`nemo_microservices.resources.v2.models`#

Module Contents#

Classes#

`AsyncModelsResource`
`AsyncModelsResourceWithRawResponse`
`AsyncModelsResourceWithStreamingResponse`
`ModelsResource`
`ModelsResourceWithRawResponse`
`ModelsResourceWithStreamingResponse`

API#

class nemo_microservices.resources.v2.models.AsyncModelsResource( client: nemo_microservices._client.AsyncNeMoMicroservices, )#

Bases: nemo_microservices._resource.AsyncAPIResource

Initialization

async create( *, name: str, api_endpoint: nemo_microservices.types.shared_params.api_endpoint_data.APIEndpointData | nemo_microservices._types.Omit = omit, artifact: nemo_microservices.types.shared_params.model_artifact.ModelArtifact | nemo_microservices._types.Omit = omit, base_model: str | nemo_microservices._types.Omit = omit, custom_fields: Dict[str, object] | nemo_microservices._types.Omit = omit, description: str | nemo_microservices._types.Omit = omit, guardrails: nemo_microservices.types.shared_params.guardrail_config_param.GuardrailConfigParam | nemo_microservices._types.Omit = omit, model_providers: nemo_microservices._types.SequenceNotStr[str] | nemo_microservices._types.Omit = omit, namespace: str | nemo_microservices._types.Omit = omit, ownership: Dict[str, object] | nemo_microservices._types.Omit = omit, peft: nemo_microservices.types.shared_params.parameter_efficient_finetuning_data.ParameterEfficientFinetuningData | nemo_microservices._types.Omit = omit, project: str | nemo_microservices._types.Omit = omit, prompt: nemo_microservices.types.shared_params.prompt_data.PromptData | nemo_microservices._types.Omit = omit, spec: nemo_microservices.types.shared_params.model_spec.ModelSpec | 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.models.model_entity.ModelEntity#

Create a new model entity.

This endpoint creates a new Model Entity in the Models service database. The Model Entity will be registered for use within the platform.

Args: name: Name of the model entity

api_endpoint: Data about an API endpoint.

artifact: Data about a model artifact (a set of checkpoint files, configs, and other auxiliary info).

  The `files_url` field can point to a DataStore location.

  Example:

  - nds://models/rdinu/my-lora-customization

  The `rdinu/my-lora-customization` part above is the actual repository.

  If a specific revision needs to be referred, the HuggingFace syntax is used.

  - nds://models/rdinu/my-lora-customization@v1
  - nds://models/rdinu/my-lora-customization@8df79a8

base_model: Link to another model which is used as a base for the current model

custom_fields: Custom fields for additional metadata

description: Optional description of the model

guardrails: A guardrail configuration

model_providers: List of ModelProvider namespace/name resource names that provide inference for this Model Entity

namespace: The namespace of the model entity

ownership: Ownership information for the model

peft: Data about a parameter-efficient finetuning.

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

prompt: Prompt engineering data.

spec: Detailed specification about a model.

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( model_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 Model entity.

Permanently deletes a model entity from the platform.

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( *, page: int | nemo_microservices._types.Omit = omit, page_size: int | nemo_microservices._types.Omit = omit, sort: nemo_microservices.types.v2.models.model_entity_sort_field.ModelEntitySortField | 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.models.model_list_response.ModelListResponse#

List Models endpoint with filtering, search, pagination, and sorting.

Supports filter parameters for various criteria (including peft, custom fields), search parameters for substring matching (name, base_model, peft, custom_property), pagination (page, page_size), sorting, and namespace filtering via query parameter.

Args: page: Page number.

page_size: Page size.

sort: Sort fields for Model Entity queries.

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( model_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.models.model_entity.ModelEntity#

Get Model by Namespace and Name.

Returns the details of a specific model entity identified by its 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( model_name: str, *, namespace: str, api_endpoint: nemo_microservices.types.shared_params.api_endpoint_data.APIEndpointData | nemo_microservices._types.Omit = omit, artifact: nemo_microservices.types.shared_params.model_artifact.ModelArtifact | nemo_microservices._types.Omit = omit, base_model: str | nemo_microservices._types.Omit = omit, custom_fields: Dict[str, object] | nemo_microservices._types.Omit = omit, description: str | nemo_microservices._types.Omit = omit, guardrails: nemo_microservices.types.shared_params.guardrail_config_param.GuardrailConfigParam | nemo_microservices._types.Omit = omit, model_providers: nemo_microservices._types.SequenceNotStr[str] | nemo_microservices._types.Omit = omit, ownership: Dict[str, object] | nemo_microservices._types.Omit = omit, peft: nemo_microservices.types.shared_params.parameter_efficient_finetuning_data.ParameterEfficientFinetuningData | nemo_microservices._types.Omit = omit, prompt: nemo_microservices.types.shared_params.prompt_data.PromptData | nemo_microservices._types.Omit = omit, spec: nemo_microservices.types.shared_params.model_spec.ModelSpec | 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.models.model_entity.ModelEntity#

Update Model metadata.

Updates the metadata of an existing model entity.

If the request body has an empty field, the old value is kept.

Args: api_endpoint: Data about an API endpoint.

artifact: Data about a model artifact (a set of checkpoint files, configs, and other auxiliary info).

  The `files_url` field can point to a DataStore location.

  Example:

  - nds://models/rdinu/my-lora-customization

  The `rdinu/my-lora-customization` part above is the actual repository.

  If a specific revision needs to be referred, the HuggingFace syntax is used.

  - nds://models/rdinu/my-lora-customization@v1
  - nds://models/rdinu/my-lora-customization@8df79a8

base_model: Link to another model which is used as a base for the current model

custom_fields: Custom fields for additional metadata

description: Optional description of the model

guardrails: A guardrail configuration

model_providers: List of ModelProvider namespace/name resource names that provide inference for this Model Entity

ownership: Ownership information for the model

peft: Data about a parameter-efficient finetuning.

prompt: Prompt engineering data.

spec: Detailed specification about a model.

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.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.resources.v2.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.resources.v2.models.AsyncModelsResourceWithRawResponse( models: nemo_microservices.resources.v2.models.AsyncModelsResource, )#: Initialization

class nemo_microservices.resources.v2.models.AsyncModelsResourceWithStreamingResponse( models: nemo_microservices.resources.v2.models.AsyncModelsResource, )#: Initialization

class nemo_microservices.resources.v2.models.ModelsResource(client: nemo_microservices._client.NeMoMicroservices)#

Bases: nemo_microservices._resource.SyncAPIResource

Initialization

create( *, name: str, api_endpoint: nemo_microservices.types.shared_params.api_endpoint_data.APIEndpointData | nemo_microservices._types.Omit = omit, artifact: nemo_microservices.types.shared_params.model_artifact.ModelArtifact | nemo_microservices._types.Omit = omit, base_model: str | nemo_microservices._types.Omit = omit, custom_fields: Dict[str, object] | nemo_microservices._types.Omit = omit, description: str | nemo_microservices._types.Omit = omit, guardrails: nemo_microservices.types.shared_params.guardrail_config_param.GuardrailConfigParam | nemo_microservices._types.Omit = omit, model_providers: nemo_microservices._types.SequenceNotStr[str] | nemo_microservices._types.Omit = omit, namespace: str | nemo_microservices._types.Omit = omit, ownership: Dict[str, object] | nemo_microservices._types.Omit = omit, peft: nemo_microservices.types.shared_params.parameter_efficient_finetuning_data.ParameterEfficientFinetuningData | nemo_microservices._types.Omit = omit, project: str | nemo_microservices._types.Omit = omit, prompt: nemo_microservices.types.shared_params.prompt_data.PromptData | nemo_microservices._types.Omit = omit, spec: nemo_microservices.types.shared_params.model_spec.ModelSpec | 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.models.model_entity.ModelEntity#

Create a new model entity.

This endpoint creates a new Model Entity in the Models service database. The Model Entity will be registered for use within the platform.

Args: name: Name of the model entity

api_endpoint: Data about an API endpoint.

artifact: Data about a model artifact (a set of checkpoint files, configs, and other auxiliary info).

  The `files_url` field can point to a DataStore location.

  Example:

  - nds://models/rdinu/my-lora-customization

  The `rdinu/my-lora-customization` part above is the actual repository.

  If a specific revision needs to be referred, the HuggingFace syntax is used.

  - nds://models/rdinu/my-lora-customization@v1
  - nds://models/rdinu/my-lora-customization@8df79a8

base_model: Link to another model which is used as a base for the current model

custom_fields: Custom fields for additional metadata

description: Optional description of the model

guardrails: A guardrail configuration

model_providers: List of ModelProvider namespace/name resource names that provide inference for this Model Entity

namespace: The namespace of the model entity

ownership: Ownership information for the model

peft: Data about a parameter-efficient finetuning.

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

prompt: Prompt engineering data.

spec: Detailed specification about a model.

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( model_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 Model entity.

Permanently deletes a model entity from the platform.

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( *, page: int | nemo_microservices._types.Omit = omit, page_size: int | nemo_microservices._types.Omit = omit, sort: nemo_microservices.types.v2.models.model_entity_sort_field.ModelEntitySortField | 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.models.model_list_response.ModelListResponse#

List Models endpoint with filtering, search, pagination, and sorting.

Supports filter parameters for various criteria (including peft, custom fields), search parameters for substring matching (name, base_model, peft, custom_property), pagination (page, page_size), sorting, and namespace filtering via query parameter.

Args: page: Page number.

page_size: Page size.

sort: Sort fields for Model Entity queries.

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( model_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.models.model_entity.ModelEntity#

Get Model by Namespace and Name.

Returns the details of a specific model entity identified by its 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( model_name: str, *, namespace: str, api_endpoint: nemo_microservices.types.shared_params.api_endpoint_data.APIEndpointData | nemo_microservices._types.Omit = omit, artifact: nemo_microservices.types.shared_params.model_artifact.ModelArtifact | nemo_microservices._types.Omit = omit, base_model: str | nemo_microservices._types.Omit = omit, custom_fields: Dict[str, object] | nemo_microservices._types.Omit = omit, description: str | nemo_microservices._types.Omit = omit, guardrails: nemo_microservices.types.shared_params.guardrail_config_param.GuardrailConfigParam | nemo_microservices._types.Omit = omit, model_providers: nemo_microservices._types.SequenceNotStr[str] | nemo_microservices._types.Omit = omit, ownership: Dict[str, object] | nemo_microservices._types.Omit = omit, peft: nemo_microservices.types.shared_params.parameter_efficient_finetuning_data.ParameterEfficientFinetuningData | nemo_microservices._types.Omit = omit, prompt: nemo_microservices.types.shared_params.prompt_data.PromptData | nemo_microservices._types.Omit = omit, spec: nemo_microservices.types.shared_params.model_spec.ModelSpec | 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.models.model_entity.ModelEntity#

Update Model metadata.

Updates the metadata of an existing model entity.

If the request body has an empty field, the old value is kept.

Args: api_endpoint: Data about an API endpoint.

artifact: Data about a model artifact (a set of checkpoint files, configs, and other auxiliary info).

  The `files_url` field can point to a DataStore location.

  Example:

  - nds://models/rdinu/my-lora-customization

  The `rdinu/my-lora-customization` part above is the actual repository.

  If a specific revision needs to be referred, the HuggingFace syntax is used.

  - nds://models/rdinu/my-lora-customization@v1
  - nds://models/rdinu/my-lora-customization@8df79a8

base_model: Link to another model which is used as a base for the current model

custom_fields: Custom fields for additional metadata

description: Optional description of the model

guardrails: A guardrail configuration

model_providers: List of ModelProvider namespace/name resource names that provide inference for this Model Entity

ownership: Ownership information for the model

peft: Data about a parameter-efficient finetuning.

prompt: Prompt engineering data.

spec: Detailed specification about a model.

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.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.resources.v2.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.resources.v2.models.ModelsResourceWithRawResponse( models: nemo_microservices.resources.v2.models.ModelsResource, )#: Initialization

class nemo_microservices.resources.v2.models.ModelsResourceWithStreamingResponse( models: nemo_microservices.resources.v2.models.ModelsResource, )#: Initialization

nemo_microservices.resources.v2.models#

Module Contents#

Classes#

API#

`nemo_microservices.resources.v2.models`#