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.AsyncAPIResourceInitialization
- 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,
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,
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,
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,
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,
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,
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_responsethat 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
- class nemo_microservices.resources.v2.inference.deployment_configs.deployment_configs.AsyncDeploymentConfigsResourceWithStreamingResponse(
- deployment_configs: nemo_microservices.resources.v2.inference.deployment_configs.deployment_configs.AsyncDeploymentConfigsResource,
Initialization
- class nemo_microservices.resources.v2.inference.deployment_configs.deployment_configs.DeploymentConfigsResource(
- client: nemo_microservices._client.NeMoMicroservices,
Bases:
nemo_microservices._resource.SyncAPIResourceInitialization
- 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,
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,
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,
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,
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,
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,
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_responsethat 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
- class nemo_microservices.resources.v2.inference.deployment_configs.deployment_configs.DeploymentConfigsResourceWithStreamingResponse(
- deployment_configs: nemo_microservices.resources.v2.inference.deployment_configs.deployment_configs.DeploymentConfigsResource,
Initialization