Class: Aws::Bedrock::Client
- Inherits:
-
Seahorse::Client::Base
- Object
- Seahorse::Client::Base
- Aws::Bedrock::Client
- Includes:
- ClientStubs
- Defined in:
- gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb
Overview
An API client for Bedrock. To construct a client, you need to configure a :region
and :credentials
.
client = Aws::Bedrock::Client.new(
region: region_name,
credentials: credentials,
# ...
)
For details on configuring region and credentials see the developer guide.
See #initialize for a full list of supported configuration options.
Instance Attribute Summary
Attributes inherited from Seahorse::Client::Base
API Operations collapse
-
#create_evaluation_job(params = {}) ⇒ Types::CreateEvaluationJobResponse
API operation for creating and managing Amazon Bedrock automatic model evaluation jobs and model evaluation jobs that use human workers.
-
#create_guardrail(params = {}) ⇒ Types::CreateGuardrailResponse
Creates a guardrail to block topics and to filter out harmful content.
-
#create_guardrail_version(params = {}) ⇒ Types::CreateGuardrailVersionResponse
Creates a version of the guardrail.
-
#create_model_customization_job(params = {}) ⇒ Types::CreateModelCustomizationJobResponse
Creates a fine-tuning job to customize a base model.
-
#create_provisioned_model_throughput(params = {}) ⇒ Types::CreateProvisionedModelThroughputResponse
Creates dedicated throughput for a base or custom model with the model units and for the duration that you specify.
-
#delete_custom_model(params = {}) ⇒ Struct
Deletes a custom model that you created earlier.
-
#delete_guardrail(params = {}) ⇒ Struct
Deletes a guardrail.
-
#delete_model_invocation_logging_configuration(params = {}) ⇒ Struct
Delete the invocation logging.
-
#delete_provisioned_model_throughput(params = {}) ⇒ Struct
Deletes a Provisioned Throughput.
-
#get_custom_model(params = {}) ⇒ Types::GetCustomModelResponse
Get the properties associated with a Amazon Bedrock custom model that you have created.For more information, see [Custom models][1] in the Amazon Bedrock User Guide.
-
#get_evaluation_job(params = {}) ⇒ Types::GetEvaluationJobResponse
Retrieves the properties associated with a model evaluation job, including the status of the job.
-
#get_foundation_model(params = {}) ⇒ Types::GetFoundationModelResponse
Get details about a Amazon Bedrock foundation model.
-
#get_guardrail(params = {}) ⇒ Types::GetGuardrailResponse
Gets details about a guardrail.
-
#get_model_customization_job(params = {}) ⇒ Types::GetModelCustomizationJobResponse
Retrieves the properties associated with a model-customization job, including the status of the job.
-
#get_model_invocation_logging_configuration(params = {}) ⇒ Types::GetModelInvocationLoggingConfigurationResponse
Get the current configuration values for model invocation logging.
-
#get_provisioned_model_throughput(params = {}) ⇒ Types::GetProvisionedModelThroughputResponse
Returns details for a Provisioned Throughput.
-
#list_custom_models(params = {}) ⇒ Types::ListCustomModelsResponse
Returns a list of the custom models that you have created with the
CreateModelCustomizationJob
operation. -
#list_evaluation_jobs(params = {}) ⇒ Types::ListEvaluationJobsResponse
Lists model evaluation jobs.
-
#list_foundation_models(params = {}) ⇒ Types::ListFoundationModelsResponse
Lists Amazon Bedrock foundation models that you can use.
-
#list_guardrails(params = {}) ⇒ Types::ListGuardrailsResponse
Lists details about all the guardrails in an account.
-
#list_model_customization_jobs(params = {}) ⇒ Types::ListModelCustomizationJobsResponse
Returns a list of model customization jobs that you have submitted.
-
#list_provisioned_model_throughputs(params = {}) ⇒ Types::ListProvisionedModelThroughputsResponse
Lists the Provisioned Throughputs in the account.
-
#list_tags_for_resource(params = {}) ⇒ Types::ListTagsForResourceResponse
List the tags associated with the specified resource.
-
#put_model_invocation_logging_configuration(params = {}) ⇒ Struct
Set the configuration values for model invocation logging.
-
#stop_evaluation_job(params = {}) ⇒ Struct
Stops an in progress model evaluation job.
-
#stop_model_customization_job(params = {}) ⇒ Struct
Stops an active model customization job.
-
#tag_resource(params = {}) ⇒ Struct
Associate tags with a resource.
-
#untag_resource(params = {}) ⇒ Struct
Remove one or more tags from a resource.
-
#update_guardrail(params = {}) ⇒ Types::UpdateGuardrailResponse
Updates a guardrail with the values you specify.
-
#update_provisioned_model_throughput(params = {}) ⇒ Struct
Updates the name or associated model for a Provisioned Throughput.
Instance Method Summary collapse
-
#initialize(options) ⇒ Client
constructor
A new instance of Client.
Methods included from ClientStubs
#api_requests, #stub_data, #stub_responses
Methods inherited from Seahorse::Client::Base
add_plugin, api, clear_plugins, define, new, #operation_names, plugins, remove_plugin, set_api, set_plugins
Methods included from Seahorse::Client::HandlerBuilder
#handle, #handle_request, #handle_response
Constructor Details
#initialize(options) ⇒ Client
Returns a new instance of Client.
409 410 411 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 409 def initialize(*args) super end |
Instance Method Details
#create_evaluation_job(params = {}) ⇒ Types::CreateEvaluationJobResponse
API operation for creating and managing Amazon Bedrock automatic model evaluation jobs and model evaluation jobs that use human workers. To learn more about the requirements for creating a model evaluation job see, Model evaluations.
559 560 561 562 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 559 def create_evaluation_job(params = {}, = {}) req = build_request(:create_evaluation_job, params) req.send_request() end |
#create_guardrail(params = {}) ⇒ Types::CreateGuardrailResponse
Creates a guardrail to block topics and to filter out harmful content.
Specify a
name
and optionaldescription
.Specify messages for when the guardrail successfully blocks a prompt or a model response in the
blockedInputMessaging
andblockedOutputsMessaging
fields.Specify topics for the guardrail to deny in the
topicPolicyConfig
object. Each GuardrailTopicConfig object in thetopicsConfig
list pertains to one topic.Give a
name
anddescription
so that the guardrail can properly identify the topic.Specify
DENY
in thetype
field.(Optional) Provide up to five prompts that you would categorize as belonging to the topic in the
examples
list.
Specify filter strengths for the harmful categories defined in Amazon Bedrock in the
contentPolicyConfig
object. Each GuardrailContentFilterConfig object in thefiltersConfig
list pertains to a harmful category. For more information, see Content filters. For more information about the fields in a content filter, see GuardrailContentFilterConfig.Specify the category in the
type
field.Specify the strength of the filter for prompts in the
inputStrength
field and for model responses in thestrength
field of the GuardrailContentFilterConfig.
(Optional) For security, include the ARN of a KMS key in the
kmsKeyId
field.(Optional) Attach any tags to the guardrail in the
tags
object. For more information, see Tag resources.
736 737 738 739 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 736 def create_guardrail(params = {}, = {}) req = build_request(:create_guardrail, params) req.send_request() end |
#create_guardrail_version(params = {}) ⇒ Types::CreateGuardrailVersionResponse
Creates a version of the guardrail. Use this API to create a snapshot of the guardrail when you are satisfied with a configuration, or to compare the configuration with another version.
787 788 789 790 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 787 def create_guardrail_version(params = {}, = {}) req = build_request(:create_guardrail_version, params) req.send_request() end |
#create_model_customization_job(params = {}) ⇒ Types::CreateModelCustomizationJobResponse
Creates a fine-tuning job to customize a base model.
You specify the base foundation model and the location of the training data. After the model-customization job completes successfully, your custom model resource will be ready to use. Amazon Bedrock returns validation loss metrics and output generations after the job completes.
For information on the format of training and validation data, see Prepare the datasets.
Model-customization jobs are asynchronous and the completion time
depends on the base model and the training/validation data size. To
monitor a job, use the GetModelCustomizationJob
operation to
retrieve the job status.
For more information, see Custom models in the Amazon Bedrock User Guide.
936 937 938 939 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 936 def create_model_customization_job(params = {}, = {}) req = build_request(:create_model_customization_job, params) req.send_request() end |
#create_provisioned_model_throughput(params = {}) ⇒ Types::CreateProvisionedModelThroughputResponse
Creates dedicated throughput for a base or custom model with the model units and for the duration that you specify. For pricing details, see Amazon Bedrock Pricing. For more information, see Provisioned Throughput in the Amazon Bedrock User Guide.
1043 1044 1045 1046 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 1043 def create_provisioned_model_throughput(params = {}, = {}) req = build_request(:create_provisioned_model_throughput, params) req.send_request() end |
#delete_custom_model(params = {}) ⇒ Struct
Deletes a custom model that you created earlier. For more information, see Custom models in the Amazon Bedrock User Guide.
1070 1071 1072 1073 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 1070 def delete_custom_model(params = {}, = {}) req = build_request(:delete_custom_model, params) req.send_request() end |
#delete_guardrail(params = {}) ⇒ Struct
Deletes a guardrail.
To delete a guardrail, only specify the ARN of the guardrail in the
guardrailIdentifier
field. If you delete a guardrail, all of its versions will be deleted.To delete a version of a guardrail, specify the ARN of the guardrail in the
guardrailIdentifier
field and the version in theguardrailVersion
field.
1104 1105 1106 1107 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 1104 def delete_guardrail(params = {}, = {}) req = build_request(:delete_guardrail, params) req.send_request() end |
#delete_model_invocation_logging_configuration(params = {}) ⇒ Struct
Delete the invocation logging.
1117 1118 1119 1120 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 1117 def delete_model_invocation_logging_configuration(params = {}, = {}) req = build_request(:delete_model_invocation_logging_configuration, params) req.send_request() end |
#delete_provisioned_model_throughput(params = {}) ⇒ Struct
Deletes a Provisioned Throughput. You can't delete a Provisioned Throughput before the commitment term is over. For more information, see Provisioned Throughput in the Amazon Bedrock User Guide.
1145 1146 1147 1148 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 1145 def delete_provisioned_model_throughput(params = {}, = {}) req = build_request(:delete_provisioned_model_throughput, params) req.send_request() end |
#get_custom_model(params = {}) ⇒ Types::GetCustomModelResponse
Get the properties associated with a Amazon Bedrock custom model that you have created.For more information, see Custom models in the Amazon Bedrock User Guide.
1208 1209 1210 1211 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 1208 def get_custom_model(params = {}, = {}) req = build_request(:get_custom_model, params) req.send_request() end |
#get_evaluation_job(params = {}) ⇒ Types::GetEvaluationJobResponse
Retrieves the properties associated with a model evaluation job, including the status of the job. For more information, see Model evaluations.
1286 1287 1288 1289 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 1286 def get_evaluation_job(params = {}, = {}) req = build_request(:get_evaluation_job, params) req.send_request() end |
#get_foundation_model(params = {}) ⇒ Types::GetFoundationModelResponse
Get details about a Amazon Bedrock foundation model.
1327 1328 1329 1330 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 1327 def get_foundation_model(params = {}, = {}) req = build_request(:get_foundation_model, params) req.send_request() end |
#get_guardrail(params = {}) ⇒ Types::GetGuardrailResponse
Gets details about a guardrail. If you don't specify a version, the
response returns details for the DRAFT
version.
1414 1415 1416 1417 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 1414 def get_guardrail(params = {}, = {}) req = build_request(:get_guardrail, params) req.send_request() end |
#get_model_customization_job(params = {}) ⇒ Types::GetModelCustomizationJobResponse
Retrieves the properties associated with a model-customization job, including the status of the job. For more information, see Custom models in the Amazon Bedrock User Guide.
1494 1495 1496 1497 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 1494 def get_model_customization_job(params = {}, = {}) req = build_request(:get_model_customization_job, params) req.send_request() end |
#get_model_invocation_logging_configuration(params = {}) ⇒ Types::GetModelInvocationLoggingConfigurationResponse
Get the current configuration values for model invocation logging.
1521 1522 1523 1524 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 1521 def get_model_invocation_logging_configuration(params = {}, = {}) req = build_request(:get_model_invocation_logging_configuration, params) req.send_request() end |
#get_provisioned_model_throughput(params = {}) ⇒ Types::GetProvisionedModelThroughputResponse
Returns details for a Provisioned Throughput. For more information, see Provisioned Throughput in the Amazon Bedrock User Guide.
1578 1579 1580 1581 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 1578 def get_provisioned_model_throughput(params = {}, = {}) req = build_request(:get_provisioned_model_throughput, params) req.send_request() end |
#list_custom_models(params = {}) ⇒ Types::ListCustomModelsResponse
Returns a list of the custom models that you have created with the
CreateModelCustomizationJob
operation.
For more information, see Custom models in the Amazon Bedrock User Guide.
The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.
1659 1660 1661 1662 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 1659 def list_custom_models(params = {}, = {}) req = build_request(:list_custom_models, params) req.send_request() end |
#list_evaluation_jobs(params = {}) ⇒ Types::ListEvaluationJobsResponse
Lists model evaluation jobs.
The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.
1731 1732 1733 1734 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 1731 def list_evaluation_jobs(params = {}, = {}) req = build_request(:list_evaluation_jobs, params) req.send_request() end |
#list_foundation_models(params = {}) ⇒ Types::ListFoundationModelsResponse
Lists Amazon Bedrock foundation models that you can use. You can filter the results with the request parameters. For more information, see Foundation models in the Amazon Bedrock User Guide.
1803 1804 1805 1806 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 1803 def list_foundation_models(params = {}, = {}) req = build_request(:list_foundation_models, params) req.send_request() end |
#list_guardrails(params = {}) ⇒ Types::ListGuardrailsResponse
Lists details about all the guardrails in an account. To list the
DRAFT
version of all your guardrails, don't specify the
guardrailIdentifier
field. To list all versions of a guardrail,
specify the ARN of the guardrail in the guardrailIdentifier
field.
You can set the maximum number of results to return in a response in
the maxResults
field. If there are more results than the number you
set, the response returns a nextToken
that you can send in another
ListGuardrails
request to see the next batch of results.
The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.
1861 1862 1863 1864 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 1861 def list_guardrails(params = {}, = {}) req = build_request(:list_guardrails, params) req.send_request() end |
#list_model_customization_jobs(params = {}) ⇒ Types::ListModelCustomizationJobsResponse
Returns a list of model customization jobs that you have submitted. You can filter the jobs to return based on one or more criteria.
For more information, see Custom models in the Amazon Bedrock User Guide.
The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.
1941 1942 1943 1944 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 1941 def list_model_customization_jobs(params = {}, = {}) req = build_request(:list_model_customization_jobs, params) req.send_request() end |
#list_provisioned_model_throughputs(params = {}) ⇒ Types::ListProvisionedModelThroughputsResponse
Lists the Provisioned Throughputs in the account. For more information, see Provisioned Throughput in the Amazon Bedrock User Guide.
The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.
2035 2036 2037 2038 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 2035 def list_provisioned_model_throughputs(params = {}, = {}) req = build_request(:list_provisioned_model_throughputs, params) req.send_request() end |
#list_tags_for_resource(params = {}) ⇒ Types::ListTagsForResourceResponse
List the tags associated with the specified resource.
For more information, see Tagging resources in the Amazon Bedrock User Guide.
2072 2073 2074 2075 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 2072 def (params = {}, = {}) req = build_request(:list_tags_for_resource, params) req.send_request() end |
#put_model_invocation_logging_configuration(params = {}) ⇒ Struct
Set the configuration values for model invocation logging.
2110 2111 2112 2113 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 2110 def put_model_invocation_logging_configuration(params = {}, = {}) req = build_request(:put_model_invocation_logging_configuration, params) req.send_request() end |
#stop_evaluation_job(params = {}) ⇒ Struct
Stops an in progress model evaluation job.
2132 2133 2134 2135 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 2132 def stop_evaluation_job(params = {}, = {}) req = build_request(:stop_evaluation_job, params) req.send_request() end |
#stop_model_customization_job(params = {}) ⇒ Struct
Stops an active model customization job. For more information, see Custom models in the Amazon Bedrock User Guide.
2159 2160 2161 2162 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 2159 def stop_model_customization_job(params = {}, = {}) req = build_request(:stop_model_customization_job, params) req.send_request() end |
#tag_resource(params = {}) ⇒ Struct
Associate tags with a resource. For more information, see Tagging resources in the Amazon Bedrock User Guide.
2195 2196 2197 2198 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 2195 def tag_resource(params = {}, = {}) req = build_request(:tag_resource, params) req.send_request() end |
#untag_resource(params = {}) ⇒ Struct
Remove one or more tags from a resource. For more information, see Tagging resources in the Amazon Bedrock User Guide.
2226 2227 2228 2229 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 2226 def untag_resource(params = {}, = {}) req = build_request(:untag_resource, params) req.send_request() end |
#update_guardrail(params = {}) ⇒ Types::UpdateGuardrailResponse
Updates a guardrail with the values you specify.
Specify a
name
and optionaldescription
.Specify messages for when the guardrail successfully blocks a prompt or a model response in the
blockedInputMessaging
andblockedOutputsMessaging
fields.Specify topics for the guardrail to deny in the
topicPolicyConfig
object. Each GuardrailTopicConfig object in thetopicsConfig
list pertains to one topic.Give a
name
anddescription
so that the guardrail can properly identify the topic.Specify
DENY
in thetype
field.(Optional) Provide up to five prompts that you would categorize as belonging to the topic in the
examples
list.
Specify filter strengths for the harmful categories defined in Amazon Bedrock in the
contentPolicyConfig
object. Each GuardrailContentFilterConfig object in thefiltersConfig
list pertains to a harmful category. For more information, see Content filters. For more information about the fields in a content filter, see GuardrailContentFilterConfig.Specify the category in the
type
field.Specify the strength of the filter for prompts in the
inputStrength
field and for model responses in thestrength
field of the GuardrailContentFilterConfig.
(Optional) For security, include the ARN of a KMS key in the
kmsKeyId
field.(Optional) Attach any tags to the guardrail in the
tags
object. For more information, see Tag resources.
2383 2384 2385 2386 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 2383 def update_guardrail(params = {}, = {}) req = build_request(:update_guardrail, params) req.send_request() end |
#update_provisioned_model_throughput(params = {}) ⇒ Struct
Updates the name or associated model for a Provisioned Throughput. For more information, see Provisioned Throughput in the Amazon Bedrock User Guide.
2430 2431 2432 2433 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 2430 def update_provisioned_model_throughput(params = {}, = {}) req = build_request(:update_provisioned_model_throughput, params) req.send_request() end |