create_inference_profile async ¶

async def create_inference_profile(
    self,
    inference_profile_name: "capo_bedrock.types.inference_profile_name.InferenceProfileName",
    model_source: "capo_bedrock.types.inference_profile_model_source.InferenceProfileModelSource",
    *,
    config_overrides: Optional[AsyncBedrockClientConfig] = None,
    description: Optional[
        "capo_bedrock.types.inference_profile_description.InferenceProfileDescription"
    ] = None,
    client_request_token: Optional[
        "capo_bedrock.types.idempotency_token.IdempotencyToken"
    ] = None,
    tags: Optional["capo_bedrock.types.tag_list.TagList"] = None,
) -> "capo_bedrock.types.create_inference_profile_response.CreateInferenceProfileResponse":
    """<p>Creates an application inference profile to track metrics and costs when invoking a model. To create an application inference profile for a foundation model in one region, specify the ARN of the model in that region. To create an application inference profile for a foundation model across multiple regions, specify the ARN of the system-defined inference profile that contains the regions that you want to route requests to. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference.html">Increase throughput and resilience with cross-region inference in Amazon Bedrock</a>. in the Amazon Bedrock User Guide.</p>

    Args:
        inference_profile_name: <p>A name for the inference profile.</p>
        description: <p>A description for the inference profile.</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_source: <p>The foundation model or system-defined inference profile that the inference profile will track metrics and costs for.</p>
        tags: <p>An array of objects, each of which contains a tag and its value. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/what-is-service.html">Tagging resources</a> in the <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/what-is-service.html">Amazon Bedrock User Guide</a>.</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.too_many_tags_exception.TooManyTagsException: <p>The request contains more tags than can be associated with a resource (50 tags per resource). The maximum number of tags includes both existing tags and those included in your current request. </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_inference_profile_request.CreateInferenceProfileRequest]",
    ) -> AsyncOperationResponse[
        "capo_bedrock.types.create_inference_profile_response.CreateInferenceProfileResponse"
    ]:
        import capo_bedrock._operations.amazon_bedrock_control_plane_service.create_inference_profile

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

    def _redact_input(
        input_: "capo_bedrock.types.create_inference_profile_request.CreateInferenceProfileRequest",
    ) -> dict[str, Any]:
        import capo_bedrock.types.create_inference_profile_request

        return capo_bedrock.types.create_inference_profile_request.redact_sensitive(
            input_
        )

    interceptors_, options_ = self.operation_options(
        config_overrides,
        OperationLogging("CreateInferenceProfile", redact_input=_redact_input),
    )
    input_: capo_bedrock.types.create_inference_profile_request.CreateInferenceProfileRequest = {
        "inference_profile_name": inference_profile_name,
        "model_source": model_source,
    }
    if description is not None:
        input_["description"] = description
    if client_request_token is None:
        client_request_token = str(uuid.uuid4())
    input_["client_request_token"] = client_request_token
    if tags is not None:
        input_["tags"] = tags

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