BedrockClient#

Index > Bedrock > BedrockClient

Auto-generated documentation for Bedrock type annotations stubs module mypy-boto3-bedrock.

BedrockClient#

Type annotations and code completion for boto3.client("bedrock"). boto3 documentation

# BedrockClient usage example

from boto3.session import Session
from mypy_boto3_bedrock.client import BedrockClient

def get_bedrock_client() -> BedrockClient:
    return Session().client("bedrock")

Exceptions#

boto3 client exceptions are generated in runtime. This class provides code completion for boto3.client("bedrock").exceptions structure.

# Exceptions.exceptions usage example

client = boto3.client("bedrock")

try:
    do_something(client)
except (
    client.exceptions.AccessDeniedException,
    client.exceptions.ClientError,
    client.exceptions.ConflictException,
    client.exceptions.InternalServerException,
    client.exceptions.ResourceNotFoundException,
    client.exceptions.ServiceQuotaExceededException,
    client.exceptions.ThrottlingException,
    client.exceptions.TooManyTagsException,
    client.exceptions.ValidationException,
) as e:
    print(e)

# Exceptions.exceptions type checking example

from mypy_boto3_bedrock.client import Exceptions

def handle_error(exc: Exceptions.AccessDeniedException) -> None:
    ...

Methods#

batch_delete_evaluation_job#

Creates a batch deletion job.

Type annotations and code completion for boto3.client("bedrock").batch_delete_evaluation_job method. boto3 documentation

# batch_delete_evaluation_job method definition

def batch_delete_evaluation_job(
    self,
    *,
    jobIdentifiers: Sequence[str],
) -> BatchDeleteEvaluationJobResponseTypeDef:  # (1)
    ...

See BatchDeleteEvaluationJobResponseTypeDef

# batch_delete_evaluation_job method usage example with argument unpacking

kwargs: BatchDeleteEvaluationJobRequestRequestTypeDef = {  # (1)
    "jobIdentifiers": ...,
}

parent.batch_delete_evaluation_job(**kwargs)

See BatchDeleteEvaluationJobRequestRequestTypeDef

can_paginate#

Check if an operation can be paginated.

Type annotations and code completion for boto3.client("bedrock").can_paginate method. boto3 documentation

# can_paginate method definition

def can_paginate(
    self,
    operation_name: str,
) -> bool:
    ...

close#

Closes underlying endpoint connections.

Type annotations and code completion for boto3.client("bedrock").close method. boto3 documentation

# close method definition

def close(
    self,
) -> None:
    ...

create_evaluation_job#

API operation for creating and managing Amazon Bedrock automatic model evaluation jobs and model evaluation jobs that use human workers.

Type annotations and code completion for boto3.client("bedrock").create_evaluation_job method. boto3 documentation

# create_evaluation_job method definition

def create_evaluation_job(
    self,
    *,
    jobName: str,
    roleArn: str,
    evaluationConfig: Union[EvaluationConfigTypeDef, EvaluationConfigOutputTypeDef],  # (1)
    inferenceConfig: Union[EvaluationInferenceConfigTypeDef, EvaluationInferenceConfigOutputTypeDef],  # (2)
    outputDataConfig: EvaluationOutputDataConfigTypeDef,  # (3)
    jobDescription: str = ...,
    clientRequestToken: str = ...,
    customerEncryptionKeyId: str = ...,
    jobTags: Sequence[TagTypeDef] = ...,  # (4)
) -> CreateEvaluationJobResponseTypeDef:  # (5)
    ...

# create_evaluation_job method usage example with argument unpacking

kwargs: CreateEvaluationJobRequestRequestTypeDef = {  # (1)
    "jobName": ...,
    "roleArn": ...,
    "evaluationConfig": ...,
    "inferenceConfig": ...,
    "outputDataConfig": ...,
}

parent.create_evaluation_job(**kwargs)

See CreateEvaluationJobRequestRequestTypeDef

create_guardrail#

Creates a guardrail to block topics and to implement safeguards for your generative AI applications.

Type annotations and code completion for boto3.client("bedrock").create_guardrail method. boto3 documentation

# create_guardrail method definition

def create_guardrail(
    self,
    *,
    name: str,
    blockedInputMessaging: str,
    blockedOutputsMessaging: str,
    description: str = ...,
    topicPolicyConfig: GuardrailTopicPolicyConfigTypeDef = ...,  # (1)
    contentPolicyConfig: GuardrailContentPolicyConfigTypeDef = ...,  # (2)
    wordPolicyConfig: GuardrailWordPolicyConfigTypeDef = ...,  # (3)
    sensitiveInformationPolicyConfig: GuardrailSensitiveInformationPolicyConfigTypeDef = ...,  # (4)
    contextualGroundingPolicyConfig: GuardrailContextualGroundingPolicyConfigTypeDef = ...,  # (5)
    kmsKeyId: str = ...,
    tags: Sequence[TagTypeDef] = ...,  # (6)
    clientRequestToken: str = ...,
) -> CreateGuardrailResponseTypeDef:  # (7)
    ...