nemo-platform-plugin 0.1.0__py3-none-any.whl

nemo_platform/types/inference/model_provider_sort.py

@@ -0,0 +1,24 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing_extensions import Literal, TypeAlias
+
+__all__ = ["ModelProviderSort"]
+
+ModelProviderSort: TypeAlias = Literal[
+    "name", "-name", "created_at", "-created_at", "updated_at", "-updated_at", "status", "-status"
+]

nemo_platform/types/inference/model_provider_status.py

@@ -0,0 +1,24 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing_extensions import Literal, TypeAlias
+
+__all__ = ["ModelProviderStatus"]
+
+ModelProviderStatus: TypeAlias = Literal[
+    "UNKNOWN", "CREATED", "PENDING", "READY", "ERROR", "DELETING", "DELETED", "LOST"
+]

nemo_platform/types/inference/model_providers_page.py

@@ -0,0 +1,37 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Dict, List, Optional
+
+from ..._models import BaseModel
+from .model_provider import ModelProvider
+from ..shared.pagination_data import PaginationData
+
+__all__ = ["ModelProvidersPage"]
+
+
+class ModelProvidersPage(BaseModel):
+    data: List[ModelProvider]
+
+    filter: Optional[Dict[str, object]] = None
+    """Filtering information."""
+
+    pagination: Optional[PaginationData] = None
+    """Pagination information."""
+
+    sort: Optional[str] = None
+    """The field on which the results are sorted."""

nemo_platform/types/inference/model_type.py

@@ -0,0 +1,22 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing_extensions import Literal, TypeAlias
+
+__all__ = ["ModelType"]
+
+ModelType: TypeAlias = Literal["llm", "embed", "other"]

nemo_platform/types/inference/nim_deployment.py

@@ -0,0 +1,96 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Dict, Optional
+
+from ..._compat import PYDANTIC_V1, ConfigDict
+from ..._models import BaseModel
+from .model_type import ModelType
+from .k8s_nim_operator_config import K8sNIMOperatorConfig
+from ..shared.tool_call_config import ToolCallConfig
+
+__all__ = ["NIMDeployment"]
+
+
+class NIMDeployment(BaseModel):
+    """Configuration for NIM-based model deployment."""
+
+    gpu: int
+    """Number of GPUs required for the deployment"""
+
+    additional_envs: Optional[Dict[str, object]] = None
+    """Additional environment variables for the deployment"""
+
+    chat_template: Optional[str] = None
+    """Jinja2 chat template string for the model.
+
+    Overrides the chat_template from ModelEntity.spec if both are set. Used by NIM
+    to format chat completions.
+    """
+
+    disk_size: Optional[str] = None
+    """Disk size for the deployment"""
+
+    image_name: Optional[str] = None
+    """Container image name from NGC. If not specified, defaults to multi-llm"""
+
+    image_tag: Optional[str] = None
+    """Container image tag from NGC"""
+
+    k8s_nim_operator_config: Optional[K8sNIMOperatorConfig] = None
+    """Kubernetes configuration for NIM deployment via k8s-nim-operator.
+
+    These fields provide typed access to commonly-used NIMService Spec fields and
+    are applied before override_config in the compilation precedence.
+    """
+
+    lora_enabled: Optional[bool] = None
+    """Whether to enable LoRA support"""
+
+    model_name: Optional[str] = None
+    """Model name - model repository name for model weights."""
+
+    model_namespace: Optional[str] = None
+    """
+    Model repository namespace - organization/user namespace as it exists in
+    repo_id.
+    """
+
+    model_provider: Optional[str] = None
+    """Model provider: 'hf' for HuggingFace or 'nmp' for NeMo Platform"""
+
+    model_revision: Optional[str] = None
+    """Model revision (branch, tag, or commit).
+
+    If not specified, parsed from model_name @revision suffix or defaults to 'main'
+    """
+
+    model_type: Optional[ModelType] = None
+    """Model type enum for NIM deployments."""
+
+    override_config: Optional[Dict[str, object]] = None
+    """Raw NIMService spec configuration that takes precedence over generated config.
+
+    Allows end users to provide advanced configuration options directly.
+    """
+
+    tool_call_config: Optional[ToolCallConfig] = None
+    """Configuration for tool calling support in NIM deployments."""
+
+    if not PYDANTIC_V1:
+        # allow fields with a `model_` prefix
+        model_config = ConfigDict(protected_namespaces=tuple())

nemo_platform/types/inference/nim_deployment_param.py

@@ -0,0 +1,93 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Dict
+from typing_extensions import Required, TypedDict
+
+from .model_type import ModelType
+from .k8s_nim_operator_config_param import K8sNIMOperatorConfigParam
+from ..shared_params.tool_call_config import ToolCallConfig
+
+__all__ = ["NIMDeploymentParam"]
+
+
+class NIMDeploymentParam(TypedDict, total=False):
+    """Configuration for NIM-based model deployment."""
+
+    gpu: Required[int]
+    """Number of GPUs required for the deployment"""
+
+    additional_envs: Dict[str, object]
+    """Additional environment variables for the deployment"""
+
+    chat_template: str
+    """Jinja2 chat template string for the model.
+
+    Overrides the chat_template from ModelEntity.spec if both are set. Used by NIM
+    to format chat completions.
+    """
+
+    disk_size: str
+    """Disk size for the deployment"""
+
+    image_name: str
+    """Container image name from NGC. If not specified, defaults to multi-llm"""
+
+    image_tag: str
+    """Container image tag from NGC"""
+
+    k8s_nim_operator_config: K8sNIMOperatorConfigParam
+    """Kubernetes configuration for NIM deployment via k8s-nim-operator.
+
+    These fields provide typed access to commonly-used NIMService Spec fields and
+    are applied before override_config in the compilation precedence.
+    """
+
+    lora_enabled: bool
+    """Whether to enable LoRA support"""
+
+    model_name: str
+    """Model name - model repository name for model weights."""
+
+    model_namespace: str
+    """
+    Model repository namespace - organization/user namespace as it exists in
+    repo_id.
+    """
+
+    model_provider: str
+    """Model provider: 'hf' for HuggingFace or 'nmp' for NeMo Platform"""
+
+    model_revision: str
+    """Model revision (branch, tag, or commit).
+
+    If not specified, parsed from model_name @revision suffix or defaults to 'main'
+    """
+
+    model_type: ModelType
+    """Model type enum for NIM deployments."""
+
+    override_config: Dict[str, object]
+    """Raw NIMService spec configuration that takes precedence over generated config.
+
+    Allows end users to provide advanced configuration options directly.
+    """
+
+    tool_call_config: ToolCallConfig
+    """Configuration for tool calling support in NIM deployments."""

nemo_platform/types/inference/provider_create_params.py

@@ -0,0 +1,94 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Dict
+from typing_extensions import Required, TypedDict
+
+from ..._types import SequenceNotStr
+from .model_provider_status import ModelProviderStatus
+
+__all__ = ["ProviderCreateParams"]
+
+
+class ProviderCreateParams(TypedDict, total=False):
+    workspace: str
+
+    host_url: Required[str]
+    """The network endpoint URL for the model provider"""
+
+    name: Required[str]
+    """Name of the model provider.
+
+    Allowed characters: letters (a-z, A-Z), digits (0-9), underscores, hyphens, and
+    dots.
+    """
+
+    api_key_secret_name: str
+    """Reference to an API key secret stored in the Secrets service.
+
+    Create the secret first via secrets API, then pass the secret name here.
+    """
+
+    auth_header_format: str
+    """
+    Jinja2 template string controlling how the API key secret is sent to the
+    upstream. Must contain exactly one variable named `auth_secret`, which is
+    substituted with the resolved secret value at request time. Example:
+    `'X-Api-Key: {{ auth_secret }}'`. If not set, defaults to
+    `'Authorization: Bearer {{ auth_secret }}'`.
+    """
+
+    default_extra_body: Dict[str, object]
+    """Default body parameters for inference requests.
+
+    Can be overridden by user requests.
+    """
+
+    default_extra_headers: Dict[str, str]
+    """Default headers for inference requests. Can be overridden by user requests."""
+
+    description: str
+    """Optional description of the model provider"""
+
+    enabled_models: SequenceNotStr[str]
+    """Optional list of specific models to enable from this provider"""
+
+    model_deployment_id: str
+    """
+    Optional reference to the ModelDeployment ID if this provider is being
+    auto-created for a deployment
+    """
+
+    project: str
+    """The URN of the project associated with this model provider"""
+
+    required_extra_body: Dict[str, object]
+    """Required body parameters for inference requests.
+
+    Cannot be overridden by user requests.
+    """
+
+    required_extra_headers: Dict[str, str]
+    """Required headers for inference requests. Cannot be overridden by user requests."""
+
+    status: ModelProviderStatus
+    """Status enum for ModelProvider objects."""
+
+    status_message: str
+    """Status message"""

nemo_platform/types/inference/provider_list_params.py

@@ -0,0 +1,47 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing_extensions import TypedDict
+
+from .model_provider_sort import ModelProviderSort
+from .model_provider_filter_param import ModelProviderFilterParam
+
+__all__ = ["ProviderListParams"]
+
+
+class ProviderListParams(TypedDict, total=False):
+    workspace: str
+
+    filter: ModelProviderFilterParam
+    """
+    Filter model providers by workspace, project, status, model_deployment_id, name,
+    description, host_url, created_at, and updated_at.
+    """
+
+    page: int
+    """Page number."""
+
+    page_size: int
+    """Page size."""
+
+    sort: ModelProviderSort
+    """The field to sort by.
+
+    To sort in decreasing order, use `-` in front of the field name.
+    """

nemo_platform/types/inference/provider_update_params.py

@@ -0,0 +1,87 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Dict
+from typing_extensions import Required, TypedDict
+
+from ..._types import SequenceNotStr
+from .model_provider_status import ModelProviderStatus
+
+__all__ = ["ProviderUpdateParams"]
+
+
+class ProviderUpdateParams(TypedDict, total=False):
+    workspace: str
+
+    host_url: Required[str]
+    """The network endpoint URL for the model provider"""
+
+    api_key_secret_name: str
+    """Reference to an API key secret stored in the Secrets service.
+
+    Create the secret first via secrets API, then pass the secret name here.
+    """
+
+    auth_header_format: str
+    """
+    Jinja2 template string controlling how the API key secret is sent to the
+    upstream. Must contain exactly one variable named `auth_secret`, which is
+    substituted with the resolved secret value at request time. Example:
+    `'X-Api-Key: {{ auth_secret }}'`. If not set, defaults to
+    `'Authorization: Bearer {{ auth_secret }}'`.
+    """
+
+    default_extra_body: Dict[str, object]
+    """Default body parameters for inference requests.
+
+    Can be overridden by user requests.
+    """
+
+    default_extra_headers: Dict[str, str]
+    """Default headers for inference requests. Can be overridden by user requests."""
+
+    description: str
+    """Optional description of the model provider"""
+
+    enabled_models: SequenceNotStr[str]
+    """Optional list of specific models to enable from this provider"""
+
+    model_deployment_id: str
+    """
+    Optional reference to the ModelDeployment ID if this provider is associated with
+    a deployment
+    """
+
+    project: str
+    """The URN of the project associated with this model provider"""
+
+    required_extra_body: Dict[str, object]
+    """Required body parameters for inference requests.
+
+    Cannot be overridden by user requests.
+    """
+
+    required_extra_headers: Dict[str, str]
+    """Required headers for inference requests. Cannot be overridden by user requests."""
+
+    status: ModelProviderStatus
+    """Status enum for ModelProvider objects."""
+
+    status_message: str
+    """Status message"""

nemo_platform/types/inference/provider_update_status_params.py

@@ -0,0 +1,48 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Iterable
+from typing_extensions import TypedDict
+
+from .model_provider_status import ModelProviderStatus
+from .served_model_mapping_param import ServedModelMappingParam
+
+__all__ = ["ProviderUpdateStatusParams"]
+
+
+class ProviderUpdateStatusParams(TypedDict, total=False):
+    workspace: str
+
+    model_deployment_id: str
+    """
+    Reference to the ModelDeployment ID if this provider is associated with a
+    deployment
+    """
+
+    served_models: Iterable[ServedModelMappingParam]
+    """List of models served by this provider with routing information for IGW"""
+
+    status: ModelProviderStatus
+    """Status enum for ModelProvider objects."""
+
+    status_message: str
+    """Status message.
+
+    If status is provided without status_message, defaults to empty string.
+    """

nemo_platform/types/inference/served_model_mapping.py

@@ -0,0 +1,35 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from ..._compat import PYDANTIC_V1, ConfigDict
+from ..._models import BaseModel
+
+__all__ = ["ServedModelMapping"]
+
+
+class ServedModelMapping(BaseModel):
+    """Mapping between a Model Entity and how it's served by this provider."""
+
+    model_entity_id: str
+    """Model Entity identifier as workspace/name (e.g., 'my-ws/my-model')"""
+
+    served_model_name: str
+    """The actual model name to send to the backend endpoint in the 'model' field"""
+
+    if not PYDANTIC_V1:
+        # allow fields with a `model_` prefix
+        model_config = ConfigDict(protected_namespaces=tuple())

nemo_platform/types/inference/served_model_mapping_param.py

@@ -0,0 +1,32 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing_extensions import Required, TypedDict
+
+__all__ = ["ServedModelMappingParam"]
+
+
+class ServedModelMappingParam(TypedDict, total=False):
+    """Mapping between a Model Entity and how it's served by this provider."""
+
+    model_entity_id: Required[str]
+    """Model Entity identifier as workspace/name (e.g., 'my-ws/my-model')"""
+
+    served_model_name: Required[str]
+    """The actual model name to send to the backend endpoint in the 'model' field"""