Class: Google::Cloud::AIPlatform::V1::DeployRequest

Inherits:
Object
  • Object
show all
Extended by:
Protobuf::MessageExts::ClassMethods
Includes:
Protobuf::MessageExts
Defined in:
proto_docs/google/cloud/aiplatform/v1/model_garden_service.rb

Overview

Request message for ModelGardenService.Deploy.

Defined Under Namespace

Classes: DeployConfig, EndpointConfig, ModelConfig

Instance Attribute Summary collapse

Instance Attribute Details

#deploy_config ⇒ ::Google::Cloud::AIPlatform::V1::DeployRequest::DeployConfig

Returns Optional. The deploy config to use for the deployment. If not specified, the default deploy config will be used.

Returns:



82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
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
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
 
# File 'proto_docs/google/cloud/aiplatform/v1/model_garden_service.rb', line 82

class DeployRequest
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # The model config to use for the deployment.
  # @!attribute [rw] accept_eula
  #   @return [::Boolean]
  #     Optional. Whether the user accepts the End User License Agreement (EULA)
  #     for the model.
  # @!attribute [rw] hugging_face_access_token
  #   @return [::String]
  #     Optional. The Hugging Face read access token used to access the model
  #     artifacts of gated models.
  # @!attribute [rw] hugging_face_cache_enabled
  #   @return [::Boolean]
  #     Optional. If true, the model will deploy with a cached version instead of
  #     directly downloading the model artifacts from Hugging Face. This is
  #     suitable for VPC-SC users with limited internet access.
  # @!attribute [rw] model_display_name
  #   @return [::String]
  #     Optional. The user-specified display name of the uploaded model. If not
  #     set, a default name will be used.
  # @!attribute [rw] container_spec
  #   @return [::Google::Cloud::AIPlatform::V1::ModelContainerSpec]
  #     Optional. The specification of the container that is to be used when
  #     deploying. If not set, the default container spec will be used.
  # @!attribute [rw] model_user_id
  #   @return [::String]
  #     Optional. The ID to use for the uploaded Model, which will become the
  #     final component of the model resource name. When not provided, Vertex AI
  #     will generate a value for this ID. When Model Registry model is provided,
  #     this field will be ignored.
  #
  #     This value may be up to 63 characters, and valid characters are
  #     `[a-z0-9_-]`. The first character cannot be a number or hyphen.
  class ModelConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # The endpoint config to use for the deployment.
  # @!attribute [rw] endpoint_display_name
  #   @return [::String]
  #     Optional. The user-specified display name of the endpoint. If not set, a
  #     default name will be used.
  # @!attribute [rw] dedicated_endpoint_enabled
  #   @deprecated This field is deprecated and may be removed in the next major version update.
  #   @return [::Boolean]
  #     Optional. Deprecated. Use dedicated_endpoint_disabled instead.
  #     If true, the endpoint will be exposed through a
  #     dedicated DNS [Endpoint.dedicated_endpoint_dns]. Your request to the
  #     dedicated DNS will be isolated from other users' traffic and will have
  #     better performance and reliability. Note: Once you enabled dedicated
  #     endpoint, you won't be able to send request to the shared DNS
  #     \\{region}-aiplatform.googleapis.com. The limitations will be removed soon.
  # @!attribute [rw] dedicated_endpoint_disabled
  #   @return [::Boolean]
  #     Optional. By default, if dedicated endpoint is enabled, the endpoint will
  #     be exposed through a dedicated DNS [Endpoint.dedicated_endpoint_dns].
  #     Your request to the dedicated DNS will be isolated from other users'
  #     traffic and will have better performance and reliability. Note: Once you
  #     enabled dedicated endpoint, you won't be able to send request to the
  #     shared DNS \\{region}-aiplatform.googleapis.com. The limitations will be
  #     removed soon.
  #
  #     If this field is set to true, the dedicated endpoint will be disabled
  #     and the deployed model will be exposed through the shared DNS
  #     \\{region}-aiplatform.googleapis.com.
  # @!attribute [rw] endpoint_user_id
  #   @return [::String]
  #     Optional. Immutable. The ID to use for endpoint, which will become the
  #     final component of the endpoint resource name. If not provided, Vertex AI
  #     will generate a value for this ID.
  #
  #     If the first character is a letter, this value may be up to 63
  #     characters, and valid characters are `[a-z0-9-]`. The last character must
  #     be a letter or number.
  #
  #     If the first character is a number, this value may be up to 9 characters,
  #     and valid characters are `[0-9]` with no leading zeros.
  #
  #     When using HTTP/JSON, this field is populated
  #     based on a query string argument, such as `?endpoint_id=12345`. This is
  #     the fallback for fields that are not included in either the URI or the
  #     body.
  class EndpointConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # The deploy config to use for the deployment.
  # @!attribute [rw] dedicated_resources
  #   @return [::Google::Cloud::AIPlatform::V1::DedicatedResources]
  #     Optional. The dedicated resources to use for the endpoint. If not set,
  #     the default resources will be used.
  # @!attribute [rw] fast_tryout_enabled
  #   @return [::Boolean]
  #     Optional. If true, enable the QMT fast tryout feature for this model if
  #     possible.
  # @!attribute [rw] system_labels
  #   @return [::Google::Protobuf::Map{::String => ::String}]
  #     Optional. System labels for Model Garden deployments.
  #     These labels are managed by Google and for tracking purposes only.
  class DeployConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # @!attribute [rw] key
    #   @return [::String]
    # @!attribute [rw] value
    #   @return [::String]
    class SystemLabelsEntry
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end
end

#destination ⇒ ::String

Returns Required. The resource name of the Location to deploy the model in. Format: projects/{project}/locations/{location}.

Returns:

  • (::String) —

    Required. The resource name of the Location to deploy the model in. Format: projects/{project}/locations/{location}



82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
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
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
 
# File 'proto_docs/google/cloud/aiplatform/v1/model_garden_service.rb', line 82

class DeployRequest
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # The model config to use for the deployment.
  # @!attribute [rw] accept_eula
  #   @return [::Boolean]
  #     Optional. Whether the user accepts the End User License Agreement (EULA)
  #     for the model.
  # @!attribute [rw] hugging_face_access_token
  #   @return [::String]
  #     Optional. The Hugging Face read access token used to access the model
  #     artifacts of gated models.
  # @!attribute [rw] hugging_face_cache_enabled
  #   @return [::Boolean]
  #     Optional. If true, the model will deploy with a cached version instead of
  #     directly downloading the model artifacts from Hugging Face. This is
  #     suitable for VPC-SC users with limited internet access.
  # @!attribute [rw] model_display_name
  #   @return [::String]
  #     Optional. The user-specified display name of the uploaded model. If not
  #     set, a default name will be used.
  # @!attribute [rw] container_spec
  #   @return [::Google::Cloud::AIPlatform::V1::ModelContainerSpec]
  #     Optional. The specification of the container that is to be used when
  #     deploying. If not set, the default container spec will be used.
  # @!attribute [rw] model_user_id
  #   @return [::String]
  #     Optional. The ID to use for the uploaded Model, which will become the
  #     final component of the model resource name. When not provided, Vertex AI
  #     will generate a value for this ID. When Model Registry model is provided,
  #     this field will be ignored.
  #
  #     This value may be up to 63 characters, and valid characters are
  #     `[a-z0-9_-]`. The first character cannot be a number or hyphen.
  class ModelConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # The endpoint config to use for the deployment.
  # @!attribute [rw] endpoint_display_name
  #   @return [::String]
  #     Optional. The user-specified display name of the endpoint. If not set, a
  #     default name will be used.
  # @!attribute [rw] dedicated_endpoint_enabled
  #   @deprecated This field is deprecated and may be removed in the next major version update.
  #   @return [::Boolean]
  #     Optional. Deprecated. Use dedicated_endpoint_disabled instead.
  #     If true, the endpoint will be exposed through a
  #     dedicated DNS [Endpoint.dedicated_endpoint_dns]. Your request to the
  #     dedicated DNS will be isolated from other users' traffic and will have
  #     better performance and reliability. Note: Once you enabled dedicated
  #     endpoint, you won't be able to send request to the shared DNS
  #     \\{region}-aiplatform.googleapis.com. The limitations will be removed soon.
  # @!attribute [rw] dedicated_endpoint_disabled
  #   @return [::Boolean]
  #     Optional. By default, if dedicated endpoint is enabled, the endpoint will
  #     be exposed through a dedicated DNS [Endpoint.dedicated_endpoint_dns].
  #     Your request to the dedicated DNS will be isolated from other users'
  #     traffic and will have better performance and reliability. Note: Once you
  #     enabled dedicated endpoint, you won't be able to send request to the
  #     shared DNS \\{region}-aiplatform.googleapis.com. The limitations will be
  #     removed soon.
  #
  #     If this field is set to true, the dedicated endpoint will be disabled
  #     and the deployed model will be exposed through the shared DNS
  #     \\{region}-aiplatform.googleapis.com.
  # @!attribute [rw] endpoint_user_id
  #   @return [::String]
  #     Optional. Immutable. The ID to use for endpoint, which will become the
  #     final component of the endpoint resource name. If not provided, Vertex AI
  #     will generate a value for this ID.
  #
  #     If the first character is a letter, this value may be up to 63
  #     characters, and valid characters are `[a-z0-9-]`. The last character must
  #     be a letter or number.
  #
  #     If the first character is a number, this value may be up to 9 characters,
  #     and valid characters are `[0-9]` with no leading zeros.
  #
  #     When using HTTP/JSON, this field is populated
  #     based on a query string argument, such as `?endpoint_id=12345`. This is
  #     the fallback for fields that are not included in either the URI or the
  #     body.
  class EndpointConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # The deploy config to use for the deployment.
  # @!attribute [rw] dedicated_resources
  #   @return [::Google::Cloud::AIPlatform::V1::DedicatedResources]
  #     Optional. The dedicated resources to use for the endpoint. If not set,
  #     the default resources will be used.
  # @!attribute [rw] fast_tryout_enabled
  #   @return [::Boolean]
  #     Optional. If true, enable the QMT fast tryout feature for this model if
  #     possible.
  # @!attribute [rw] system_labels
  #   @return [::Google::Protobuf::Map{::String => ::String}]
  #     Optional. System labels for Model Garden deployments.
  #     These labels are managed by Google and for tracking purposes only.
  class DeployConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # @!attribute [rw] key
    #   @return [::String]
    # @!attribute [rw] value
    #   @return [::String]
    class SystemLabelsEntry
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end
end

#endpoint_config ⇒ ::Google::Cloud::AIPlatform::V1::DeployRequest::EndpointConfig

Returns Optional. The endpoint config to use for the deployment. If not specified, the default endpoint config will be used.

Returns:



82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
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
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
 
# File 'proto_docs/google/cloud/aiplatform/v1/model_garden_service.rb', line 82

class DeployRequest
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # The model config to use for the deployment.
  # @!attribute [rw] accept_eula
  #   @return [::Boolean]
  #     Optional. Whether the user accepts the End User License Agreement (EULA)
  #     for the model.
  # @!attribute [rw] hugging_face_access_token
  #   @return [::String]
  #     Optional. The Hugging Face read access token used to access the model
  #     artifacts of gated models.
  # @!attribute [rw] hugging_face_cache_enabled
  #   @return [::Boolean]
  #     Optional. If true, the model will deploy with a cached version instead of
  #     directly downloading the model artifacts from Hugging Face. This is
  #     suitable for VPC-SC users with limited internet access.
  # @!attribute [rw] model_display_name
  #   @return [::String]
  #     Optional. The user-specified display name of the uploaded model. If not
  #     set, a default name will be used.
  # @!attribute [rw] container_spec
  #   @return [::Google::Cloud::AIPlatform::V1::ModelContainerSpec]
  #     Optional. The specification of the container that is to be used when
  #     deploying. If not set, the default container spec will be used.
  # @!attribute [rw] model_user_id
  #   @return [::String]
  #     Optional. The ID to use for the uploaded Model, which will become the
  #     final component of the model resource name. When not provided, Vertex AI
  #     will generate a value for this ID. When Model Registry model is provided,
  #     this field will be ignored.
  #
  #     This value may be up to 63 characters, and valid characters are
  #     `[a-z0-9_-]`. The first character cannot be a number or hyphen.
  class ModelConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # The endpoint config to use for the deployment.
  # @!attribute [rw] endpoint_display_name
  #   @return [::String]
  #     Optional. The user-specified display name of the endpoint. If not set, a
  #     default name will be used.
  # @!attribute [rw] dedicated_endpoint_enabled
  #   @deprecated This field is deprecated and may be removed in the next major version update.
  #   @return [::Boolean]
  #     Optional. Deprecated. Use dedicated_endpoint_disabled instead.
  #     If true, the endpoint will be exposed through a
  #     dedicated DNS [Endpoint.dedicated_endpoint_dns]. Your request to the
  #     dedicated DNS will be isolated from other users' traffic and will have
  #     better performance and reliability. Note: Once you enabled dedicated
  #     endpoint, you won't be able to send request to the shared DNS
  #     \\{region}-aiplatform.googleapis.com. The limitations will be removed soon.
  # @!attribute [rw] dedicated_endpoint_disabled
  #   @return [::Boolean]
  #     Optional. By default, if dedicated endpoint is enabled, the endpoint will
  #     be exposed through a dedicated DNS [Endpoint.dedicated_endpoint_dns].
  #     Your request to the dedicated DNS will be isolated from other users'
  #     traffic and will have better performance and reliability. Note: Once you
  #     enabled dedicated endpoint, you won't be able to send request to the
  #     shared DNS \\{region}-aiplatform.googleapis.com. The limitations will be
  #     removed soon.
  #
  #     If this field is set to true, the dedicated endpoint will be disabled
  #     and the deployed model will be exposed through the shared DNS
  #     \\{region}-aiplatform.googleapis.com.
  # @!attribute [rw] endpoint_user_id
  #   @return [::String]
  #     Optional. Immutable. The ID to use for endpoint, which will become the
  #     final component of the endpoint resource name. If not provided, Vertex AI
  #     will generate a value for this ID.
  #
  #     If the first character is a letter, this value may be up to 63
  #     characters, and valid characters are `[a-z0-9-]`. The last character must
  #     be a letter or number.
  #
  #     If the first character is a number, this value may be up to 9 characters,
  #     and valid characters are `[0-9]` with no leading zeros.
  #
  #     When using HTTP/JSON, this field is populated
  #     based on a query string argument, such as `?endpoint_id=12345`. This is
  #     the fallback for fields that are not included in either the URI or the
  #     body.
  class EndpointConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # The deploy config to use for the deployment.
  # @!attribute [rw] dedicated_resources
  #   @return [::Google::Cloud::AIPlatform::V1::DedicatedResources]
  #     Optional. The dedicated resources to use for the endpoint. If not set,
  #     the default resources will be used.
  # @!attribute [rw] fast_tryout_enabled
  #   @return [::Boolean]
  #     Optional. If true, enable the QMT fast tryout feature for this model if
  #     possible.
  # @!attribute [rw] system_labels
  #   @return [::Google::Protobuf::Map{::String => ::String}]
  #     Optional. System labels for Model Garden deployments.
  #     These labels are managed by Google and for tracking purposes only.
  class DeployConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # @!attribute [rw] key
    #   @return [::String]
    # @!attribute [rw] value
    #   @return [::String]
    class SystemLabelsEntry
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end
end

#hugging_face_model_id ⇒ ::String

Returns The Hugging Face model to deploy. Format: Hugging Face model ID like google/gemma-2-2b-it.

Note: The following fields are mutually exclusive: hugging_face_model_id, publisher_model_name. If a field in that set is populated, all other fields in the set will automatically be cleared.

Returns:

  • (::String) —

    The Hugging Face model to deploy. Format: Hugging Face model ID like google/gemma-2-2b-it.

    Note: The following fields are mutually exclusive: hugging_face_model_id, publisher_model_name. If a field in that set is populated, all other fields in the set will automatically be cleared.



82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
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
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
 
# File 'proto_docs/google/cloud/aiplatform/v1/model_garden_service.rb', line 82

class DeployRequest
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # The model config to use for the deployment.
  # @!attribute [rw] accept_eula
  #   @return [::Boolean]
  #     Optional. Whether the user accepts the End User License Agreement (EULA)
  #     for the model.
  # @!attribute [rw] hugging_face_access_token
  #   @return [::String]
  #     Optional. The Hugging Face read access token used to access the model
  #     artifacts of gated models.
  # @!attribute [rw] hugging_face_cache_enabled
  #   @return [::Boolean]
  #     Optional. If true, the model will deploy with a cached version instead of
  #     directly downloading the model artifacts from Hugging Face. This is
  #     suitable for VPC-SC users with limited internet access.
  # @!attribute [rw] model_display_name
  #   @return [::String]
  #     Optional. The user-specified display name of the uploaded model. If not
  #     set, a default name will be used.
  # @!attribute [rw] container_spec
  #   @return [::Google::Cloud::AIPlatform::V1::ModelContainerSpec]
  #     Optional. The specification of the container that is to be used when
  #     deploying. If not set, the default container spec will be used.
  # @!attribute [rw] model_user_id
  #   @return [::String]
  #     Optional. The ID to use for the uploaded Model, which will become the
  #     final component of the model resource name. When not provided, Vertex AI
  #     will generate a value for this ID. When Model Registry model is provided,
  #     this field will be ignored.
  #
  #     This value may be up to 63 characters, and valid characters are
  #     `[a-z0-9_-]`. The first character cannot be a number or hyphen.
  class ModelConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # The endpoint config to use for the deployment.
  # @!attribute [rw] endpoint_display_name
  #   @return [::String]
  #     Optional. The user-specified display name of the endpoint. If not set, a
  #     default name will be used.
  # @!attribute [rw] dedicated_endpoint_enabled
  #   @deprecated This field is deprecated and may be removed in the next major version update.
  #   @return [::Boolean]
  #     Optional. Deprecated. Use dedicated_endpoint_disabled instead.
  #     If true, the endpoint will be exposed through a
  #     dedicated DNS [Endpoint.dedicated_endpoint_dns]. Your request to the
  #     dedicated DNS will be isolated from other users' traffic and will have
  #     better performance and reliability. Note: Once you enabled dedicated
  #     endpoint, you won't be able to send request to the shared DNS
  #     \\{region}-aiplatform.googleapis.com. The limitations will be removed soon.
  # @!attribute [rw] dedicated_endpoint_disabled
  #   @return [::Boolean]
  #     Optional. By default, if dedicated endpoint is enabled, the endpoint will
  #     be exposed through a dedicated DNS [Endpoint.dedicated_endpoint_dns].
  #     Your request to the dedicated DNS will be isolated from other users'
  #     traffic and will have better performance and reliability. Note: Once you
  #     enabled dedicated endpoint, you won't be able to send request to the
  #     shared DNS \\{region}-aiplatform.googleapis.com. The limitations will be
  #     removed soon.
  #
  #     If this field is set to true, the dedicated endpoint will be disabled
  #     and the deployed model will be exposed through the shared DNS
  #     \\{region}-aiplatform.googleapis.com.
  # @!attribute [rw] endpoint_user_id
  #   @return [::String]
  #     Optional. Immutable. The ID to use for endpoint, which will become the
  #     final component of the endpoint resource name. If not provided, Vertex AI
  #     will generate a value for this ID.
  #
  #     If the first character is a letter, this value may be up to 63
  #     characters, and valid characters are `[a-z0-9-]`. The last character must
  #     be a letter or number.
  #
  #     If the first character is a number, this value may be up to 9 characters,
  #     and valid characters are `[0-9]` with no leading zeros.
  #
  #     When using HTTP/JSON, this field is populated
  #     based on a query string argument, such as `?endpoint_id=12345`. This is
  #     the fallback for fields that are not included in either the URI or the
  #     body.
  class EndpointConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # The deploy config to use for the deployment.
  # @!attribute [rw] dedicated_resources
  #   @return [::Google::Cloud::AIPlatform::V1::DedicatedResources]
  #     Optional. The dedicated resources to use for the endpoint. If not set,
  #     the default resources will be used.
  # @!attribute [rw] fast_tryout_enabled
  #   @return [::Boolean]
  #     Optional. If true, enable the QMT fast tryout feature for this model if
  #     possible.
  # @!attribute [rw] system_labels
  #   @return [::Google::Protobuf::Map{::String => ::String}]
  #     Optional. System labels for Model Garden deployments.
  #     These labels are managed by Google and for tracking purposes only.
  class DeployConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # @!attribute [rw] key
    #   @return [::String]
    # @!attribute [rw] value
    #   @return [::String]
    class SystemLabelsEntry
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end
end

#model_config ⇒ ::Google::Cloud::AIPlatform::V1::DeployRequest::ModelConfig

Returns Optional. The model config to use for the deployment. If not specified, the default model config will be used.

Returns:



82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
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
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
 
# File 'proto_docs/google/cloud/aiplatform/v1/model_garden_service.rb', line 82

class DeployRequest
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # The model config to use for the deployment.
  # @!attribute [rw] accept_eula
  #   @return [::Boolean]
  #     Optional. Whether the user accepts the End User License Agreement (EULA)
  #     for the model.
  # @!attribute [rw] hugging_face_access_token
  #   @return [::String]
  #     Optional. The Hugging Face read access token used to access the model
  #     artifacts of gated models.
  # @!attribute [rw] hugging_face_cache_enabled
  #   @return [::Boolean]
  #     Optional. If true, the model will deploy with a cached version instead of
  #     directly downloading the model artifacts from Hugging Face. This is
  #     suitable for VPC-SC users with limited internet access.
  # @!attribute [rw] model_display_name
  #   @return [::String]
  #     Optional. The user-specified display name of the uploaded model. If not
  #     set, a default name will be used.
  # @!attribute [rw] container_spec
  #   @return [::Google::Cloud::AIPlatform::V1::ModelContainerSpec]
  #     Optional. The specification of the container that is to be used when
  #     deploying. If not set, the default container spec will be used.
  # @!attribute [rw] model_user_id
  #   @return [::String]
  #     Optional. The ID to use for the uploaded Model, which will become the
  #     final component of the model resource name. When not provided, Vertex AI
  #     will generate a value for this ID. When Model Registry model is provided,
  #     this field will be ignored.
  #
  #     This value may be up to 63 characters, and valid characters are
  #     `[a-z0-9_-]`. The first character cannot be a number or hyphen.
  class ModelConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # The endpoint config to use for the deployment.
  # @!attribute [rw] endpoint_display_name
  #   @return [::String]
  #     Optional. The user-specified display name of the endpoint. If not set, a
  #     default name will be used.
  # @!attribute [rw] dedicated_endpoint_enabled
  #   @deprecated This field is deprecated and may be removed in the next major version update.
  #   @return [::Boolean]
  #     Optional. Deprecated. Use dedicated_endpoint_disabled instead.
  #     If true, the endpoint will be exposed through a
  #     dedicated DNS [Endpoint.dedicated_endpoint_dns]. Your request to the
  #     dedicated DNS will be isolated from other users' traffic and will have
  #     better performance and reliability. Note: Once you enabled dedicated
  #     endpoint, you won't be able to send request to the shared DNS
  #     \\{region}-aiplatform.googleapis.com. The limitations will be removed soon.
  # @!attribute [rw] dedicated_endpoint_disabled
  #   @return [::Boolean]
  #     Optional. By default, if dedicated endpoint is enabled, the endpoint will
  #     be exposed through a dedicated DNS [Endpoint.dedicated_endpoint_dns].
  #     Your request to the dedicated DNS will be isolated from other users'
  #     traffic and will have better performance and reliability. Note: Once you
  #     enabled dedicated endpoint, you won't be able to send request to the
  #     shared DNS \\{region}-aiplatform.googleapis.com. The limitations will be
  #     removed soon.
  #
  #     If this field is set to true, the dedicated endpoint will be disabled
  #     and the deployed model will be exposed through the shared DNS
  #     \\{region}-aiplatform.googleapis.com.
  # @!attribute [rw] endpoint_user_id
  #   @return [::String]
  #     Optional. Immutable. The ID to use for endpoint, which will become the
  #     final component of the endpoint resource name. If not provided, Vertex AI
  #     will generate a value for this ID.
  #
  #     If the first character is a letter, this value may be up to 63
  #     characters, and valid characters are `[a-z0-9-]`. The last character must
  #     be a letter or number.
  #
  #     If the first character is a number, this value may be up to 9 characters,
  #     and valid characters are `[0-9]` with no leading zeros.
  #
  #     When using HTTP/JSON, this field is populated
  #     based on a query string argument, such as `?endpoint_id=12345`. This is
  #     the fallback for fields that are not included in either the URI or the
  #     body.
  class EndpointConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # The deploy config to use for the deployment.
  # @!attribute [rw] dedicated_resources
  #   @return [::Google::Cloud::AIPlatform::V1::DedicatedResources]
  #     Optional. The dedicated resources to use for the endpoint. If not set,
  #     the default resources will be used.
  # @!attribute [rw] fast_tryout_enabled
  #   @return [::Boolean]
  #     Optional. If true, enable the QMT fast tryout feature for this model if
  #     possible.
  # @!attribute [rw] system_labels
  #   @return [::Google::Protobuf::Map{::String => ::String}]
  #     Optional. System labels for Model Garden deployments.
  #     These labels are managed by Google and for tracking purposes only.
  class DeployConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # @!attribute [rw] key
    #   @return [::String]
    # @!attribute [rw] value
    #   @return [::String]
    class SystemLabelsEntry
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end
end

#publisher_model_name ⇒ ::String

Returns The Model Garden model to deploy. Format: publishers/{publisher}/models/{publisher_model}@{version_id}, or publishers/hf-{hugging-face-author}/models/{hugging-face-model-name}@001.

Note: The following fields are mutually exclusive: publisher_model_name, hugging_face_model_id. If a field in that set is populated, all other fields in the set will automatically be cleared.

Returns:

  • (::String) —

    The Model Garden model to deploy. Format: publishers/{publisher}/models/{publisher_model}@{version_id}, or publishers/hf-{hugging-face-author}/models/{hugging-face-model-name}@001.

    Note: The following fields are mutually exclusive: publisher_model_name, hugging_face_model_id. If a field in that set is populated, all other fields in the set will automatically be cleared.



82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
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
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
 
# File 'proto_docs/google/cloud/aiplatform/v1/model_garden_service.rb', line 82

class DeployRequest
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # The model config to use for the deployment.
  # @!attribute [rw] accept_eula
  #   @return [::Boolean]
  #     Optional. Whether the user accepts the End User License Agreement (EULA)
  #     for the model.
  # @!attribute [rw] hugging_face_access_token
  #   @return [::String]
  #     Optional. The Hugging Face read access token used to access the model
  #     artifacts of gated models.
  # @!attribute [rw] hugging_face_cache_enabled
  #   @return [::Boolean]
  #     Optional. If true, the model will deploy with a cached version instead of
  #     directly downloading the model artifacts from Hugging Face. This is
  #     suitable for VPC-SC users with limited internet access.
  # @!attribute [rw] model_display_name
  #   @return [::String]
  #     Optional. The user-specified display name of the uploaded model. If not
  #     set, a default name will be used.
  # @!attribute [rw] container_spec
  #   @return [::Google::Cloud::AIPlatform::V1::ModelContainerSpec]
  #     Optional. The specification of the container that is to be used when
  #     deploying. If not set, the default container spec will be used.
  # @!attribute [rw] model_user_id
  #   @return [::String]
  #     Optional. The ID to use for the uploaded Model, which will become the
  #     final component of the model resource name. When not provided, Vertex AI
  #     will generate a value for this ID. When Model Registry model is provided,
  #     this field will be ignored.
  #
  #     This value may be up to 63 characters, and valid characters are
  #     `[a-z0-9_-]`. The first character cannot be a number or hyphen.
  class ModelConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # The endpoint config to use for the deployment.
  # @!attribute [rw] endpoint_display_name
  #   @return [::String]
  #     Optional. The user-specified display name of the endpoint. If not set, a
  #     default name will be used.
  # @!attribute [rw] dedicated_endpoint_enabled
  #   @deprecated This field is deprecated and may be removed in the next major version update.
  #   @return [::Boolean]
  #     Optional. Deprecated. Use dedicated_endpoint_disabled instead.
  #     If true, the endpoint will be exposed through a
  #     dedicated DNS [Endpoint.dedicated_endpoint_dns]. Your request to the
  #     dedicated DNS will be isolated from other users' traffic and will have
  #     better performance and reliability. Note: Once you enabled dedicated
  #     endpoint, you won't be able to send request to the shared DNS
  #     \\{region}-aiplatform.googleapis.com. The limitations will be removed soon.
  # @!attribute [rw] dedicated_endpoint_disabled
  #   @return [::Boolean]
  #     Optional. By default, if dedicated endpoint is enabled, the endpoint will
  #     be exposed through a dedicated DNS [Endpoint.dedicated_endpoint_dns].
  #     Your request to the dedicated DNS will be isolated from other users'
  #     traffic and will have better performance and reliability. Note: Once you
  #     enabled dedicated endpoint, you won't be able to send request to the
  #     shared DNS \\{region}-aiplatform.googleapis.com. The limitations will be
  #     removed soon.
  #
  #     If this field is set to true, the dedicated endpoint will be disabled
  #     and the deployed model will be exposed through the shared DNS
  #     \\{region}-aiplatform.googleapis.com.
  # @!attribute [rw] endpoint_user_id
  #   @return [::String]
  #     Optional. Immutable. The ID to use for endpoint, which will become the
  #     final component of the endpoint resource name. If not provided, Vertex AI
  #     will generate a value for this ID.
  #
  #     If the first character is a letter, this value may be up to 63
  #     characters, and valid characters are `[a-z0-9-]`. The last character must
  #     be a letter or number.
  #
  #     If the first character is a number, this value may be up to 9 characters,
  #     and valid characters are `[0-9]` with no leading zeros.
  #
  #     When using HTTP/JSON, this field is populated
  #     based on a query string argument, such as `?endpoint_id=12345`. This is
  #     the fallback for fields that are not included in either the URI or the
  #     body.
  class EndpointConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # The deploy config to use for the deployment.
  # @!attribute [rw] dedicated_resources
  #   @return [::Google::Cloud::AIPlatform::V1::DedicatedResources]
  #     Optional. The dedicated resources to use for the endpoint. If not set,
  #     the default resources will be used.
  # @!attribute [rw] fast_tryout_enabled
  #   @return [::Boolean]
  #     Optional. If true, enable the QMT fast tryout feature for this model if
  #     possible.
  # @!attribute [rw] system_labels
  #   @return [::Google::Protobuf::Map{::String => ::String}]
  #     Optional. System labels for Model Garden deployments.
  #     These labels are managed by Google and for tracking purposes only.
  class DeployConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # @!attribute [rw] key
    #   @return [::String]
    # @!attribute [rw] value
    #   @return [::String]
    class SystemLabelsEntry
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end
end