"x-goog-user-project"] = @quota_project_id if @quota_project_id

  options.apply_defaults timeout:      @config.rpcs.fetch_models.timeout,
                         metadata:     call_metadata,
                         retry_policy: @config.rpcs.fetch_models.retry_policy

  options.apply_defaults timeout:      @config.timeout,
                         metadata:     @config.metadata,
                         retry_policy: @config.retry_policy

  @gke_inference_quickstart_stub.fetch_models request, options do |result, operation|
    yield result, operation if block_given?
  end
rescue ::Gapic::Rest::Error => e
  raise ::Google::Cloud::Error.from_error(e)
end

#fetch_profiles(request, options = nil) ⇒ ::Gapic::Rest::PagedEnumerable<::Google::Cloud::GkeRecommender::V1::Profile> #fetch_profiles(model: nil, model_server: nil, model_server_version: nil, performance_requirements: nil, page_size: nil, page_token: nil) ⇒ ::Gapic::Rest::PagedEnumerable<::Google::Cloud::GkeRecommender::V1::Profile>

Fetches available profiles. A profile contains performance metrics and cost information for a specific model server setup. Profiles can be filtered by parameters. If no filters are provided, all profiles are returned.

Profiles display a single value per performance metric based on the provided performance requirements. If no requirements are given, the metrics represent the inflection point. See Run best practice inference with GKE Inference Quickstart recipes for details.

Examples:

Basic example

require "google/cloud/gke_recommender/v1"

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

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

# Call the fetch_profiles method.
result = client.fetch_profiles 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::GkeRecommender::V1::Profile.
  p item
end

Overloads:

  • #fetch_profiles(request, options = nil) ⇒ ::Gapic::Rest::PagedEnumerable<::Google::Cloud::GkeRecommender::V1::Profile>

    Pass arguments to fetch_profiles via a request object, either of type FetchProfilesRequest or an equivalent Hash.

    Parameters:

    • request (::Google::Cloud::GkeRecommender::V1::FetchProfilesRequest, ::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) (defaults to: nil) —

      Overrides the default settings for this call, e.g, timeout, retries etc. Optional.

  • #fetch_profiles(model: nil, model_server: nil, model_server_version: nil, performance_requirements: nil, page_size: nil, page_token: nil) ⇒ ::Gapic::Rest::PagedEnumerable<::Google::Cloud::GkeRecommender::V1::Profile>

    Pass arguments to fetch_profiles 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:

    • model (::String) (defaults to: nil) —

      Optional. The model to filter profiles by. Open-source models follow the Huggingface Hub owner/model_name format. If not provided, all models are returned. Use GkeInferenceQuickstart.FetchModels to find available models.

    • model_server (::String) (defaults to: nil) —

      Optional. The model server to filter profiles by. If not provided, all model servers are returned. Use GkeInferenceQuickstart.FetchModelServers to find available model servers for a given model.

    • model_server_version (::String) (defaults to: nil) —

      Optional. The model server version to filter profiles by. If not provided, all model server versions are returned. Use GkeInferenceQuickstart.FetchModelServerVersions to find available versions for a given model and server.

    • performance_requirements (::Google::Cloud::GkeRecommender::V1::PerformanceRequirements, ::Hash) (defaults to: nil) —

      Optional. The performance requirements to filter profiles. Profiles that do not meet these requirements are filtered out. If not provided, all profiles are returned.

    • page_size (::Integer) (defaults to: nil) —

      Optional. The target number of results to return in a single response. If not specified, a default value will be chosen by the service. Note that the response may include a partial list and a caller should only rely on the response's next_page_token to determine if there are more instances left to be queried.

    • page_token (::String) (defaults to: nil) —

      Optional. The value of next_page_token received from a previous FetchProfilesRequest call. Provide this to retrieve the subsequent page in a multi-page list of results. When paginating, all other parameters provided to FetchProfilesRequest must match the call that provided the page token.

Yields:

  • (result, operation) —

    Access the result along with the TransportOperation object

Yield Parameters:

Returns:

Raises:

  • (::Google::Cloud::Error) —

    if the REST call is aborted.



577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
 
# File 'lib/google/cloud/gke_recommender/v1/gke_inference_quickstart/rest/client.rb', line 577

def fetch_profiles request, options = nil
  raise ::ArgumentError, "request must be provided" if request.nil?

  request = ::Gapic::Protobuf.coerce request, to: ::Google::Cloud::GkeRecommender::V1::FetchProfilesRequest

  # Converts hash and nil to an options object
  options = ::Gapic::CallOptions.new(**options.to_h) if options.respond_to? :to_h

  # Customize the options with defaults
  call_metadata = @config.rpcs.fetch_profiles.metadata.to_h

  # Set x-goog-api-client, x-goog-user-project and x-goog-api-version headers
  call_metadata[:"x-goog-api-client"] ||= ::Gapic::Headers.x_goog_api_client \
    lib_name: @config.lib_name, lib_version: @config.lib_version,
    gapic_version: ::Google::Cloud::GkeRecommender::V1::VERSION,
    transports_version_send: [:rest]

  call_metadata[:"x-goog-api-version"] = API_VERSION unless API_VERSION.empty?
  call_metadata[:"x-goog-user-project"] = @quota_project_id if @quota_project_id

  options.apply_defaults timeout:      @config.rpcs.fetch_profiles.timeout,
                         metadata:     call_metadata,
                         retry_policy: @config.rpcs.fetch_profiles.retry_policy

  options.apply_defaults timeout:      @config.timeout,
                         metadata:     @config.metadata,
                         retry_policy: @config.retry_policy

  @gke_inference_quickstart_stub.fetch_profiles request, options do |result, operation|
    result = ::Gapic::Rest::PagedEnumerable.new @gke_inference_quickstart_stub, :fetch_profiles, "profile", request, result, options
    yield result, operation if block_given?
    throw :response, result
  end
rescue ::Gapic::Rest::Error => e
  raise ::Google::Cloud::Error.from_error(e)
end

#generate_optimized_manifest(request, options = nil) ⇒ ::Google::Cloud::GkeRecommender::V1::GenerateOptimizedManifestResponse #generate_optimized_manifest(model_server_info: nil, accelerator_type: nil, kubernetes_namespace: nil, performance_requirements: nil, storage_config: nil) ⇒ ::Google::Cloud::GkeRecommender::V1::GenerateOptimizedManifestResponse

Generates an optimized deployment manifest for a given model and model server, based on the specified accelerator, performance targets, and configurations. See Run best practice inference with GKE Inference Quickstart recipes for deployment details.

Examples:

Basic example

require "google/cloud/gke_recommender/v1"

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

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

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

# The returned object is of type Google::Cloud::GkeRecommender::V1::GenerateOptimizedManifestResponse.
p result

Overloads:

Yields:

  • (result, operation) —

    Access the result along with the TransportOperation object

Yield Parameters:

Returns:

Raises:

  • (::Google::Cloud::Error) —

    if the REST call is aborted.



680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
 
# File 'lib/google/cloud/gke_recommender/v1/gke_inference_quickstart/rest/client.rb', line 680

def generate_optimized_manifest request, options = nil
  raise ::ArgumentError, "request must be provided" if request.nil?

  request = ::Gapic::Protobuf.coerce request, to: ::Google::Cloud::GkeRecommender::V1::GenerateOptimizedManifestRequest

  # Converts hash and nil to an options object
  options = ::Gapic::CallOptions.new(**options.to_h) if options.respond_to? :to_h

  # Customize the options with defaults
  call_metadata = @config.rpcs.generate_optimized_manifest.metadata.to_h

  # Set x-goog-api-client, x-goog-user-project and x-goog-api-version headers
  call_metadata[:"x-goog-api-client"] ||= ::Gapic::Headers.x_goog_api_client \
    lib_name: @config.lib_name, lib_version: @config.lib_version,
    gapic_version: ::Google::Cloud::GkeRecommender::V1::VERSION,
    transports_version_send: [:rest]

  call_metadata[:"x-goog-api-version"] = API_VERSION unless API_VERSION.empty?
  call_metadata[:"x-goog-user-project"] = @quota_project_id if @quota_project_id

  options.apply_defaults timeout:      @config.rpcs.generate_optimized_manifest.timeout,
                         metadata:     call_metadata,
                         retry_policy: @config.rpcs.generate_optimized_manifest.retry_policy

  options.apply_defaults timeout:      @config.timeout,
                         metadata:     @config.metadata,
                         retry_policy: @config.retry_policy

  @gke_inference_quickstart_stub.generate_optimized_manifest request, options do |result, operation|
    yield result, operation if block_given?
  end
rescue ::Gapic::Rest::Error => e
  raise ::Google::Cloud::Error.from_error(e)
end

#logger ⇒ Logger

The logger used for request/response debug logging.

Returns:

  • (Logger) 


186
187
188
 
# File 'lib/google/cloud/gke_recommender/v1/gke_inference_quickstart/rest/client.rb', line 186

def logger
  @gke_inference_quickstart_stub.logger
end

#universe_domain ⇒ String

The effective universe domain

Returns:

  • (String) 


119
120
121
 
# File 'lib/google/cloud/gke_recommender/v1/gke_inference_quickstart/rest/client.rb', line 119

def universe_domain
  @gke_inference_quickstart_stub.universe_domain
end