create_model_invocation_job async ¶

async def create_model_invocation_job(
    self,
    job_name: "capo_bedrock.types.model_invocation_job_name.ModelInvocationJobName",
    role_arn: "capo_bedrock.types.role_arn.RoleArn",
    model_id: "capo_bedrock.types.model_id.ModelId",
    input_data_config: "capo_bedrock.types.model_invocation_job_input_data_config.ModelInvocationJobInputDataConfig",
    output_data_config: "capo_bedrock.types.model_invocation_job_output_data_config.ModelInvocationJobOutputDataConfig",
    *,
    config_overrides: Optional[AsyncBedrockClientConfig] = None,
    client_request_token: Optional[
        "capo_bedrock.types.model_invocation_idempotency_token.ModelInvocationIdempotencyToken"
    ] = None,
    vpc_config: Optional["capo_bedrock.types.vpc_config.VpcConfig"] = None,
    timeout_duration_in_hours: Optional[
        "capo_bedrock.types.model_invocation_job_timeout_duration_in_hours.ModelInvocationJobTimeoutDurationInHours"
    ] = None,
    tags: Optional["capo_bedrock.types.tag_list.TagList"] = None,
    model_invocation_type: Optional[
        "capo_bedrock.types.model_invocation_type.ModelInvocationType"
    ] = None,
) -> "capo_bedrock.types.create_model_invocation_job_response.CreateModelInvocationJobResponse":
    """<p>Creates a batch inference job to invoke a model on multiple prompts. Format your data according to <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/batch-inference-data">Format your inference data</a> and upload it to an Amazon S3 bucket. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/batch-inference.html">Process multiple prompts with batch inference</a>.</p> <p>The response returns a <code>jobArn</code> that you can use to stop or get details about the job.</p>

    Args:
        job_name: <p>A name to give the batch inference job.</p>
        role_arn: <p>The Amazon Resource Name (ARN) of the service role with permissions to carry out and manage batch inference. You can use the console to create a default service role or follow the steps at <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/batch-iam-sr.html">Create a service role for batch inference</a>.</p>
        client_request_token: <p>A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see <a href="https://docs.aws.amazon.com/AWSEC2/latest/APIReference/Run_Instance_Idempotency.html">Ensuring idempotency</a>.</p>
        model_id: <p>The unique identifier of the foundation model to use for the batch inference job.</p>
        input_data_config: <p>Details about the location of the input to the batch inference job.</p>
        output_data_config: <p>Details about the location of the output of the batch inference job.</p>
        vpc_config: <p>The configuration of the Virtual Private Cloud (VPC) for the data in the batch inference job. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/batch-vpc">Protect batch inference jobs using a VPC</a>.</p>
        timeout_duration_in_hours: <p>The number of hours after which to force the batch inference job to time out.</p>
        tags: <p>Any tags to associate with the batch inference job. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/tagging.html">Tagging Amazon Bedrock resources</a>.</p>
        model_invocation_type: <p>The invocation endpoint for ModelInvocationJob</p>

    Raises:
        capo_bedrock.errors.access_denied_exception.AccessDeniedException: <p>The request is denied because of missing access permissions.</p>
        capo_bedrock.errors.conflict_exception.ConflictException: <p>Error occurred because of a conflict while performing an operation.</p>
        capo_bedrock.errors.internal_server_exception.InternalServerException: <p>An internal server error occurred. Retry your request.</p>
        capo_bedrock.errors.resource_not_found_exception.ResourceNotFoundException: <p>The specified resource Amazon Resource Name (ARN) was not found. Check the Amazon Resource Name (ARN) and try your request again.</p>
        capo_bedrock.errors.service_quota_exceeded_exception.ServiceQuotaExceededException: <p>The number of requests exceeds the service quota. Resubmit your request later.</p>
        capo_bedrock.errors.throttling_exception.ThrottlingException: <p>The number of requests exceeds the limit. Resubmit your request later.</p>
        capo_bedrock.errors.validation_exception.ValidationException: <p>Input validation failed. Check your request parameters and retry the request.</p>
        capo_bedrock.errors.UnknownServiceError: The service returned an error code this client does not model.
    """

    async def _handler(
        req: "AsyncOperationRequest[capo_bedrock.types.create_model_invocation_job_request.CreateModelInvocationJobRequest]",
    ) -> AsyncOperationResponse[
        "capo_bedrock.types.create_model_invocation_job_response.CreateModelInvocationJobResponse"
    ]:
        import capo_bedrock._operations.amazon_bedrock_control_plane_service.create_model_invocation_job

        (
            output,
            http_response,
        ) = await capo_bedrock._operations.amazon_bedrock_control_plane_service.create_model_invocation_job.async_create_model_invocation_job(
            req.options, req.input
        )
        return AsyncOperationResponse(output=output, response=http_response)

    interceptors_, options_ = self.operation_options(
        config_overrides, OperationLogging("CreateModelInvocationJob")
    )
    input_: capo_bedrock.types.create_model_invocation_job_request.CreateModelInvocationJobRequest = {
        "job_name": job_name,
        "role_arn": role_arn,
        "model_id": model_id,
        "input_data_config": input_data_config,
        "output_data_config": output_data_config,
    }
    if client_request_token is None:
        client_request_token = str(uuid.uuid4())
    input_["client_request_token"] = client_request_token
    if vpc_config is not None:
        input_["vpc_config"] = vpc_config
    if timeout_duration_in_hours is not None:
        input_["timeout_duration_in_hours"] = timeout_duration_in_hours
    if tags is not None:
        input_["tags"] = tags
    if model_invocation_type is not None:
        input_["model_invocation_type"] = model_invocation_type

    response = await aexecute_pipeline(
        AsyncOperationRequest(input=input_, options=options_),
        handler=_handler,
        interceptors=list(interceptors_),
    )
    await response.response.aclose()
    return response.output