nemo_microservices.lib.custom_resources.inference.models#

Module Contents#

Classes#

API#

class nemo_microservices.lib.custom_resources.inference.models.AsyncModelsResource(
client: nemo_microservices._client.AsyncNeMoMicroservices,
)#

Bases: nemo_microservices._resource.AsyncAPIResource

Initialization

async list(
*,
extra_headers: nemo_microservices._types.Headers | None = None,
extra_query: nemo_microservices._types.Query | None = None,
extra_body: nemo_microservices._types.Body | None = None,
timeout: float | httpx.Timeout | None | nemo_microservices._types.NotGiven = NOT_GIVEN,
) nemo_microservices.lib.custom_types.inference.model_list_response.ModelListResponse#

Returns a list of models available for inference.

Note: this endpoint doesn’t support pagination or filtering.

property with_raw_response: nemo_microservices.lib.custom_resources.inference.models.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: nemo_microservices.lib.custom_resources.inference.models.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

class nemo_microservices.lib.custom_resources.inference.models.AsyncModelsResourceWithRawResponse(
models: nemo_microservices.lib.custom_resources.inference.models.AsyncModelsResource,
)#

Initialization

class nemo_microservices.lib.custom_resources.inference.models.AsyncModelsResourceWithStreamingResponse(
models: nemo_microservices.lib.custom_resources.inference.models.AsyncModelsResource,
)#

Initialization

class nemo_microservices.lib.custom_resources.inference.models.ModelsResource(client: nemo_microservices._client.NeMoMicroservices)#

Bases: nemo_microservices._resource.SyncAPIResource

Initialization

list(
*,
extra_headers: nemo_microservices._types.Headers | None = None,
extra_query: nemo_microservices._types.Query | None = None,
extra_body: nemo_microservices._types.Body | None = None,
timeout: float | httpx.Timeout | None | nemo_microservices._types.NotGiven = NOT_GIVEN,
) nemo_microservices.lib.custom_types.inference.model_list_response.ModelListResponse#

Returns a list of models available for inference.

Note: this endpoint doesn’t support pagination or filtering.

property with_raw_response: nemo_microservices.lib.custom_resources.inference.models.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: nemo_microservices.lib.custom_resources.inference.models.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

class nemo_microservices.lib.custom_resources.inference.models.ModelsResourceWithRawResponse(
models: nemo_microservices.lib.custom_resources.inference.models.ModelsResource,
)#

Initialization

class nemo_microservices.lib.custom_resources.inference.models.ModelsResourceWithStreamingResponse(
models: nemo_microservices.lib.custom_resources.inference.models.ModelsResource,
)#

Initialization