nemo_microservices.resources.v2.inference.deployment_configs.deployment_configs#

Module Contents#

Classes#

API#

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

Bases: nemo_microservices._resource.AsyncAPIResource

Initialization

async create(
*,
name: str,
nim_deployment: nemo_microservices.types.v2.inference.nim_deployment_param.NIMDeploymentParam,
description: str | nemo_microservices._types.Omit = omit,
model_entity_id: str | nemo_microservices._types.Omit = omit,
namespace: str | nemo_microservices._types.Omit = omit,
project: str | nemo_microservices._types.Omit = omit,
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.types.v2.inference.model_deployment_config.ModelDeploymentConfig#

Create a new ModelDeploymentConfig (version 1).

Args: name: Name of the deployment configuration

nim_deployment: Configuration for NIM-based model deployment.

description: Optional description of the deployment configuration

model_entity_id: Optional reference to the base model entity ID for this deployment

namespace: The namespace of the deployment configuration

project: The URN of the project associated with this deployment configuration

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

async delete(
deployment_config_name: str,
*,
namespace: str,
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,
) None#

Delete all versions of a ModelDeploymentConfig.

This operation will fail with 409 Conflict if any ModelDeployments currently reference this config. Delete the dependent deployments first.

Args: 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

async list(
*,
namespace: Optional[str] | nemo_microservices._types.Omit = omit,
project: Optional[str] | nemo_microservices._types.Omit = omit,
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.types.v2.inference.deployment_config_list_response.DeploymentConfigListResponse#

List all ModelDeploymentConfigs with optional filtering.

Returns only the latest version of each config.

Args: 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

async list_namespace(
namespace: str,
*,
project: Optional[str] | nemo_microservices._types.Omit = omit,
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.types.v2.inference.deployment_config_list_namespace_response.DeploymentConfigListNamespaceResponse#

List ModelDeploymentConfigs for a specific namespace.

Returns only the latest version of each config.

Args: 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

async retrieve(
deployment_config_name: str,
*,
namespace: str,
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.types.v2.inference.model_deployment_config.ModelDeploymentConfig#

Get the latest version of a ModelDeploymentConfig.

Args: 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

async update(
deployment_config_name: str,
*,
namespace: str,
nim_deployment: nemo_microservices.types.v2.inference.nim_deployment_param.NIMDeploymentParam,
description: str | nemo_microservices._types.Omit = omit,
model_entity_id: str | nemo_microservices._types.Omit = omit,
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.types.v2.inference.model_deployment_config.ModelDeploymentConfig#

Update a ModelDeploymentConfig (creates a new immutable version).

Args: nim_deployment: Configuration for NIM-based model deployment.

description: Optional description of the deployment configuration

model_entity_id: Optional reference to the base model entity ID for this deployment

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

property versions: nemo_microservices.resources.v2.inference.deployment_configs.versions.AsyncVersionsResource#
property with_raw_response: nemo_microservices.resources.v2.inference.deployment_configs.deployment_configs.AsyncDeploymentConfigsResourceWithRawResponse#

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.deployment_configs.deployment_configs.AsyncDeploymentConfigsResourceWithStreamingResponse#

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.deployment_configs.deployment_configs.AsyncDeploymentConfigsResourceWithRawResponse(
deployment_configs: nemo_microservices.resources.v2.inference.deployment_configs.deployment_configs.AsyncDeploymentConfigsResource,
)#

Initialization

property versions: nemo_microservices.resources.v2.inference.deployment_configs.versions.AsyncVersionsResourceWithRawResponse#
class nemo_microservices.resources.v2.inference.deployment_configs.deployment_configs.AsyncDeploymentConfigsResourceWithStreamingResponse(
deployment_configs: nemo_microservices.resources.v2.inference.deployment_configs.deployment_configs.AsyncDeploymentConfigsResource,
)#

Initialization

property versions: nemo_microservices.resources.v2.inference.deployment_configs.versions.AsyncVersionsResourceWithStreamingResponse#
class nemo_microservices.resources.v2.inference.deployment_configs.deployment_configs.DeploymentConfigsResource(
client: nemo_microservices._client.NeMoMicroservices,
)#

Bases: nemo_microservices._resource.SyncAPIResource

Initialization

create(
*,
name: str,
nim_deployment: nemo_microservices.types.v2.inference.nim_deployment_param.NIMDeploymentParam,
description: str | nemo_microservices._types.Omit = omit,
model_entity_id: str | nemo_microservices._types.Omit = omit,
namespace: str | nemo_microservices._types.Omit = omit,
project: str | nemo_microservices._types.Omit = omit,
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.types.v2.inference.model_deployment_config.ModelDeploymentConfig#

Create a new ModelDeploymentConfig (version 1).

Args: name: Name of the deployment configuration

nim_deployment: Configuration for NIM-based model deployment.

description: Optional description of the deployment configuration

model_entity_id: Optional reference to the base model entity ID for this deployment

namespace: The namespace of the deployment configuration

project: The URN of the project associated with this deployment configuration

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

delete(
deployment_config_name: str,
*,
namespace: str,
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,
) None#

Delete all versions of a ModelDeploymentConfig.

This operation will fail with 409 Conflict if any ModelDeployments currently reference this config. Delete the dependent deployments first.

Args: 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

list(
*,
namespace: Optional[str] | nemo_microservices._types.Omit = omit,
project: Optional[str] | nemo_microservices._types.Omit = omit,
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.types.v2.inference.deployment_config_list_response.DeploymentConfigListResponse#

List all ModelDeploymentConfigs with optional filtering.

Returns only the latest version of each config.

Args: 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

list_namespace(
namespace: str,
*,
project: Optional[str] | nemo_microservices._types.Omit = omit,
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.types.v2.inference.deployment_config_list_namespace_response.DeploymentConfigListNamespaceResponse#

List ModelDeploymentConfigs for a specific namespace.

Returns only the latest version of each config.

Args: 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

retrieve(
deployment_config_name: str,
*,
namespace: str,
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.types.v2.inference.model_deployment_config.ModelDeploymentConfig#

Get the latest version of a ModelDeploymentConfig.

Args: 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

update(
deployment_config_name: str,
*,
namespace: str,
nim_deployment: nemo_microservices.types.v2.inference.nim_deployment_param.NIMDeploymentParam,
description: str | nemo_microservices._types.Omit = omit,
model_entity_id: str | nemo_microservices._types.Omit = omit,
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.types.v2.inference.model_deployment_config.ModelDeploymentConfig#

Update a ModelDeploymentConfig (creates a new immutable version).

Args: nim_deployment: Configuration for NIM-based model deployment.

description: Optional description of the deployment configuration

model_entity_id: Optional reference to the base model entity ID for this deployment

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

property versions: nemo_microservices.resources.v2.inference.deployment_configs.versions.VersionsResource#
property with_raw_response: nemo_microservices.resources.v2.inference.deployment_configs.deployment_configs.DeploymentConfigsResourceWithRawResponse#

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.deployment_configs.deployment_configs.DeploymentConfigsResourceWithStreamingResponse#

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.deployment_configs.deployment_configs.DeploymentConfigsResourceWithRawResponse(
deployment_configs: nemo_microservices.resources.v2.inference.deployment_configs.deployment_configs.DeploymentConfigsResource,
)#

Initialization

property versions: nemo_microservices.resources.v2.inference.deployment_configs.versions.VersionsResourceWithRawResponse#
class nemo_microservices.resources.v2.inference.deployment_configs.deployment_configs.DeploymentConfigsResourceWithStreamingResponse(
deployment_configs: nemo_microservices.resources.v2.inference.deployment_configs.deployment_configs.DeploymentConfigsResource,
)#

Initialization

property versions: nemo_microservices.resources.v2.inference.deployment_configs.versions.VersionsResourceWithStreamingResponse#