Guardrail Models Resource#

Sync Guardrail Models Resource#

class nemo_microservices.resources.guardrail.ModelsResource(client: NeMoMicroservices)

Bases: SyncAPIResource

property with_raw_response: ModelsResourceWithRawResponse

This property can be used as a prefix for any HTTP method call to return the raw response object instead of the parsed content.

For more information, see https://docs.nvidia.com/nemo/microservices/latest/pysdk/index.html#accessing-raw-response-data-e-g-headers

property with_streaming_response: ModelsResourceWithStreamingResponse

An alternative to .with_raw_response that doesn’t eagerly read the response body.

For more information, see https://docs.nvidia.com/nemo/microservices/latest/pysdk/index.html#with_streaming_response

list(
*,
response_model: object | NotGiven = NOT_GIVEN,
extra_headers: Headers | None = None,
extra_query: Query | None = None,
extra_body: Body | None = None,
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
) → ModelsResponse

Return list of models registered in the Global Config Registry in OpenAI format as below { “object”: “list”, “data”: [ { “id”: “gpt-4o-audio-preview-2024-12-17”, “object”: “model”, “created”: 1734034239, “owned_by”: “system” }, … ] }

Parameters:

  • extra_headers – Send extra headers

  • extra_query – Add additional query parameters to the request

  • extra_body – Add additional JSON properties to the request

  • timeout – Override the client-level default timeout for this request, in seconds

create_from_dict(data: dict[str, object]) → object

Async Guardrail Models Resource#

class nemo_microservices.resources.guardrail.AsyncModelsResource(client: AsyncNeMoMicroservices)

Bases: AsyncAPIResource

property with_raw_response: AsyncModelsResourceWithRawResponse

This property can be used as a prefix for any HTTP method call to return the raw response object instead of the parsed content.

For more information, see https://docs.nvidia.com/nemo/microservices/latest/pysdk/index.html#accessing-raw-response-data-e-g-headers

property with_streaming_response: AsyncModelsResourceWithStreamingResponse

An alternative to .with_raw_response that doesn’t eagerly read the response body.

For more information, see https://docs.nvidia.com/nemo/microservices/latest/pysdk/index.html#with_streaming_response

async list(
*,
response_model: object | NotGiven = NOT_GIVEN,
extra_headers: Headers | None = None,
extra_query: Query | None = None,
extra_body: Body | None = None,
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
) → ModelsResponse

Return list of models registered in the Global Config Registry in OpenAI format as below { “object”: “list”, “data”: [ { “id”: “gpt-4o-audio-preview-2024-12-17”, “object”: “model”, “created”: 1734034239, “owned_by”: “system” }, … ] }

Parameters:

  • extra_headers – Send extra headers

  • extra_query – Add additional query parameters to the request

  • extra_body – Add additional JSON properties to the request

  • timeout – Override the client-level default timeout for this request, in seconds

create_from_dict(
data: dict[str, object],
) → object