gcore 0.15.0__py3-none-any.whl → 0.17.0__py3-none-any.whl

gcore/resources/cloud/inference/applications/deployments.py

@@ -18,7 +18,7 @@ from ....._response import (
 )
 from ....._base_client import make_request_options
 from .....types.cloud.task_id_list import TaskIDList
-from .....types.cloud.inference.applications import deployment_patch_params, deployment_create_params
+from .....types.cloud.inference.applications import deployment_create_params, deployment_update_params
 from .....types.cloud.inference.applications.inference_application_deployment import InferenceApplicationDeployment
 from .....types.cloud.inference.applications.inference_application_deployment_list import (
     InferenceApplicationDeploymentList,
@@ -93,9 +93,7 @@ class DeploymentsResource(SyncAPIResource):
         if project_id is None:
             project_id = self._client._get_cloud_project_id_path_param()
         return self._post(
-            f"/cloud/v3/inference/applications/{project_id}/deployments"
-            if self._client._base_url_overridden
-            else f"https://api.gcore.com//cloud/v3/inference/applications/{project_id}/deployments",
+            f"/cloud/v3/inference/applications/{project_id}/deployments",
             body=maybe_transform(
                 {
                     "application_name": application_name,
@@ -112,25 +110,39 @@ class DeploymentsResource(SyncAPIResource):
             cast_to=TaskIDList,
         )
 
-    def list(
+    def update(
         self,
+        deployment_name: str,
         *,
         project_id: int | None = None,
+        api_keys: SequenceNotStr[str] | Omit = omit,
+        components_configuration: Dict[str, Optional[deployment_update_params.ComponentsConfiguration]] | Omit = omit,
+        regions: Iterable[int] | 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,
-    ) -> InferenceApplicationDeploymentList:
-        """
-        Returns a list of your application deployments, including deployment names,
-        associated catalog applications, regions, component configurations, and current
-        status. Useful for monitoring and managing all active AI application instances.
+    ) -> TaskIDList:
+        """Updates an existing application deployment.
+
+        You can modify the target regions
+        and update configurations for individual components. To disable a component, set
+        its value to null. Only the provided fields will be updated; all others remain
+        unchanged.
 
         Args:
           project_id: Project ID
 
+          deployment_name: Name of deployment
+
+          api_keys: List of API keys for the application
+
+          components_configuration: Mapping of component names to their configuration (e.g., `"model": {...}`)
+
+          regions: Geographical regions to be updated for the deployment
+
           extra_headers: Send extra headers
 
           extra_query: Add additional query parameters to the request
@@ -141,19 +153,26 @@ class DeploymentsResource(SyncAPIResource):
         """
         if project_id is None:
             project_id = self._client._get_cloud_project_id_path_param()
-        return self._get(
-            f"/cloud/v3/inference/applications/{project_id}/deployments"
-            if self._client._base_url_overridden
-            else f"https://api.gcore.com//cloud/v3/inference/applications/{project_id}/deployments",
+        if not deployment_name:
+            raise ValueError(f"Expected a non-empty value for `deployment_name` but received {deployment_name!r}")
+        return self._patch(
+            f"/cloud/v3/inference/applications/{project_id}/deployments/{deployment_name}",
+            body=maybe_transform(
+                {
+                    "api_keys": api_keys,
+                    "components_configuration": components_configuration,
+                    "regions": regions,
+                },
+                deployment_update_params.DeploymentUpdateParams,
+            ),
             options=make_request_options(
                 extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
             ),
-            cast_to=InferenceApplicationDeploymentList,
+            cast_to=TaskIDList,
         )
 
-    def delete(
+    def list(
         self,
-        deployment_name: str,
         *,
         project_id: int | None = None,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
@@ -162,17 +181,15 @@ class DeploymentsResource(SyncAPIResource):
         extra_query: Query | None = None,
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = not_given,
-    ) -> TaskIDList:
+    ) -> InferenceApplicationDeploymentList:
         """
-        Deletes an existing application deployment along with all associated resources.
-        This action will permanently remove the deployment and **terminate all related
-        inference instances** that are part of the application.
+        Returns a list of your application deployments, including deployment names,
+        associated catalog applications, regions, component configurations, and current
+        status. Useful for monitoring and managing all active AI application instances.
 
         Args:
           project_id: Project ID
 
-          deployment_name: Name of deployment
-
           extra_headers: Send extra headers
 
           extra_query: Add additional query parameters to the request
@@ -183,19 +200,15 @@ class DeploymentsResource(SyncAPIResource):
         """
         if project_id is None:
             project_id = self._client._get_cloud_project_id_path_param()
-        if not deployment_name:
-            raise ValueError(f"Expected a non-empty value for `deployment_name` but received {deployment_name!r}")
-        return self._delete(
-            f"/cloud/v3/inference/applications/{project_id}/deployments/{deployment_name}"
-            if self._client._base_url_overridden
-            else f"https://api.gcore.com//cloud/v3/inference/applications/{project_id}/deployments/{deployment_name}",
+        return self._get(
+            f"/cloud/v3/inference/applications/{project_id}/deployments",
             options=make_request_options(
                 extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
             ),
-            cast_to=TaskIDList,
+            cast_to=InferenceApplicationDeploymentList,
         )
 
-    def get(
+    def delete(
         self,
         deployment_name: str,
         *,
@@ -206,13 +219,11 @@ class DeploymentsResource(SyncAPIResource):
         extra_query: Query | None = None,
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = not_given,
-    ) -> InferenceApplicationDeployment:
-        """Retrieves detailed information about a specific application deployment.
-
-        The
-        response includes the catalog application it was created from, deployment name,
-        active regions, configuration of each component, and the current status of the
-        deployment.
+    ) -> TaskIDList:
+        """
+        Deletes an existing application deployment along with all associated resources.
+        This action will permanently remove the deployment and **terminate all related
+        inference instances** that are part of the application.
 
         Args:
           project_id: Project ID
@@ -231,49 +242,38 @@ class DeploymentsResource(SyncAPIResource):
             project_id = self._client._get_cloud_project_id_path_param()
         if not deployment_name:
             raise ValueError(f"Expected a non-empty value for `deployment_name` but received {deployment_name!r}")
-        return self._get(
-            f"/cloud/v3/inference/applications/{project_id}/deployments/{deployment_name}"
-            if self._client._base_url_overridden
-            else f"https://api.gcore.com//cloud/v3/inference/applications/{project_id}/deployments/{deployment_name}",
+        return self._delete(
+            f"/cloud/v3/inference/applications/{project_id}/deployments/{deployment_name}",
             options=make_request_options(
                 extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
             ),
-            cast_to=InferenceApplicationDeployment,
+            cast_to=TaskIDList,
         )
 
-    def patch(
+    def get(
         self,
         deployment_name: str,
         *,
         project_id: int | None = None,
-        api_keys: SequenceNotStr[str] | Omit = omit,
-        components_configuration: Dict[str, Optional[deployment_patch_params.ComponentsConfiguration]] | Omit = omit,
-        regions: Iterable[int] | 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,
-    ) -> TaskIDList:
-        """Updates an existing application deployment.
+    ) -> InferenceApplicationDeployment:
+        """Retrieves detailed information about a specific application deployment.
 
-        You can modify the target regions
-        and update configurations for individual components. To disable a component, set
-        its value to null. Only the provided fields will be updated; all others remain
-        unchanged.
+        The
+        response includes the catalog application it was created from, deployment name,
+        active regions, configuration of each component, and the current status of the
+        deployment.
 
         Args:
           project_id: Project ID
 
           deployment_name: Name of deployment
 
-          api_keys: List of API keys for the application
-
-          components_configuration: Mapping of component names to their configuration (e.g., `"model": {...}`)
-
-          regions: Geographical regions to be updated for the deployment
-
           extra_headers: Send extra headers
 
           extra_query: Add additional query parameters to the request
@@ -286,22 +286,12 @@ class DeploymentsResource(SyncAPIResource):
             project_id = self._client._get_cloud_project_id_path_param()
         if not deployment_name:
             raise ValueError(f"Expected a non-empty value for `deployment_name` but received {deployment_name!r}")
-        return self._patch(
-            f"/cloud/v3/inference/applications/{project_id}/deployments/{deployment_name}"
-            if self._client._base_url_overridden
-            else f"https://api.gcore.com//cloud/v3/inference/applications/{project_id}/deployments/{deployment_name}",
-            body=maybe_transform(
-                {
-                    "api_keys": api_keys,
-                    "components_configuration": components_configuration,
-                    "regions": regions,
-                },
-                deployment_patch_params.DeploymentPatchParams,
-            ),
+        return self._get(
+            f"/cloud/v3/inference/applications/{project_id}/deployments/{deployment_name}",
             options=make_request_options(
                 extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
             ),
-            cast_to=TaskIDList,
+            cast_to=InferenceApplicationDeployment,
         )
 
 
@@ -371,9 +361,7 @@ class AsyncDeploymentsResource(AsyncAPIResource):
         if project_id is None:
             project_id = self._client._get_cloud_project_id_path_param()
         return await self._post(
-            f"/cloud/v3/inference/applications/{project_id}/deployments"
-            if self._client._base_url_overridden
-            else f"https://api.gcore.com//cloud/v3/inference/applications/{project_id}/deployments",
+            f"/cloud/v3/inference/applications/{project_id}/deployments",
             body=await async_maybe_transform(
                 {
                     "application_name": application_name,
@@ -390,25 +378,39 @@ class AsyncDeploymentsResource(AsyncAPIResource):
             cast_to=TaskIDList,
         )
 
-    async def list(
+    async def update(
         self,
+        deployment_name: str,
         *,
         project_id: int | None = None,
+        api_keys: SequenceNotStr[str] | Omit = omit,
+        components_configuration: Dict[str, Optional[deployment_update_params.ComponentsConfiguration]] | Omit = omit,
+        regions: Iterable[int] | 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,
-    ) -> InferenceApplicationDeploymentList:
-        """
-        Returns a list of your application deployments, including deployment names,
-        associated catalog applications, regions, component configurations, and current
-        status. Useful for monitoring and managing all active AI application instances.
+    ) -> TaskIDList:
+        """Updates an existing application deployment.
+
+        You can modify the target regions
+        and update configurations for individual components. To disable a component, set
+        its value to null. Only the provided fields will be updated; all others remain
+        unchanged.
 
         Args:
           project_id: Project ID
 
+          deployment_name: Name of deployment
+
+          api_keys: List of API keys for the application
+
+          components_configuration: Mapping of component names to their configuration (e.g., `"model": {...}`)
+
+          regions: Geographical regions to be updated for the deployment
+
           extra_headers: Send extra headers
 
           extra_query: Add additional query parameters to the request
@@ -419,19 +421,26 @@ class AsyncDeploymentsResource(AsyncAPIResource):
         """
         if project_id is None:
             project_id = self._client._get_cloud_project_id_path_param()
-        return await self._get(
-            f"/cloud/v3/inference/applications/{project_id}/deployments"
-            if self._client._base_url_overridden
-            else f"https://api.gcore.com//cloud/v3/inference/applications/{project_id}/deployments",
+        if not deployment_name:
+            raise ValueError(f"Expected a non-empty value for `deployment_name` but received {deployment_name!r}")
+        return await self._patch(
+            f"/cloud/v3/inference/applications/{project_id}/deployments/{deployment_name}",
+            body=await async_maybe_transform(
+                {
+                    "api_keys": api_keys,
+                    "components_configuration": components_configuration,
+                    "regions": regions,
+                },
+                deployment_update_params.DeploymentUpdateParams,
+            ),
             options=make_request_options(
                 extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
             ),
-            cast_to=InferenceApplicationDeploymentList,
+            cast_to=TaskIDList,
         )
 
-    async def delete(
+    async def list(
         self,
-        deployment_name: str,
         *,
         project_id: int | None = None,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
@@ -440,17 +449,15 @@ class AsyncDeploymentsResource(AsyncAPIResource):
         extra_query: Query | None = None,
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = not_given,
-    ) -> TaskIDList:
+    ) -> InferenceApplicationDeploymentList:
         """
-        Deletes an existing application deployment along with all associated resources.
-        This action will permanently remove the deployment and **terminate all related
-        inference instances** that are part of the application.
+        Returns a list of your application deployments, including deployment names,
+        associated catalog applications, regions, component configurations, and current
+        status. Useful for monitoring and managing all active AI application instances.
 
         Args:
           project_id: Project ID
 
-          deployment_name: Name of deployment
-
           extra_headers: Send extra headers
 
           extra_query: Add additional query parameters to the request
@@ -461,19 +468,15 @@ class AsyncDeploymentsResource(AsyncAPIResource):
         """
         if project_id is None:
             project_id = self._client._get_cloud_project_id_path_param()
-        if not deployment_name:
-            raise ValueError(f"Expected a non-empty value for `deployment_name` but received {deployment_name!r}")
-        return await self._delete(
-            f"/cloud/v3/inference/applications/{project_id}/deployments/{deployment_name}"
-            if self._client._base_url_overridden
-            else f"https://api.gcore.com//cloud/v3/inference/applications/{project_id}/deployments/{deployment_name}",
+        return await self._get(
+            f"/cloud/v3/inference/applications/{project_id}/deployments",
             options=make_request_options(
                 extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
             ),
-            cast_to=TaskIDList,
+            cast_to=InferenceApplicationDeploymentList,
         )
 
-    async def get(
+    async def delete(
         self,
         deployment_name: str,
         *,
@@ -484,13 +487,11 @@ class AsyncDeploymentsResource(AsyncAPIResource):
         extra_query: Query | None = None,
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = not_given,
-    ) -> InferenceApplicationDeployment:
-        """Retrieves detailed information about a specific application deployment.
-
-        The
-        response includes the catalog application it was created from, deployment name,
-        active regions, configuration of each component, and the current status of the
-        deployment.
+    ) -> TaskIDList:
+        """
+        Deletes an existing application deployment along with all associated resources.
+        This action will permanently remove the deployment and **terminate all related
+        inference instances** that are part of the application.
 
         Args:
           project_id: Project ID
@@ -509,49 +510,38 @@ class AsyncDeploymentsResource(AsyncAPIResource):
             project_id = self._client._get_cloud_project_id_path_param()
         if not deployment_name:
             raise ValueError(f"Expected a non-empty value for `deployment_name` but received {deployment_name!r}")
-        return await self._get(
-            f"/cloud/v3/inference/applications/{project_id}/deployments/{deployment_name}"
-            if self._client._base_url_overridden
-            else f"https://api.gcore.com//cloud/v3/inference/applications/{project_id}/deployments/{deployment_name}",
+        return await self._delete(
+            f"/cloud/v3/inference/applications/{project_id}/deployments/{deployment_name}",
             options=make_request_options(
                 extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
             ),
-            cast_to=InferenceApplicationDeployment,
+            cast_to=TaskIDList,
         )
 
-    async def patch(
+    async def get(
         self,
         deployment_name: str,
         *,
         project_id: int | None = None,
-        api_keys: SequenceNotStr[str] | Omit = omit,
-        components_configuration: Dict[str, Optional[deployment_patch_params.ComponentsConfiguration]] | Omit = omit,
-        regions: Iterable[int] | 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,
-    ) -> TaskIDList:
-        """Updates an existing application deployment.
+    ) -> InferenceApplicationDeployment:
+        """Retrieves detailed information about a specific application deployment.
 
-        You can modify the target regions
-        and update configurations for individual components. To disable a component, set
-        its value to null. Only the provided fields will be updated; all others remain
-        unchanged.
+        The
+        response includes the catalog application it was created from, deployment name,
+        active regions, configuration of each component, and the current status of the
+        deployment.
 
         Args:
           project_id: Project ID
 
           deployment_name: Name of deployment
 
-          api_keys: List of API keys for the application
-
-          components_configuration: Mapping of component names to their configuration (e.g., `"model": {...}`)
-
-          regions: Geographical regions to be updated for the deployment
-
           extra_headers: Send extra headers
 
           extra_query: Add additional query parameters to the request
@@ -564,22 +554,12 @@ class AsyncDeploymentsResource(AsyncAPIResource):
             project_id = self._client._get_cloud_project_id_path_param()
         if not deployment_name:
             raise ValueError(f"Expected a non-empty value for `deployment_name` but received {deployment_name!r}")
-        return await self._patch(
-            f"/cloud/v3/inference/applications/{project_id}/deployments/{deployment_name}"
-            if self._client._base_url_overridden
-            else f"https://api.gcore.com//cloud/v3/inference/applications/{project_id}/deployments/{deployment_name}",
-            body=await async_maybe_transform(
-                {
-                    "api_keys": api_keys,
-                    "components_configuration": components_configuration,
-                    "regions": regions,
-                },
-                deployment_patch_params.DeploymentPatchParams,
-            ),
+        return await self._get(
+            f"/cloud/v3/inference/applications/{project_id}/deployments/{deployment_name}",
             options=make_request_options(
                 extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
             ),
-            cast_to=TaskIDList,
+            cast_to=InferenceApplicationDeployment,
         )
 
 
@@ -590,6 +570,9 @@ class DeploymentsResourceWithRawResponse:
         self.create = to_raw_response_wrapper(
             deployments.create,
         )
+        self.update = to_raw_response_wrapper(
+            deployments.update,
+        )
         self.list = to_raw_response_wrapper(
             deployments.list,
         )
@@ -599,9 +582,6 @@ class DeploymentsResourceWithRawResponse:
         self.get = to_raw_response_wrapper(
             deployments.get,
         )
-        self.patch = to_raw_response_wrapper(
-            deployments.patch,
-        )
 
 
 class AsyncDeploymentsResourceWithRawResponse:
@@ -611,6 +591,9 @@ class AsyncDeploymentsResourceWithRawResponse:
         self.create = async_to_raw_response_wrapper(
             deployments.create,
         )
+        self.update = async_to_raw_response_wrapper(
+            deployments.update,
+        )
         self.list = async_to_raw_response_wrapper(
             deployments.list,
         )
@@ -620,9 +603,6 @@ class AsyncDeploymentsResourceWithRawResponse:
         self.get = async_to_raw_response_wrapper(
             deployments.get,
         )
-        self.patch = async_to_raw_response_wrapper(
-            deployments.patch,
-        )
 
 
 class DeploymentsResourceWithStreamingResponse:
@@ -632,6 +612,9 @@ class DeploymentsResourceWithStreamingResponse:
         self.create = to_streamed_response_wrapper(
             deployments.create,
         )
+        self.update = to_streamed_response_wrapper(
+            deployments.update,
+        )
         self.list = to_streamed_response_wrapper(
             deployments.list,
         )
@@ -641,9 +624,6 @@ class DeploymentsResourceWithStreamingResponse:
         self.get = to_streamed_response_wrapper(
             deployments.get,
         )
-        self.patch = to_streamed_response_wrapper(
-            deployments.patch,
-        )
 
 
 class AsyncDeploymentsResourceWithStreamingResponse:
@@ -653,6 +633,9 @@ class AsyncDeploymentsResourceWithStreamingResponse:
         self.create = async_to_streamed_response_wrapper(
             deployments.create,
         )
+        self.update = async_to_streamed_response_wrapper(
+            deployments.update,
+        )
         self.list = async_to_streamed_response_wrapper(
             deployments.list,
         )
@@ -662,6 +645,3 @@ class AsyncDeploymentsResourceWithStreamingResponse:
         self.get = async_to_streamed_response_wrapper(
             deployments.get,
         )
-        self.patch = async_to_streamed_response_wrapper(
-            deployments.patch,
-        )

gcore/resources/cloud/inference/applications/templates.py

@@ -58,9 +58,7 @@ class TemplatesResource(SyncAPIResource):
         required to create a fully functional application deployment.
         """
         return self._get(
-            "/cloud/v3/inference/applications/catalog"
-            if self._client._base_url_overridden
-            else "https://api.gcore.com//cloud/v3/inference/applications/catalog",
+            "/cloud/v3/inference/applications/catalog",
             options=make_request_options(
                 extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
             ),
@@ -99,9 +97,7 @@ class TemplatesResource(SyncAPIResource):
         if not application_name:
             raise ValueError(f"Expected a non-empty value for `application_name` but received {application_name!r}")
         return self._get(
-            f"/cloud/v3/inference/applications/catalog/{application_name}"
-            if self._client._base_url_overridden
-            else f"https://api.gcore.com//cloud/v3/inference/applications/catalog/{application_name}",
+            f"/cloud/v3/inference/applications/catalog/{application_name}",
             options=make_request_options(
                 extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
             ),
@@ -147,9 +143,7 @@ class AsyncTemplatesResource(AsyncAPIResource):
         required to create a fully functional application deployment.
         """
         return await self._get(
-            "/cloud/v3/inference/applications/catalog"
-            if self._client._base_url_overridden
-            else "https://api.gcore.com//cloud/v3/inference/applications/catalog",
+            "/cloud/v3/inference/applications/catalog",
             options=make_request_options(
                 extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
             ),
@@ -188,9 +182,7 @@ class AsyncTemplatesResource(AsyncAPIResource):
         if not application_name:
             raise ValueError(f"Expected a non-empty value for `application_name` but received {application_name!r}")
         return await self._get(
-            f"/cloud/v3/inference/applications/catalog/{application_name}"
-            if self._client._base_url_overridden
-            else f"https://api.gcore.com//cloud/v3/inference/applications/catalog/{application_name}",
+            f"/cloud/v3/inference/applications/catalog/{application_name}",
             options=make_request_options(
                 extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
             ),