nemo_microservices.resources.v2.inference.inference#

Module Contents#

Classes#

API#

class nemo_microservices.resources.v2.inference.inference.AsyncInferenceResource(
client: nemo_microservices._client.AsyncNeMoMicroservices,
)#

Bases: nemo_microservices._resource.AsyncAPIResource

Initialization

property deployment_configs: nemo_microservices.resources.v2.inference.deployment_configs.deployment_configs.AsyncDeploymentConfigsResource#
property deployments: nemo_microservices.resources.v2.inference.deployments.deployments.AsyncDeploymentsResource#
property gateway: nemo_microservices.resources.v2.inference.gateway.gateway.AsyncGatewayResource#
property providers: nemo_microservices.resources.v2.inference.providers.AsyncProvidersResource#
property with_raw_response: nemo_microservices.resources.v2.inference.inference.AsyncInferenceResourceWithRawResponse#

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.resources.v2.inference.inference.AsyncInferenceResourceWithStreamingResponse#

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.resources.v2.inference.inference.AsyncInferenceResourceWithRawResponse(
inference: nemo_microservices.resources.v2.inference.inference.AsyncInferenceResource,
)#

Initialization

property deployment_configs: nemo_microservices.resources.v2.inference.deployment_configs.deployment_configs.AsyncDeploymentConfigsResourceWithRawResponse#
property deployments: nemo_microservices.resources.v2.inference.deployments.deployments.AsyncDeploymentsResourceWithRawResponse#
property gateway: nemo_microservices.resources.v2.inference.gateway.gateway.AsyncGatewayResourceWithRawResponse#
property providers: nemo_microservices.resources.v2.inference.providers.AsyncProvidersResourceWithRawResponse#
class nemo_microservices.resources.v2.inference.inference.AsyncInferenceResourceWithStreamingResponse(
inference: nemo_microservices.resources.v2.inference.inference.AsyncInferenceResource,
)#

Initialization

property deployment_configs: nemo_microservices.resources.v2.inference.deployment_configs.deployment_configs.AsyncDeploymentConfigsResourceWithStreamingResponse#
property deployments: nemo_microservices.resources.v2.inference.deployments.deployments.AsyncDeploymentsResourceWithStreamingResponse#
property gateway: nemo_microservices.resources.v2.inference.gateway.gateway.AsyncGatewayResourceWithStreamingResponse#
property providers: nemo_microservices.resources.v2.inference.providers.AsyncProvidersResourceWithStreamingResponse#
class nemo_microservices.resources.v2.inference.inference.InferenceResource(
client: nemo_microservices._client.NeMoMicroservices,
)#

Bases: nemo_microservices._resource.SyncAPIResource

Initialization

property deployment_configs: nemo_microservices.resources.v2.inference.deployment_configs.deployment_configs.DeploymentConfigsResource#
property deployments: nemo_microservices.resources.v2.inference.deployments.deployments.DeploymentsResource#
property gateway: nemo_microservices.resources.v2.inference.gateway.gateway.GatewayResource#
property providers: nemo_microservices.resources.v2.inference.providers.ProvidersResource#
property with_raw_response: nemo_microservices.resources.v2.inference.inference.InferenceResourceWithRawResponse#

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.resources.v2.inference.inference.InferenceResourceWithStreamingResponse#

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.resources.v2.inference.inference.InferenceResourceWithRawResponse(
inference: nemo_microservices.resources.v2.inference.inference.InferenceResource,
)#

Initialization

property deployment_configs: nemo_microservices.resources.v2.inference.deployment_configs.deployment_configs.DeploymentConfigsResourceWithRawResponse#
property deployments: nemo_microservices.resources.v2.inference.deployments.deployments.DeploymentsResourceWithRawResponse#
property gateway: nemo_microservices.resources.v2.inference.gateway.gateway.GatewayResourceWithRawResponse#
property providers: nemo_microservices.resources.v2.inference.providers.ProvidersResourceWithRawResponse#
class nemo_microservices.resources.v2.inference.inference.InferenceResourceWithStreamingResponse(
inference: nemo_microservices.resources.v2.inference.inference.InferenceResource,
)#

Initialization

property deployment_configs: nemo_microservices.resources.v2.inference.deployment_configs.deployment_configs.DeploymentConfigsResourceWithStreamingResponse#
property deployments: nemo_microservices.resources.v2.inference.deployments.deployments.DeploymentsResourceWithStreamingResponse#
property gateway: nemo_microservices.resources.v2.inference.gateway.gateway.GatewayResourceWithStreamingResponse#
property providers: nemo_microservices.resources.v2.inference.providers.ProvidersResourceWithStreamingResponse#