Class: AWS.Bedrock
- Inherits:
-
AWS.Service
- Object
- AWS.Service
- AWS.Bedrock
- Identifier:
- bedrock
- API Version:
- 2023-04-20
- Defined in:
- (unknown)
Overview
Constructs a service interface object. Each API operation is exposed as a function on service.
Service Description
Describes the API operations for creating, managing, fine-turning, and evaluating Amazon Bedrock models.
Sending a Request Using Bedrock
var bedrock = new AWS.Bedrock();
bedrock.batchDeleteEvaluationJob(params, function (err, data) {
if (err) console.log(err, err.stack); // an error occurred
else console.log(data); // successful response
});
Locking the API Version
In order to ensure that the Bedrock object uses this specific API, you can
construct the object by passing the apiVersion option to the constructor:
var bedrock = new AWS.Bedrock({apiVersion: '2023-04-20'});
You can also set the API version globally in AWS.config.apiVersions using
the bedrock service identifier:
AWS.config.apiVersions = {
bedrock: '2023-04-20',
// other service API versions
};
var bedrock = new AWS.Bedrock();
Constructor Summary collapse
-
new AWS.Bedrock(options = {}) ⇒ Object
constructor
Constructs a service object.
Property Summary collapse
-
endpoint ⇒ AWS.Endpoint
readwrite
An Endpoint object representing the endpoint URL for service requests.
Properties inherited from AWS.Service
Method Summary collapse
-
batchDeleteEvaluationJob(params = {}, callback) ⇒ AWS.Request
Creates a batch deletion job.
-
createEvaluationJob(params = {}, callback) ⇒ AWS.Request
API operation for creating and managing Amazon Bedrock automatic model evaluation jobs and model evaluation jobs that use human workers.
-
createGuardrail(params = {}, callback) ⇒ AWS.Request
Creates a guardrail to block topics and to implement safeguards for your generative AI applications.
You can configure the following policies in a guardrail to avoid undesirable and harmful content, filter out denied topics and words, and remove sensitive information for privacy protection.
-
Content filters - Adjust filter strengths to block input prompts or model responses containing harmful content.
-
Denied topics - Define a set of topics that are undesirable in the context of your application.
-
-
createGuardrailVersion(params = {}, callback) ⇒ AWS.Request
Creates a version of the guardrail.
-
createModelCopyJob(params = {}, callback) ⇒ AWS.Request
Copies a model to another region so that it can be used there.
-
createModelCustomizationJob(params = {}, callback) ⇒ AWS.Request
Creates a fine-tuning job to customize a base model.
You specify the base foundation model and the location of the training data.
-
createModelImportJob(params = {}, callback) ⇒ AWS.Request
Creates a model import job to import model that you have customized in other environments, such as Amazon SageMaker.
-
createModelInvocationJob(params = {}, callback) ⇒ AWS.Request
Creates a batch inference job to invoke a model on multiple prompts.
-
createProvisionedModelThroughput(params = {}, callback) ⇒ AWS.Request
Creates dedicated throughput for a base or custom model with the model units and for the duration that you specify.
-
deleteCustomModel(params = {}, callback) ⇒ AWS.Request
Deletes a custom model that you created earlier.
-
deleteGuardrail(params = {}, callback) ⇒ AWS.Request
Deletes a guardrail.
-
To delete a guardrail, only specify the ARN of the guardrail in the
guardrailIdentifierfield.
-
-
deleteImportedModel(params = {}, callback) ⇒ AWS.Request
Deletes a custom model that you imported earlier.
-
deleteModelInvocationLoggingConfiguration(params = {}, callback) ⇒ AWS.Request
Delete the invocation logging.
-
deleteProvisionedModelThroughput(params = {}, callback) ⇒ AWS.Request
Deletes a Provisioned Throughput.
-
getCustomModel(params = {}, callback) ⇒ AWS.Request
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.
.
-
getEvaluationJob(params = {}, callback) ⇒ AWS.Request
Retrieves the properties associated with a model evaluation job, including the status of the job.
-
getFoundationModel(params = {}, callback) ⇒ AWS.Request
Get details about a Amazon Bedrock foundation model.
.
-
getGuardrail(params = {}, callback) ⇒ AWS.Request
Gets details about a guardrail.
-
getImportedModel(params = {}, callback) ⇒ AWS.Request
Gets properties associated with a customized model you imported.
-
getInferenceProfile(params = {}, callback) ⇒ AWS.Request
Gets information about an inference profile.
-
getModelCopyJob(params = {}, callback) ⇒ AWS.Request
Retrieves information about a model copy job.
-
getModelCustomizationJob(params = {}, callback) ⇒ AWS.Request
Retrieves the properties associated with a model-customization job, including the status of the job.
-
getModelImportJob(params = {}, callback) ⇒ AWS.Request
Retrieves the properties associated with import model job, including the status of the job.
-
getModelInvocationJob(params = {}, callback) ⇒ AWS.Request
Gets details about a batch inference job.
-
getModelInvocationLoggingConfiguration(params = {}, callback) ⇒ AWS.Request
Get the current configuration values for model invocation logging.
.
-
getProvisionedModelThroughput(params = {}, callback) ⇒ AWS.Request
Returns details for a Provisioned Throughput.
-
listCustomModels(params = {}, callback) ⇒ AWS.Request
Returns a list of the custom models that you have created with the
CreateModelCustomizationJoboperation.For more information, see Custom models in the Amazon Bedrock User Guide.
. -
listEvaluationJobs(params = {}, callback) ⇒ AWS.Request
Lists model evaluation jobs.
.
-
listFoundationModels(params = {}, callback) ⇒ AWS.Request
Lists Amazon Bedrock foundation models that you can use.
-
listGuardrails(params = {}, callback) ⇒ AWS.Request
Lists details about all the guardrails in an account.
-
listImportedModels(params = {}, callback) ⇒ AWS.Request
Returns a list of models you've imported.
-
listInferenceProfiles(params = {}, callback) ⇒ AWS.Request
Returns a list of inference profiles that you can use.
.
-
listModelCopyJobs(params = {}, callback) ⇒ AWS.Request
Returns a list of model copy jobs that you have submitted.
-
listModelCustomizationJobs(params = {}, callback) ⇒ AWS.Request
Returns a list of model customization jobs that you have submitted.
-
listModelImportJobs(params = {}, callback) ⇒ AWS.Request
Returns a list of import jobs you've submitted.
-
listModelInvocationJobs(params = {}, callback) ⇒ AWS.Request
Lists all batch inference jobs in the account.
-
listProvisionedModelThroughputs(params = {}, callback) ⇒ AWS.Request
Lists the Provisioned Throughputs in the account.
-
listTagsForResource(params = {}, callback) ⇒ AWS.Request
List the tags associated with the specified resource.
For more information, see Tagging resources in the Amazon Bedrock User Guide.
. -
putModelInvocationLoggingConfiguration(params = {}, callback) ⇒ AWS.Request
Set the configuration values for model invocation logging.
.
-
stopEvaluationJob(params = {}, callback) ⇒ AWS.Request
Stops an in progress model evaluation job.
.
-
stopModelCustomizationJob(params = {}, callback) ⇒ AWS.Request
Stops an active model customization job.
-
stopModelInvocationJob(params = {}, callback) ⇒ AWS.Request
Stops a batch inference job.
-
tagResource(params = {}, callback) ⇒ AWS.Request
Associate tags with a resource.
-
untagResource(params = {}, callback) ⇒ AWS.Request
Remove one or more tags from a resource.
-
updateGuardrail(params = {}, callback) ⇒ AWS.Request
Updates a guardrail with the values you specify.
-
Specify a
nameand optionaldescription. -
Specify messages for when the guardrail successfully blocks a prompt or a model response in the
blockedInputMessagingandblockedOutputsMessagingfields. -
Specify topics for the guardrail to deny in the
topicPolicyConfigobject.
-
-
updateProvisionedModelThroughput(params = {}, callback) ⇒ AWS.Request
Updates the name or associated model for a Provisioned Throughput.
-
waitFor(state, params = {}, callback) ⇒ AWS.Request
Waits for a given Bedrock resource.
Methods inherited from AWS.Service
makeRequest, makeUnauthenticatedRequest, setupRequestListeners, defineService
Constructor Details
new AWS.Bedrock(options = {}) ⇒ Object
Constructs a service object. This object has one method for each API operation.