gcore 0.1.0a1__py3-none-any.whl

gcore/resources/cloud/inference/inference.py

@@ -0,0 +1,295 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+import httpx
+
+from .models import (
+    ModelsResource,
+    AsyncModelsResource,
+    ModelsResourceWithRawResponse,
+    AsyncModelsResourceWithRawResponse,
+    ModelsResourceWithStreamingResponse,
+    AsyncModelsResourceWithStreamingResponse,
+)
+from .flavors import (
+    FlavorsResource,
+    AsyncFlavorsResource,
+    FlavorsResourceWithRawResponse,
+    AsyncFlavorsResourceWithRawResponse,
+    FlavorsResourceWithStreamingResponse,
+    AsyncFlavorsResourceWithStreamingResponse,
+)
+from .secrets import (
+    SecretsResource,
+    AsyncSecretsResource,
+    SecretsResourceWithRawResponse,
+    AsyncSecretsResourceWithRawResponse,
+    SecretsResourceWithStreamingResponse,
+    AsyncSecretsResourceWithStreamingResponse,
+)
+from ...._types import NOT_GIVEN, Body, Query, Headers, NotGiven
+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 .registry_credentials import (
+    RegistryCredentialsResource,
+    AsyncRegistryCredentialsResource,
+    RegistryCredentialsResourceWithRawResponse,
+    AsyncRegistryCredentialsResourceWithRawResponse,
+    RegistryCredentialsResourceWithStreamingResponse,
+    AsyncRegistryCredentialsResourceWithStreamingResponse,
+)
+from .deployments.deployments import (
+    DeploymentsResource,
+    AsyncDeploymentsResource,
+    DeploymentsResourceWithRawResponse,
+    AsyncDeploymentsResourceWithRawResponse,
+    DeploymentsResourceWithStreamingResponse,
+    AsyncDeploymentsResourceWithStreamingResponse,
+)
+from ....types.cloud.region_capacity_list import RegionCapacityList
+
+__all__ = ["InferenceResource", "AsyncInferenceResource"]
+
+
+class InferenceResource(SyncAPIResource):
+    @cached_property
+    def flavors(self) -> FlavorsResource:
+        return FlavorsResource(self._client)
+
+    @cached_property
+    def models(self) -> ModelsResource:
+        return ModelsResource(self._client)
+
+    @cached_property
+    def deployments(self) -> DeploymentsResource:
+        return DeploymentsResource(self._client)
+
+    @cached_property
+    def registry_credentials(self) -> RegistryCredentialsResource:
+        return RegistryCredentialsResource(self._client)
+
+    @cached_property
+    def secrets(self) -> SecretsResource:
+        return SecretsResource(self._client)
+
+    @cached_property
+    def with_raw_response(self) -> InferenceResourceWithRawResponse:
+        """
+        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://www.github.com/G-Core/gcore-python#accessing-raw-response-data-eg-headers
+        """
+        return InferenceResourceWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> InferenceResourceWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/G-Core/gcore-python#with_streaming_response
+        """
+        return InferenceResourceWithStreamingResponse(self)
+
+    def get_capacity_by_region(
+        self,
+        *,
+        # 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,
+    ) -> RegionCapacityList:
+        """Get inference capacity by region"""
+        return self._get(
+            "/cloud/v3/inference/capacity",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=RegionCapacityList,
+        )
+
+
+class AsyncInferenceResource(AsyncAPIResource):
+    @cached_property
+    def flavors(self) -> AsyncFlavorsResource:
+        return AsyncFlavorsResource(self._client)
+
+    @cached_property
+    def models(self) -> AsyncModelsResource:
+        return AsyncModelsResource(self._client)
+
+    @cached_property
+    def deployments(self) -> AsyncDeploymentsResource:
+        return AsyncDeploymentsResource(self._client)
+
+    @cached_property
+    def registry_credentials(self) -> AsyncRegistryCredentialsResource:
+        return AsyncRegistryCredentialsResource(self._client)
+
+    @cached_property
+    def secrets(self) -> AsyncSecretsResource:
+        return AsyncSecretsResource(self._client)
+
+    @cached_property
+    def with_raw_response(self) -> AsyncInferenceResourceWithRawResponse:
+        """
+        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://www.github.com/G-Core/gcore-python#accessing-raw-response-data-eg-headers
+        """
+        return AsyncInferenceResourceWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AsyncInferenceResourceWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/G-Core/gcore-python#with_streaming_response
+        """
+        return AsyncInferenceResourceWithStreamingResponse(self)
+
+    async def get_capacity_by_region(
+        self,
+        *,
+        # 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,
+    ) -> RegionCapacityList:
+        """Get inference capacity by region"""
+        return await self._get(
+            "/cloud/v3/inference/capacity",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=RegionCapacityList,
+        )
+
+
+class InferenceResourceWithRawResponse:
+    def __init__(self, inference: InferenceResource) -> None:
+        self._inference = inference
+
+        self.get_capacity_by_region = to_raw_response_wrapper(
+            inference.get_capacity_by_region,
+        )
+
+    @cached_property
+    def flavors(self) -> FlavorsResourceWithRawResponse:
+        return FlavorsResourceWithRawResponse(self._inference.flavors)
+
+    @cached_property
+    def models(self) -> ModelsResourceWithRawResponse:
+        return ModelsResourceWithRawResponse(self._inference.models)
+
+    @cached_property
+    def deployments(self) -> DeploymentsResourceWithRawResponse:
+        return DeploymentsResourceWithRawResponse(self._inference.deployments)
+
+    @cached_property
+    def registry_credentials(self) -> RegistryCredentialsResourceWithRawResponse:
+        return RegistryCredentialsResourceWithRawResponse(self._inference.registry_credentials)
+
+    @cached_property
+    def secrets(self) -> SecretsResourceWithRawResponse:
+        return SecretsResourceWithRawResponse(self._inference.secrets)
+
+
+class AsyncInferenceResourceWithRawResponse:
+    def __init__(self, inference: AsyncInferenceResource) -> None:
+        self._inference = inference
+
+        self.get_capacity_by_region = async_to_raw_response_wrapper(
+            inference.get_capacity_by_region,
+        )
+
+    @cached_property
+    def flavors(self) -> AsyncFlavorsResourceWithRawResponse:
+        return AsyncFlavorsResourceWithRawResponse(self._inference.flavors)
+
+    @cached_property
+    def models(self) -> AsyncModelsResourceWithRawResponse:
+        return AsyncModelsResourceWithRawResponse(self._inference.models)
+
+    @cached_property
+    def deployments(self) -> AsyncDeploymentsResourceWithRawResponse:
+        return AsyncDeploymentsResourceWithRawResponse(self._inference.deployments)
+
+    @cached_property
+    def registry_credentials(self) -> AsyncRegistryCredentialsResourceWithRawResponse:
+        return AsyncRegistryCredentialsResourceWithRawResponse(self._inference.registry_credentials)
+
+    @cached_property
+    def secrets(self) -> AsyncSecretsResourceWithRawResponse:
+        return AsyncSecretsResourceWithRawResponse(self._inference.secrets)
+
+
+class InferenceResourceWithStreamingResponse:
+    def __init__(self, inference: InferenceResource) -> None:
+        self._inference = inference
+
+        self.get_capacity_by_region = to_streamed_response_wrapper(
+            inference.get_capacity_by_region,
+        )
+
+    @cached_property
+    def flavors(self) -> FlavorsResourceWithStreamingResponse:
+        return FlavorsResourceWithStreamingResponse(self._inference.flavors)
+
+    @cached_property
+    def models(self) -> ModelsResourceWithStreamingResponse:
+        return ModelsResourceWithStreamingResponse(self._inference.models)
+
+    @cached_property
+    def deployments(self) -> DeploymentsResourceWithStreamingResponse:
+        return DeploymentsResourceWithStreamingResponse(self._inference.deployments)
+
+    @cached_property
+    def registry_credentials(self) -> RegistryCredentialsResourceWithStreamingResponse:
+        return RegistryCredentialsResourceWithStreamingResponse(self._inference.registry_credentials)
+
+    @cached_property
+    def secrets(self) -> SecretsResourceWithStreamingResponse:
+        return SecretsResourceWithStreamingResponse(self._inference.secrets)
+
+
+class AsyncInferenceResourceWithStreamingResponse:
+    def __init__(self, inference: AsyncInferenceResource) -> None:
+        self._inference = inference
+
+        self.get_capacity_by_region = async_to_streamed_response_wrapper(
+            inference.get_capacity_by_region,
+        )
+
+    @cached_property
+    def flavors(self) -> AsyncFlavorsResourceWithStreamingResponse:
+        return AsyncFlavorsResourceWithStreamingResponse(self._inference.flavors)
+
+    @cached_property
+    def models(self) -> AsyncModelsResourceWithStreamingResponse:
+        return AsyncModelsResourceWithStreamingResponse(self._inference.models)
+
+    @cached_property
+    def deployments(self) -> AsyncDeploymentsResourceWithStreamingResponse:
+        return AsyncDeploymentsResourceWithStreamingResponse(self._inference.deployments)
+
+    @cached_property
+    def registry_credentials(self) -> AsyncRegistryCredentialsResourceWithStreamingResponse:
+        return AsyncRegistryCredentialsResourceWithStreamingResponse(self._inference.registry_credentials)
+
+    @cached_property
+    def secrets(self) -> AsyncSecretsResourceWithStreamingResponse:
+        return AsyncSecretsResourceWithStreamingResponse(self._inference.secrets)

gcore/resources/cloud/inference/models.py

@@ -0,0 +1,289 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+import httpx
+
+from ...._types import NOT_GIVEN, Body, Query, Headers, NotGiven
+from ...._utils import 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 SyncOffsetPage, AsyncOffsetPage
+from ...._base_client import AsyncPaginator, make_request_options
+from ....types.cloud.inference import MlcatalogOrderByChoices, model_list_params
+from ....types.cloud.inference.mlcatalog_model_card import MlcatalogModelCard
+from ....types.cloud.inference.mlcatalog_order_by_choices import MlcatalogOrderByChoices
+
+__all__ = ["ModelsResource", "AsyncModelsResource"]
+
+
+class ModelsResource(SyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> ModelsResourceWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/G-Core/gcore-python#accessing-raw-response-data-eg-headers
+        """
+        return ModelsResourceWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> ModelsResourceWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/G-Core/gcore-python#with_streaming_response
+        """
+        return ModelsResourceWithStreamingResponse(self)
+
+    def list(
+        self,
+        *,
+        limit: int | NotGiven = NOT_GIVEN,
+        offset: int | NotGiven = NOT_GIVEN,
+        order_by: MlcatalogOrderByChoices | NotGiven = NOT_GIVEN,
+        # 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,
+    ) -> SyncOffsetPage[MlcatalogModelCard]:
+        """List models from catalog
+
+        Args:
+          limit: Optional.
+
+        Limit the number of returned items
+
+          offset: Optional. Offset value is used to exclude the first set of records from the
+              result
+
+          order_by: Order instances by transmitted fields and directions
+
+          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
+        """
+        return self._get_api_list(
+            "/cloud/v3/inference/models",
+            page=SyncOffsetPage[MlcatalogModelCard],
+            options=make_request_options(
+                extra_headers=extra_headers,
+                extra_query=extra_query,
+                extra_body=extra_body,
+                timeout=timeout,
+                query=maybe_transform(
+                    {
+                        "limit": limit,
+                        "offset": offset,
+                        "order_by": order_by,
+                    },
+                    model_list_params.ModelListParams,
+                ),
+            ),
+            model=MlcatalogModelCard,
+        )
+
+    def get(
+        self,
+        model_id: 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,
+    ) -> MlcatalogModelCard:
+        """
+        Get model from catalog
+
+        Args:
+          model_id: Model ID
+
+          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 not model_id:
+            raise ValueError(f"Expected a non-empty value for `model_id` but received {model_id!r}")
+        return self._get(
+            f"/cloud/v3/inference/models/{model_id}",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=MlcatalogModelCard,
+        )
+
+
+class AsyncModelsResource(AsyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> AsyncModelsResourceWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/G-Core/gcore-python#accessing-raw-response-data-eg-headers
+        """
+        return AsyncModelsResourceWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AsyncModelsResourceWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/G-Core/gcore-python#with_streaming_response
+        """
+        return AsyncModelsResourceWithStreamingResponse(self)
+
+    def list(
+        self,
+        *,
+        limit: int | NotGiven = NOT_GIVEN,
+        offset: int | NotGiven = NOT_GIVEN,
+        order_by: MlcatalogOrderByChoices | NotGiven = NOT_GIVEN,
+        # 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[MlcatalogModelCard, AsyncOffsetPage[MlcatalogModelCard]]:
+        """List models from catalog
+
+        Args:
+          limit: Optional.
+
+        Limit the number of returned items
+
+          offset: Optional. Offset value is used to exclude the first set of records from the
+              result
+
+          order_by: Order instances by transmitted fields and directions
+
+          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
+        """
+        return self._get_api_list(
+            "/cloud/v3/inference/models",
+            page=AsyncOffsetPage[MlcatalogModelCard],
+            options=make_request_options(
+                extra_headers=extra_headers,
+                extra_query=extra_query,
+                extra_body=extra_body,
+                timeout=timeout,
+                query=maybe_transform(
+                    {
+                        "limit": limit,
+                        "offset": offset,
+                        "order_by": order_by,
+                    },
+                    model_list_params.ModelListParams,
+                ),
+            ),
+            model=MlcatalogModelCard,
+        )
+
+    async def get(
+        self,
+        model_id: 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,
+    ) -> MlcatalogModelCard:
+        """
+        Get model from catalog
+
+        Args:
+          model_id: Model ID
+
+          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 not model_id:
+            raise ValueError(f"Expected a non-empty value for `model_id` but received {model_id!r}")
+        return await self._get(
+            f"/cloud/v3/inference/models/{model_id}",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=MlcatalogModelCard,
+        )
+
+
+class ModelsResourceWithRawResponse:
+    def __init__(self, models: ModelsResource) -> None:
+        self._models = models
+
+        self.list = to_raw_response_wrapper(
+            models.list,
+        )
+        self.get = to_raw_response_wrapper(
+            models.get,
+        )
+
+
+class AsyncModelsResourceWithRawResponse:
+    def __init__(self, models: AsyncModelsResource) -> None:
+        self._models = models
+
+        self.list = async_to_raw_response_wrapper(
+            models.list,
+        )
+        self.get = async_to_raw_response_wrapper(
+            models.get,
+        )
+
+
+class ModelsResourceWithStreamingResponse:
+    def __init__(self, models: ModelsResource) -> None:
+        self._models = models
+
+        self.list = to_streamed_response_wrapper(
+            models.list,
+        )
+        self.get = to_streamed_response_wrapper(
+            models.get,
+        )
+
+
+class AsyncModelsResourceWithStreamingResponse:
+    def __init__(self, models: AsyncModelsResource) -> None:
+        self._models = models
+
+        self.list = async_to_streamed_response_wrapper(
+            models.list,
+        )
+        self.get = async_to_streamed_response_wrapper(
+            models.get,
+        )