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

nemo_platform/resources/guardrail/guardrail.py

@@ -0,0 +1,463 @@
+# 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, Union, Iterable
+
+import httpx
+
+from .configs import (
+    ConfigsResource,
+    AsyncConfigsResource,
+    ConfigsResourceWithRawResponse,
+    AsyncConfigsResourceWithRawResponse,
+    ConfigsResourceWithStreamingResponse,
+    AsyncConfigsResourceWithStreamingResponse,
+)
+from ..._types import Body, Omit, Query, Headers, NotGiven, SequenceNotStr, omit, not_given
+from ..._utils import path_template, maybe_transform, async_maybe_transform
+from ..._compat import cached_property
+from ..._resource import SyncAPIResource, AsyncAPIResource
+from ..._response import (
+    to_raw_response_wrapper,
+    to_streamed_response_wrapper,
+    async_to_raw_response_wrapper,
+    async_to_streamed_response_wrapper,
+)
+from ..._base_client import make_request_options
+from ...types.guardrail import GuardrailsDataParam, guardrail_check_params
+from ...types.guardrail.guardrails_data_param import GuardrailsDataParam
+from ...types.guardrail.guardrail_check_response import GuardrailCheckResponse
+
+__all__ = ["GuardrailResource", "AsyncGuardrailResource"]
+
+
+class GuardrailResource(SyncAPIResource):
+    @cached_property
+    def configs(self) -> ConfigsResource:
+        return ConfigsResource(self._client)
+
+    @cached_property
+    def with_raw_response(self) -> GuardrailResourceWithRawResponse:
+        """
+        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
+        """
+        return GuardrailResourceWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> GuardrailResourceWithStreamingResponse:
+        """
+        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
+        """
+        return GuardrailResourceWithStreamingResponse(self)
+
+    def check(
+        self,
+        *,
+        workspace: str | None = None,
+        messages: Iterable[guardrail_check_params.Message],
+        model: str,
+        frequency_penalty: float | Omit = omit,
+        function_call: Union[str, Dict[str, object]] | Omit = omit,
+        guardrails: GuardrailsDataParam | Omit = omit,
+        ignore_eos: bool | Omit = omit,
+        logit_bias: Dict[str, float] | Omit = omit,
+        logprobs: bool | Omit = omit,
+        max_completion_tokens: int | Omit = omit,
+        max_tokens: int | Omit = omit,
+        n: int | Omit = omit,
+        presence_penalty: float | Omit = omit,
+        reasoning_effort: str | Omit = omit,
+        response_format: Dict[str, object] | Omit = omit,
+        seed: int | Omit = omit,
+        stop: Union[str, SequenceNotStr[str]] | Omit = omit,
+        stream: bool | Omit = omit,
+        stream_options: Dict[str, bool] | Omit = omit,
+        temperature: float | Omit = omit,
+        tool_choice: Union[str, Dict[str, object]] | Omit = omit,
+        tools: Iterable[Dict[str, object]] | Omit = omit,
+        top_logprobs: int | Omit = omit,
+        top_p: float | Omit = omit,
+        user: str | Omit = omit,
+        vision: bool | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> GuardrailCheckResponse:
+        """
+        Chat completion for the provided conversation.
+
+        Args:
+          messages: A list of messages comprising the conversation so far
+
+          model: The model to use for completion. Must be one of the available models.
+
+          frequency_penalty: Positive values penalize new tokens based on their existing frequency in the
+              text.
+
+          function_call: Deprecated in favor of tool_choice. 'none' means the model will not call a
+              function and instead generates a message. 'auto' means the model can pick
+              between generating a message or calling a function. Specifying a particular
+              function via {'name': 'my_function'} forces the model to call that function.
+
+          guardrails: Guardrails specific options for the request.
+
+          ignore_eos: Ignore the eos when running
+
+          logit_bias: Modify the likelihood of specified tokens appearing in the completion. Maps
+              token IDs (as strings) to bias values from -100 to 100.
+
+          logprobs: Whether to return log probabilities of the output tokens or not. If true,
+              returns the log probabilities of each output token returned in the content of
+              message
+
+          max_completion_tokens: An upper bound for the number of tokens that can be generated for a completion,
+              including visible output tokens and reasoning tokens. Preferred over max_tokens
+              for reasoning models.
+
+          max_tokens: The maximum number of tokens that can be generated in the chat completion.
+
+          n: How many chat completion choices to generate for each input message.
+
+          presence_penalty: Positive values penalize new tokens based on whether they appear in the text so
+              far.
+
+          reasoning_effort: Constrains effort on reasoning for reasoning models. Reducing reasoning effort
+              can result in faster responses and fewer tokens used on reasoning in a response.
+
+          response_format:
+              Format of the response. Use {'type': 'json_object'} for JSON mode or {'type':
+              'json_schema', 'json_schema': {...}} for structured outputs.
+
+          seed: If specified, attempts to sample deterministically.
+
+          stop: Up to 4 sequences where the API will stop generating further tokens.
+
+          stream: If set, partial message deltas will be sent, like in ChatGPT.
+
+          stream_options: Options for streaming response. Only set this when stream=True. Supports
+              include_usage to receive token usage in the final stream chunk.
+
+          temperature: What sampling temperature to use, between 0 and 2.
+
+          tool_choice: Controls which (if any) tool is called by the model. 'none' means no tool is
+              called, 'auto' lets the model decide, 'required' forces a tool call.
+
+          tools: A list of tools the model may call. Each tool is an object with a 'type' field
+              and a 'function' definition.
+
+          top_logprobs: The number of most likely tokens to return at each token position.
+
+          top_p: An alternative to sampling with temperature, called nucleus sampling.
+
+          user: A unique identifier representing your end-user, used by some providers for abuse
+              monitoring.
+
+          vision: Whether this is a vision-capable request with image inputs.
+
+          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
+        """
+        if workspace is None:
+            workspace = self._client._get_workspace_path_param()
+        if not workspace:
+            raise ValueError(f"Expected a non-empty value for `workspace` but received {workspace!r}")
+        return self._post(
+            path_template("/apis/guardrails/v2/workspaces/{workspace}/checks", workspace=workspace),
+            body=maybe_transform(
+                {
+                    "messages": messages,
+                    "model": model,
+                    "frequency_penalty": frequency_penalty,
+                    "function_call": function_call,
+                    "guardrails": guardrails,
+                    "ignore_eos": ignore_eos,
+                    "logit_bias": logit_bias,
+                    "logprobs": logprobs,
+                    "max_completion_tokens": max_completion_tokens,
+                    "max_tokens": max_tokens,
+                    "n": n,
+                    "presence_penalty": presence_penalty,
+                    "reasoning_effort": reasoning_effort,
+                    "response_format": response_format,
+                    "seed": seed,
+                    "stop": stop,
+                    "stream": stream,
+                    "stream_options": stream_options,
+                    "temperature": temperature,
+                    "tool_choice": tool_choice,
+                    "tools": tools,
+                    "top_logprobs": top_logprobs,
+                    "top_p": top_p,
+                    "user": user,
+                    "vision": vision,
+                },
+                guardrail_check_params.GuardrailCheckParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=GuardrailCheckResponse,
+        )
+
+
+class AsyncGuardrailResource(AsyncAPIResource):
+    @cached_property
+    def configs(self) -> AsyncConfigsResource:
+        return AsyncConfigsResource(self._client)
+
+    @cached_property
+    def with_raw_response(self) -> AsyncGuardrailResourceWithRawResponse:
+        """
+        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
+        """
+        return AsyncGuardrailResourceWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AsyncGuardrailResourceWithStreamingResponse:
+        """
+        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
+        """
+        return AsyncGuardrailResourceWithStreamingResponse(self)
+
+    async def check(
+        self,
+        *,
+        workspace: str | None = None,
+        messages: Iterable[guardrail_check_params.Message],
+        model: str,
+        frequency_penalty: float | Omit = omit,
+        function_call: Union[str, Dict[str, object]] | Omit = omit,
+        guardrails: GuardrailsDataParam | Omit = omit,
+        ignore_eos: bool | Omit = omit,
+        logit_bias: Dict[str, float] | Omit = omit,
+        logprobs: bool | Omit = omit,
+        max_completion_tokens: int | Omit = omit,
+        max_tokens: int | Omit = omit,
+        n: int | Omit = omit,
+        presence_penalty: float | Omit = omit,
+        reasoning_effort: str | Omit = omit,
+        response_format: Dict[str, object] | Omit = omit,
+        seed: int | Omit = omit,
+        stop: Union[str, SequenceNotStr[str]] | Omit = omit,
+        stream: bool | Omit = omit,
+        stream_options: Dict[str, bool] | Omit = omit,
+        temperature: float | Omit = omit,
+        tool_choice: Union[str, Dict[str, object]] | Omit = omit,
+        tools: Iterable[Dict[str, object]] | Omit = omit,
+        top_logprobs: int | Omit = omit,
+        top_p: float | Omit = omit,
+        user: str | Omit = omit,
+        vision: bool | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> GuardrailCheckResponse:
+        """
+        Chat completion for the provided conversation.
+
+        Args:
+          messages: A list of messages comprising the conversation so far
+
+          model: The model to use for completion. Must be one of the available models.
+
+          frequency_penalty: Positive values penalize new tokens based on their existing frequency in the
+              text.
+
+          function_call: Deprecated in favor of tool_choice. 'none' means the model will not call a
+              function and instead generates a message. 'auto' means the model can pick
+              between generating a message or calling a function. Specifying a particular
+              function via {'name': 'my_function'} forces the model to call that function.
+
+          guardrails: Guardrails specific options for the request.
+
+          ignore_eos: Ignore the eos when running
+
+          logit_bias: Modify the likelihood of specified tokens appearing in the completion. Maps
+              token IDs (as strings) to bias values from -100 to 100.
+
+          logprobs: Whether to return log probabilities of the output tokens or not. If true,
+              returns the log probabilities of each output token returned in the content of
+              message
+
+          max_completion_tokens: An upper bound for the number of tokens that can be generated for a completion,
+              including visible output tokens and reasoning tokens. Preferred over max_tokens
+              for reasoning models.
+
+          max_tokens: The maximum number of tokens that can be generated in the chat completion.
+
+          n: How many chat completion choices to generate for each input message.
+
+          presence_penalty: Positive values penalize new tokens based on whether they appear in the text so
+              far.
+
+          reasoning_effort: Constrains effort on reasoning for reasoning models. Reducing reasoning effort
+              can result in faster responses and fewer tokens used on reasoning in a response.
+
+          response_format:
+              Format of the response. Use {'type': 'json_object'} for JSON mode or {'type':
+              'json_schema', 'json_schema': {...}} for structured outputs.
+
+          seed: If specified, attempts to sample deterministically.
+
+          stop: Up to 4 sequences where the API will stop generating further tokens.
+
+          stream: If set, partial message deltas will be sent, like in ChatGPT.
+
+          stream_options: Options for streaming response. Only set this when stream=True. Supports
+              include_usage to receive token usage in the final stream chunk.
+
+          temperature: What sampling temperature to use, between 0 and 2.
+
+          tool_choice: Controls which (if any) tool is called by the model. 'none' means no tool is
+              called, 'auto' lets the model decide, 'required' forces a tool call.
+
+          tools: A list of tools the model may call. Each tool is an object with a 'type' field
+              and a 'function' definition.
+
+          top_logprobs: The number of most likely tokens to return at each token position.
+
+          top_p: An alternative to sampling with temperature, called nucleus sampling.
+
+          user: A unique identifier representing your end-user, used by some providers for abuse
+              monitoring.
+
+          vision: Whether this is a vision-capable request with image inputs.
+
+          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
+        """
+        if workspace is None:
+            workspace = self._client._get_workspace_path_param()
+        if not workspace:
+            raise ValueError(f"Expected a non-empty value for `workspace` but received {workspace!r}")
+        return await self._post(
+            path_template("/apis/guardrails/v2/workspaces/{workspace}/checks", workspace=workspace),
+            body=await async_maybe_transform(
+                {
+                    "messages": messages,
+                    "model": model,
+                    "frequency_penalty": frequency_penalty,
+                    "function_call": function_call,
+                    "guardrails": guardrails,
+                    "ignore_eos": ignore_eos,
+                    "logit_bias": logit_bias,
+                    "logprobs": logprobs,
+                    "max_completion_tokens": max_completion_tokens,
+                    "max_tokens": max_tokens,
+                    "n": n,
+                    "presence_penalty": presence_penalty,
+                    "reasoning_effort": reasoning_effort,
+                    "response_format": response_format,
+                    "seed": seed,
+                    "stop": stop,
+                    "stream": stream,
+                    "stream_options": stream_options,
+                    "temperature": temperature,
+                    "tool_choice": tool_choice,
+                    "tools": tools,
+                    "top_logprobs": top_logprobs,
+                    "top_p": top_p,
+                    "user": user,
+                    "vision": vision,
+                },
+                guardrail_check_params.GuardrailCheckParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=GuardrailCheckResponse,
+        )
+
+
+class GuardrailResourceWithRawResponse:
+    def __init__(self, guardrail: GuardrailResource) -> None:
+        self._guardrail = guardrail
+
+        self.check = to_raw_response_wrapper(
+            guardrail.check,
+        )
+
+    @cached_property
+    def configs(self) -> ConfigsResourceWithRawResponse:
+        return ConfigsResourceWithRawResponse(self._guardrail.configs)
+
+
+class AsyncGuardrailResourceWithRawResponse:
+    def __init__(self, guardrail: AsyncGuardrailResource) -> None:
+        self._guardrail = guardrail
+
+        self.check = async_to_raw_response_wrapper(
+            guardrail.check,
+        )
+
+    @cached_property
+    def configs(self) -> AsyncConfigsResourceWithRawResponse:
+        return AsyncConfigsResourceWithRawResponse(self._guardrail.configs)
+
+
+class GuardrailResourceWithStreamingResponse:
+    def __init__(self, guardrail: GuardrailResource) -> None:
+        self._guardrail = guardrail
+
+        self.check = to_streamed_response_wrapper(
+            guardrail.check,
+        )
+
+    @cached_property
+    def configs(self) -> ConfigsResourceWithStreamingResponse:
+        return ConfigsResourceWithStreamingResponse(self._guardrail.configs)
+
+
+class AsyncGuardrailResourceWithStreamingResponse:
+    def __init__(self, guardrail: AsyncGuardrailResource) -> None:
+        self._guardrail = guardrail
+
+        self.check = async_to_streamed_response_wrapper(
+            guardrail.check,
+        )
+
+    @cached_property
+    def configs(self) -> AsyncConfigsResourceWithStreamingResponse:
+        return AsyncConfigsResourceWithStreamingResponse(self._guardrail.configs)

nemo_platform/resources/iam/__init__.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 .iam import (
+    IamResource,
+    AsyncIamResource,
+    IamResourceWithRawResponse,
+    AsyncIamResourceWithRawResponse,
+    IamResourceWithStreamingResponse,
+    AsyncIamResourceWithStreamingResponse,
+)
+from .role_bindings import (
+    RoleBindingsResource,
+    AsyncRoleBindingsResource,
+    RoleBindingsResourceWithRawResponse,
+    AsyncRoleBindingsResourceWithRawResponse,
+    RoleBindingsResourceWithStreamingResponse,
+    AsyncRoleBindingsResourceWithStreamingResponse,
+)
+
+__all__ = [
+    "RoleBindingsResource",
+    "AsyncRoleBindingsResource",
+    "RoleBindingsResourceWithRawResponse",
+    "AsyncRoleBindingsResourceWithRawResponse",
+    "RoleBindingsResourceWithStreamingResponse",
+    "AsyncRoleBindingsResourceWithStreamingResponse",
+    "IamResource",
+    "AsyncIamResource",
+    "IamResourceWithRawResponse",
+    "AsyncIamResourceWithRawResponse",
+    "IamResourceWithStreamingResponse",
+    "AsyncIamResourceWithStreamingResponse",
+]

nemo_platform/resources/iam/api.md

@@ -0,0 +1,22 @@
+# Iam
+
+## RoleBindings
+
+Types:
+
+```python
+from nemo_platform.types.iam import (
+    DateRangeFilter,
+    RoleBinding,
+    RoleBindingFilter,
+    RoleBindingParam,
+    RoleBindingsPage,
+)
+```
+
+Methods:
+
+- <code title="post /apis/auth/v2/iam/role-bindings">client.iam.role_bindings.<a href="./src/nemo_platform/resources/iam/role_bindings.py">create</a>(\*\*<a href="src/nemo_platform/types/iam/role_binding_create_params.py">params</a>) -> <a href="./src/nemo_platform/types/iam/role_binding.py">RoleBinding</a></code>
+- <code title="get /apis/auth/v2/iam/role-bindings/{name}">client.iam.role_bindings.<a href="./src/nemo_platform/resources/iam/role_bindings.py">retrieve</a>(name) -> <a href="./src/nemo_platform/types/iam/role_binding.py">RoleBinding</a></code>
+- <code title="get /apis/auth/v2/iam/role-bindings">client.iam.role_bindings.<a href="./src/nemo_platform/resources/iam/role_bindings.py">list</a>(\*\*<a href="src/nemo_platform/types/iam/role_binding_list_params.py">params</a>) -> <a href="./src/nemo_platform/types/iam/role_binding.py">SyncDefaultPagination[RoleBinding]</a></code>
+- <code title="delete /apis/auth/v2/iam/role-bindings/{name}">client.iam.role_bindings.<a href="./src/nemo_platform/resources/iam/role_bindings.py">delete</a>(name, \*\*<a href="src/nemo_platform/types/iam/role_binding_delete_params.py">params</a>) -> <a href="./src/nemo_platform/types/shared/delete_response.py">DeleteResponse</a></code>

nemo_platform/resources/iam/iam.py

@@ -0,0 +1,117 @@
+# 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 ..._compat import cached_property
+from ..._resource import SyncAPIResource, AsyncAPIResource
+from .role_bindings import (
+    RoleBindingsResource,
+    AsyncRoleBindingsResource,
+    RoleBindingsResourceWithRawResponse,
+    AsyncRoleBindingsResourceWithRawResponse,
+    RoleBindingsResourceWithStreamingResponse,
+    AsyncRoleBindingsResourceWithStreamingResponse,
+)
+
+__all__ = ["IamResource", "AsyncIamResource"]
+
+
+class IamResource(SyncAPIResource):
+    @cached_property
+    def role_bindings(self) -> RoleBindingsResource:
+        return RoleBindingsResource(self._client)
+
+    @cached_property
+    def with_raw_response(self) -> IamResourceWithRawResponse:
+        """
+        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
+        """
+        return IamResourceWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> IamResourceWithStreamingResponse:
+        """
+        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
+        """
+        return IamResourceWithStreamingResponse(self)
+
+
+class AsyncIamResource(AsyncAPIResource):
+    @cached_property
+    def role_bindings(self) -> AsyncRoleBindingsResource:
+        return AsyncRoleBindingsResource(self._client)
+
+    @cached_property
+    def with_raw_response(self) -> AsyncIamResourceWithRawResponse:
+        """
+        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
+        """
+        return AsyncIamResourceWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AsyncIamResourceWithStreamingResponse:
+        """
+        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
+        """
+        return AsyncIamResourceWithStreamingResponse(self)
+
+
+class IamResourceWithRawResponse:
+    def __init__(self, iam: IamResource) -> None:
+        self._iam = iam
+
+    @cached_property
+    def role_bindings(self) -> RoleBindingsResourceWithRawResponse:
+        return RoleBindingsResourceWithRawResponse(self._iam.role_bindings)
+
+
+class AsyncIamResourceWithRawResponse:
+    def __init__(self, iam: AsyncIamResource) -> None:
+        self._iam = iam
+
+    @cached_property
+    def role_bindings(self) -> AsyncRoleBindingsResourceWithRawResponse:
+        return AsyncRoleBindingsResourceWithRawResponse(self._iam.role_bindings)
+
+
+class IamResourceWithStreamingResponse:
+    def __init__(self, iam: IamResource) -> None:
+        self._iam = iam
+
+    @cached_property
+    def role_bindings(self) -> RoleBindingsResourceWithStreamingResponse:
+        return RoleBindingsResourceWithStreamingResponse(self._iam.role_bindings)
+
+
+class AsyncIamResourceWithStreamingResponse:
+    def __init__(self, iam: AsyncIamResource) -> None:
+        self._iam = iam
+
+    @cached_property
+    def role_bindings(self) -> AsyncRoleBindingsResourceWithStreamingResponse:
+        return AsyncRoleBindingsResourceWithStreamingResponse(self._iam.role_bindings)