`nemo_microservices.resources.v2.inference.providers`#

Module Contents#

Classes#

`AsyncProvidersResource`
`AsyncProvidersResourceWithRawResponse`
`AsyncProvidersResourceWithStreamingResponse`
`ProvidersResource`
`ProvidersResourceWithRawResponse`
`ProvidersResourceWithStreamingResponse`

API#

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

Bases: nemo_microservices._resource.AsyncAPIResource

Initialization

async create( *, host_url: str, name: str, api_key: str | nemo_microservices._types.Omit = omit, api_key_id: str | nemo_microservices._types.Omit = omit, description: str | nemo_microservices._types.Omit = omit, enabled_models: nemo_microservices._types.SequenceNotStr[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_provider.ModelProvider#

Create a new model provider.

Args: host_url: The network endpoint URL for the model provider

name: Name of the model provider

api_key: The API key value itself. Will be stored in Secrets service. Mutually exclusive with api_key_id.

api_key_id: Reference to the API key stored in Secrets service. Mutually exclusive with api_key.

description: Optional description of the model provider

enabled_models: Optional list of specific models to enable from this provider

namespace: The namespace of the model provider

project: The URN of the project associated with this model provider

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( provider_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 a model provider by namespace and name.

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( *, models: nemo_microservices._types.SequenceNotStr[str] | None | nemo_microservices._types.Omit = omit, namespace: str | None | nemo_microservices._types.Omit = omit, project: str | None | nemo_microservices._types.Omit = omit, status: nemo_microservices.types.v2.inference.model_provider_status.ModelProviderStatus | None | 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.provider_list_response.ProviderListResponse#

List model providers with optional filtering.

Supports filter parameters for either status (to list healthy ModelProviders) or models (to discover ModelProviders based on the models they’re advertising).

Args: models: Filter by models

namespace: Filter by namespace

project: Filter by project URN

status: Status enum for ModelProvider objects.

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, *, models: nemo_microservices._types.SequenceNotStr[str] | None | nemo_microservices._types.Omit = omit, project: str | None | nemo_microservices._types.Omit = omit, status: nemo_microservices.types.v2.inference.model_provider_status.ModelProviderStatus | None | 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.provider_list_namespace_response.ProviderListNamespaceResponse#

List model providers for a specific namespace.

Args: models: Filter by models

project: Filter by project URN

status: Status enum for ModelProvider objects.

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( provider_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_provider.ModelProvider#

Get a model provider by namespace and name.

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( provider_name: str, *, namespace: str, host_url: str, api_key: str | nemo_microservices._types.Omit = omit, api_key_id: str | nemo_microservices._types.Omit = omit, description: str | nemo_microservices._types.Omit = omit, enabled_models: nemo_microservices._types.SequenceNotStr[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_provider.ModelProvider#

Create or update a model provider.

Args: host_url: The network endpoint URL for the model provider

api_key: The API key value itself. Will be stored in Secrets service. Mutually exclusive with api_key_id.

api_key_id: Reference to the API key stored in Secrets service. Mutually exclusive with api_key.

description: Optional description of the model provider

enabled_models: Optional list of specific models to enable from this provider

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 with_raw_response: nemo_microservices.resources.v2.inference.providers.AsyncProvidersResourceWithRawResponse#

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.providers.AsyncProvidersResourceWithStreamingResponse#

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.providers.AsyncProvidersResourceWithRawResponse( providers: nemo_microservices.resources.v2.inference.providers.AsyncProvidersResource, )#: Initialization

class nemo_microservices.resources.v2.inference.providers.AsyncProvidersResourceWithStreamingResponse( providers: nemo_microservices.resources.v2.inference.providers.AsyncProvidersResource, )#: Initialization

class nemo_microservices.resources.v2.inference.providers.ProvidersResource( client: nemo_microservices._client.NeMoMicroservices, )#

Bases: nemo_microservices._resource.SyncAPIResource

Initialization

create( *, host_url: str, name: str, api_key: str | nemo_microservices._types.Omit = omit, api_key_id: str | nemo_microservices._types.Omit = omit, description: str | nemo_microservices._types.Omit = omit, enabled_models: nemo_microservices._types.SequenceNotStr[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_provider.ModelProvider#

Create a new model provider.

Args: host_url: The network endpoint URL for the model provider

name: Name of the model provider

api_key: The API key value itself. Will be stored in Secrets service. Mutually exclusive with api_key_id.

api_key_id: Reference to the API key stored in Secrets service. Mutually exclusive with api_key.

description: Optional description of the model provider

enabled_models: Optional list of specific models to enable from this provider

namespace: The namespace of the model provider

project: The URN of the project associated with this model provider

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( provider_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 a model provider by namespace and name.

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( *, models: nemo_microservices._types.SequenceNotStr[str] | None | nemo_microservices._types.Omit = omit, namespace: str | None | nemo_microservices._types.Omit = omit, project: str | None | nemo_microservices._types.Omit = omit, status: nemo_microservices.types.v2.inference.model_provider_status.ModelProviderStatus | None | 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.provider_list_response.ProviderListResponse#

List model providers with optional filtering.

Supports filter parameters for either status (to list healthy ModelProviders) or models (to discover ModelProviders based on the models they’re advertising).

Args: models: Filter by models

namespace: Filter by namespace

project: Filter by project URN

status: Status enum for ModelProvider objects.

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, *, models: nemo_microservices._types.SequenceNotStr[str] | None | nemo_microservices._types.Omit = omit, project: str | None | nemo_microservices._types.Omit = omit, status: nemo_microservices.types.v2.inference.model_provider_status.ModelProviderStatus | None | 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.provider_list_namespace_response.ProviderListNamespaceResponse#

List model providers for a specific namespace.

Args: models: Filter by models

project: Filter by project URN

status: Status enum for ModelProvider objects.

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( provider_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_provider.ModelProvider#

Get a model provider by namespace and name.

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( provider_name: str, *, namespace: str, host_url: str, api_key: str | nemo_microservices._types.Omit = omit, api_key_id: str | nemo_microservices._types.Omit = omit, description: str | nemo_microservices._types.Omit = omit, enabled_models: nemo_microservices._types.SequenceNotStr[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_provider.ModelProvider#

Create or update a model provider.

Args: host_url: The network endpoint URL for the model provider

api_key: The API key value itself. Will be stored in Secrets service. Mutually exclusive with api_key_id.

api_key_id: Reference to the API key stored in Secrets service. Mutually exclusive with api_key.

description: Optional description of the model provider

enabled_models: Optional list of specific models to enable from this provider

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 with_raw_response: nemo_microservices.resources.v2.inference.providers.ProvidersResourceWithRawResponse#

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.providers.ProvidersResourceWithStreamingResponse#

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.providers.ProvidersResourceWithRawResponse( providers: nemo_microservices.resources.v2.inference.providers.ProvidersResource, )#: Initialization

class nemo_microservices.resources.v2.inference.providers.ProvidersResourceWithStreamingResponse( providers: nemo_microservices.resources.v2.inference.providers.ProvidersResource, )#: Initialization

nemo_microservices.resources.v2.inference.providers#

Module Contents#

Classes#

API#

`nemo_microservices.resources.v2.inference.providers`#