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

nemo_platform/resources/intake/exports/exports.py

@@ -0,0 +1,229 @@
+# 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
+
+import httpx
+
+from .jobs import (
+    JobsResource,
+    AsyncJobsResource,
+    JobsResourceWithRawResponse,
+    AsyncJobsResourceWithRawResponse,
+    JobsResourceWithStreamingResponse,
+    AsyncJobsResourceWithStreamingResponse,
+)
+from ...._types import Body, Query, Headers, NotGiven, 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.intake import export_preview_params
+from ....types.intake.export_preview_response import ExportPreviewResponse
+from ....types.intake.export_config_param_param import ExportConfigParamParam
+
+__all__ = ["ExportsResource", "AsyncExportsResource"]
+
+
+class ExportsResource(SyncAPIResource):
+    @cached_property
+    def jobs(self) -> JobsResource:
+        return JobsResource(self._client)
+
+    @cached_property
+    def with_raw_response(self) -> ExportsResourceWithRawResponse:
+        """
+        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 ExportsResourceWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> ExportsResourceWithStreamingResponse:
+        """
+        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 ExportsResourceWithStreamingResponse(self)
+
+    def preview(
+        self,
+        *,
+        workspace: str | None = None,
+        config: ExportConfigParamParam,
+        # 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,
+    ) -> ExportPreviewResponse:
+        """
+        Preview export data without writing to a file (max 100 records).
+
+        Args:
+          config: Input schema for export configuration.
+
+              Defines what entries to export and how to format them.
+
+          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/intake/v2/workspaces/{workspace}/export/preview", workspace=workspace),
+            body=maybe_transform({"config": config}, export_preview_params.ExportPreviewParams),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=ExportPreviewResponse,
+        )
+
+
+class AsyncExportsResource(AsyncAPIResource):
+    @cached_property
+    def jobs(self) -> AsyncJobsResource:
+        return AsyncJobsResource(self._client)
+
+    @cached_property
+    def with_raw_response(self) -> AsyncExportsResourceWithRawResponse:
+        """
+        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 AsyncExportsResourceWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AsyncExportsResourceWithStreamingResponse:
+        """
+        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 AsyncExportsResourceWithStreamingResponse(self)
+
+    async def preview(
+        self,
+        *,
+        workspace: str | None = None,
+        config: ExportConfigParamParam,
+        # 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,
+    ) -> ExportPreviewResponse:
+        """
+        Preview export data without writing to a file (max 100 records).
+
+        Args:
+          config: Input schema for export configuration.
+
+              Defines what entries to export and how to format them.
+
+          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/intake/v2/workspaces/{workspace}/export/preview", workspace=workspace),
+            body=await async_maybe_transform({"config": config}, export_preview_params.ExportPreviewParams),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=ExportPreviewResponse,
+        )
+
+
+class ExportsResourceWithRawResponse:
+    def __init__(self, exports: ExportsResource) -> None:
+        self._exports = exports
+
+        self.preview = to_raw_response_wrapper(
+            exports.preview,
+        )
+
+    @cached_property
+    def jobs(self) -> JobsResourceWithRawResponse:
+        return JobsResourceWithRawResponse(self._exports.jobs)
+
+
+class AsyncExportsResourceWithRawResponse:
+    def __init__(self, exports: AsyncExportsResource) -> None:
+        self._exports = exports
+
+        self.preview = async_to_raw_response_wrapper(
+            exports.preview,
+        )
+
+    @cached_property
+    def jobs(self) -> AsyncJobsResourceWithRawResponse:
+        return AsyncJobsResourceWithRawResponse(self._exports.jobs)
+
+
+class ExportsResourceWithStreamingResponse:
+    def __init__(self, exports: ExportsResource) -> None:
+        self._exports = exports
+
+        self.preview = to_streamed_response_wrapper(
+            exports.preview,
+        )
+
+    @cached_property
+    def jobs(self) -> JobsResourceWithStreamingResponse:
+        return JobsResourceWithStreamingResponse(self._exports.jobs)
+
+
+class AsyncExportsResourceWithStreamingResponse:
+    def __init__(self, exports: AsyncExportsResource) -> None:
+        self._exports = exports
+
+        self.preview = async_to_streamed_response_wrapper(
+            exports.preview,
+        )
+
+    @cached_property
+    def jobs(self) -> AsyncJobsResourceWithStreamingResponse:
+        return AsyncJobsResourceWithStreamingResponse(self._exports.jobs)

nemo_platform/resources/intake/exports/jobs.py

@@ -0,0 +1,464 @@
+# 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
+
+import httpx
+
+from ...._types import Body, Omit, Query, Headers, NotGiven, 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 ....pagination import SyncDefaultPagination, AsyncDefaultPagination
+from ...._base_client import AsyncPaginator, make_request_options
+from ....types.intake.exports import ExportJobSortField, job_list_params, job_create_params
+from ....types.intake.exports.export_job import ExportJob
+from ....types.intake.export_config_param_param import ExportConfigParamParam
+from ....types.intake.exports.export_job_sort_field import ExportJobSortField
+from ....types.intake.exports.export_job_filter_param import ExportJobFilterParam
+
+__all__ = ["JobsResource", "AsyncJobsResource"]
+
+
+class JobsResource(SyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> JobsResourceWithRawResponse:
+        """
+        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 JobsResourceWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> JobsResourceWithStreamingResponse:
+        """
+        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 JobsResourceWithStreamingResponse(self)
+
+    def create(
+        self,
+        *,
+        workspace: str | None = None,
+        config: ExportConfigParamParam,
+        output_file_url: str,
+        # 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,
+    ) -> ExportJob:
+        """
+        Export entries to an external file.
+
+        Use the `longest_per_thread` filter to export only the longest entry per thread,
+        which is useful for thread-based exports.
+
+        Supported output file URLs:
+
+        - NeMo Datastore: nds://workspace/dataset_name
+        - HuggingFace Dataset: hf://datasets/org/name/path/to/file
+        - Local filesystem: file:///path/to/export (for development)
+
+        Args:
+          config: Input schema for export configuration.
+
+              Defines what entries to export and how to format them.
+
+          output_file_url: The place where the exported file should be written (file://, hf://, nds://,
+              etc.)
+
+          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/intake/v2/workspaces/{workspace}/export/jobs", workspace=workspace),
+            body=maybe_transform(
+                {
+                    "config": config,
+                    "output_file_url": output_file_url,
+                },
+                job_create_params.JobCreateParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=ExportJob,
+        )
+
+    def retrieve(
+        self,
+        name: str,
+        *,
+        workspace: str | None = None,
+        # 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,
+    ) -> ExportJob:
+        """
+        Check the status of an export job.
+
+        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
+        """
+        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}")
+        if not name:
+            raise ValueError(f"Expected a non-empty value for `name` but received {name!r}")
+        return self._get(
+            path_template("/apis/intake/v2/workspaces/{workspace}/export/jobs/{name}", workspace=workspace, name=name),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=ExportJob,
+        )
+
+    def list(
+        self,
+        *,
+        workspace: str | None = None,
+        filter: ExportJobFilterParam | Omit = omit,
+        page: int | Omit = omit,
+        page_size: int | Omit = omit,
+        sort: ExportJobSortField | 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,
+    ) -> SyncDefaultPagination[ExportJob]:
+        """
+        List all export jobs with filtering capabilities.
+
+        Use `workspace=-` for cross-workspace listing.
+
+        Args:
+          filter: Filter export jobs by name, status, output_file_url, created_at, and updated_at.
+
+          page: Page number.
+
+          page_size: Page size.
+
+          sort: The field to sort by. To sort in decreasing order, use `-` in front of the field
+              name.
+
+          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._get_api_list(
+            path_template("/apis/intake/v2/workspaces/{workspace}/export/jobs", workspace=workspace),
+            page=SyncDefaultPagination[ExportJob],
+            options=make_request_options(
+                extra_headers=extra_headers,
+                extra_query=extra_query,
+                extra_body=extra_body,
+                timeout=timeout,
+                query=maybe_transform(
+                    {
+                        "filter": filter,
+                        "page": page,
+                        "page_size": page_size,
+                        "sort": sort,
+                    },
+                    job_list_params.JobListParams,
+                ),
+            ),
+            model=ExportJob,
+        )
+
+
+class AsyncJobsResource(AsyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> AsyncJobsResourceWithRawResponse:
+        """
+        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 AsyncJobsResourceWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AsyncJobsResourceWithStreamingResponse:
+        """
+        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 AsyncJobsResourceWithStreamingResponse(self)
+
+    async def create(
+        self,
+        *,
+        workspace: str | None = None,
+        config: ExportConfigParamParam,
+        output_file_url: str,
+        # 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,
+    ) -> ExportJob:
+        """
+        Export entries to an external file.
+
+        Use the `longest_per_thread` filter to export only the longest entry per thread,
+        which is useful for thread-based exports.
+
+        Supported output file URLs:
+
+        - NeMo Datastore: nds://workspace/dataset_name
+        - HuggingFace Dataset: hf://datasets/org/name/path/to/file
+        - Local filesystem: file:///path/to/export (for development)
+
+        Args:
+          config: Input schema for export configuration.
+
+              Defines what entries to export and how to format them.
+
+          output_file_url: The place where the exported file should be written (file://, hf://, nds://,
+              etc.)
+
+          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/intake/v2/workspaces/{workspace}/export/jobs", workspace=workspace),
+            body=await async_maybe_transform(
+                {
+                    "config": config,
+                    "output_file_url": output_file_url,
+                },
+                job_create_params.JobCreateParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=ExportJob,
+        )
+
+    async def retrieve(
+        self,
+        name: str,
+        *,
+        workspace: str | None = None,
+        # 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,
+    ) -> ExportJob:
+        """
+        Check the status of an export job.
+
+        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
+        """
+        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}")
+        if not name:
+            raise ValueError(f"Expected a non-empty value for `name` but received {name!r}")
+        return await self._get(
+            path_template("/apis/intake/v2/workspaces/{workspace}/export/jobs/{name}", workspace=workspace, name=name),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=ExportJob,
+        )
+
+    def list(
+        self,
+        *,
+        workspace: str | None = None,
+        filter: ExportJobFilterParam | Omit = omit,
+        page: int | Omit = omit,
+        page_size: int | Omit = omit,
+        sort: ExportJobSortField | 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,
+    ) -> AsyncPaginator[ExportJob, AsyncDefaultPagination[ExportJob]]:
+        """
+        List all export jobs with filtering capabilities.
+
+        Use `workspace=-` for cross-workspace listing.
+
+        Args:
+          filter: Filter export jobs by name, status, output_file_url, created_at, and updated_at.
+
+          page: Page number.
+
+          page_size: Page size.
+
+          sort: The field to sort by. To sort in decreasing order, use `-` in front of the field
+              name.
+
+          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._get_api_list(
+            path_template("/apis/intake/v2/workspaces/{workspace}/export/jobs", workspace=workspace),
+            page=AsyncDefaultPagination[ExportJob],
+            options=make_request_options(
+                extra_headers=extra_headers,
+                extra_query=extra_query,
+                extra_body=extra_body,
+                timeout=timeout,
+                query=maybe_transform(
+                    {
+                        "filter": filter,
+                        "page": page,
+                        "page_size": page_size,
+                        "sort": sort,
+                    },
+                    job_list_params.JobListParams,
+                ),
+            ),
+            model=ExportJob,
+        )
+
+
+class JobsResourceWithRawResponse:
+    def __init__(self, jobs: JobsResource) -> None:
+        self._jobs = jobs
+
+        self.create = to_raw_response_wrapper(
+            jobs.create,
+        )
+        self.retrieve = to_raw_response_wrapper(
+            jobs.retrieve,
+        )
+        self.list = to_raw_response_wrapper(
+            jobs.list,
+        )
+
+
+class AsyncJobsResourceWithRawResponse:
+    def __init__(self, jobs: AsyncJobsResource) -> None:
+        self._jobs = jobs
+
+        self.create = async_to_raw_response_wrapper(
+            jobs.create,
+        )
+        self.retrieve = async_to_raw_response_wrapper(
+            jobs.retrieve,
+        )
+        self.list = async_to_raw_response_wrapper(
+            jobs.list,
+        )
+
+
+class JobsResourceWithStreamingResponse:
+    def __init__(self, jobs: JobsResource) -> None:
+        self._jobs = jobs
+
+        self.create = to_streamed_response_wrapper(
+            jobs.create,
+        )
+        self.retrieve = to_streamed_response_wrapper(
+            jobs.retrieve,
+        )
+        self.list = to_streamed_response_wrapper(
+            jobs.list,
+        )
+
+
+class AsyncJobsResourceWithStreamingResponse:
+    def __init__(self, jobs: AsyncJobsResource) -> None:
+        self._jobs = jobs
+
+        self.create = async_to_streamed_response_wrapper(
+            jobs.create,
+        )
+        self.retrieve = async_to_streamed_response_wrapper(
+            jobs.retrieve,
+        )
+        self.list = async_to_streamed_response_wrapper(
+            jobs.list,
+        )