list_inference_profiles ¶

def list_inference_profiles(
    self,
    *,
    config_overrides: Optional[BedrockClientConfig] = None,
    max_results: Optional["capo_bedrock.types.max_results.MaxResults"] = None,
    next_token: Optional[
        "capo_bedrock.types.pagination_token.PaginationToken"
    ] = None,
    type_equals: Optional[
        "capo_bedrock.types.inference_profile_type.InferenceProfileType"
    ] = None,
) -> "capo_bedrock.types.list_inference_profiles_response.ListInferenceProfilesResponse":
    """<p>Returns a list of inference profiles that you can use. 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:
        max_results: <p>The maximum number of results to return in the response. If the total number of results is greater than this value, use the token returned in the response in the <code>nextToken</code> field when making another request to return the next batch of results.</p>
        next_token: <p>If the total number of results is greater than the <code>maxResults</code> value provided in the request, enter the token returned in the <code>nextToken</code> field in the response in this field to return the next batch of results.</p>
        type_equals: <p>Filters for inference profiles that match the type you specify.</p> <ul> <li> <p> <code>SYSTEM_DEFINED</code> – The inference profile is defined by Amazon Bedrock. You can route inference requests across regions with these inference profiles.</p> </li> <li> <p> <code>APPLICATION</code> – The inference profile was created by a user. This type of inference profile can track metrics and costs when invoking the model in it. The inference profile may route requests to one or multiple regions.</p> </li> </ul>

    Raises:
        capo_bedrock.errors.access_denied_exception.AccessDeniedException: <p>The request is denied because of missing access permissions.</p>
        capo_bedrock.errors.internal_server_exception.InternalServerException: <p>An internal server error occurred. Retry your request.</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.
    """

    def _handler(
        req: "OperationRequest[capo_bedrock.types.list_inference_profiles_request.ListInferenceProfilesRequest]",
    ) -> OperationResponse[
        "capo_bedrock.types.list_inference_profiles_response.ListInferenceProfilesResponse"
    ]:
        import capo_bedrock._operations.amazon_bedrock_control_plane_service.list_inference_profiles

        output, http_response = (
            capo_bedrock._operations.amazon_bedrock_control_plane_service.list_inference_profiles.list_inference_profiles(
                req.options, req.input
            )
        )
        return OperationResponse(output=output, response=http_response)

    def _redact_output(
        output: "capo_bedrock.types.list_inference_profiles_response.ListInferenceProfilesResponse",
    ) -> dict[str, Any]:
        import capo_bedrock.types.list_inference_profiles_response

        return capo_bedrock.types.list_inference_profiles_response.redact_sensitive(
            output
        )

    interceptors_, options_ = self.operation_options(
        config_overrides,
        OperationLogging("ListInferenceProfiles", redact_output=_redact_output),
    )
    input_: capo_bedrock.types.list_inference_profiles_request.ListInferenceProfilesRequest = {}
    if max_results is not None:
        input_["max_results"] = max_results
    if next_token is not None:
        input_["next_token"] = next_token
    if type_equals is not None:
        input_["type_equals"] = type_equals

    response = execute_pipeline(
        OperationRequest(input=input_, options=options_),
        handler=_handler,
        interceptors=list(interceptors_),
    )
    response.response.close()
    return response.output