vellum-ai 0.14.41__py3-none-any.whl → 1.11.2__py3-none-any.whl

vellum/client/resources/deployments/client.py

@@ -1,28 +1,21 @@
 # This file was auto-generated by Fern from our API Definition.
 
 import typing
-from ...core.client_wrapper import SyncClientWrapper
-from .types.deployments_list_request_status import DeploymentsListRequestStatus
+
+from ...core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
 from ...core.request_options import RequestOptions
-from ...types.paginated_slim_deployment_read_list import PaginatedSlimDeploymentReadList
-from ...core.pydantic_utilities import parse_obj_as
-from json.decoder import JSONDecodeError
-from ...core.api_error import ApiError
-from ...types.deployment_read import DeploymentRead
-from ...core.jsonable_encoder import jsonable_encoder
+from ...types.compile_prompt_deployment_expand_meta_request import CompilePromptDeploymentExpandMetaRequest
 from ...types.deployment_history_item import DeploymentHistoryItem
-from .types.list_deployment_release_tags_request_source import ListDeploymentReleaseTagsRequestSource
-from ...types.paginated_deployment_release_tag_read_list import PaginatedDeploymentReleaseTagReadList
+from ...types.deployment_provider_payload_response import DeploymentProviderPayloadResponse
+from ...types.deployment_read import DeploymentRead
 from ...types.deployment_release_tag_read import DeploymentReleaseTagRead
+from ...types.paginated_deployment_release_tag_read_list import PaginatedDeploymentReleaseTagReadList
+from ...types.paginated_slim_deployment_read_list import PaginatedSlimDeploymentReadList
 from ...types.prompt_deployment_input_request import PromptDeploymentInputRequest
-from ...types.compile_prompt_deployment_expand_meta_request import CompilePromptDeploymentExpandMetaRequest
-from ...types.deployment_provider_payload_response import DeploymentProviderPayloadResponse
-from ...core.serialization import convert_and_respect_annotation_metadata
-from ...errors.bad_request_error import BadRequestError
-from ...errors.forbidden_error import ForbiddenError
-from ...errors.not_found_error import NotFoundError
-from ...errors.internal_server_error import InternalServerError
-from ...core.client_wrapper import AsyncClientWrapper
+from ...types.prompt_deployment_release import PromptDeploymentRelease
+from .raw_client import AsyncRawDeploymentsClient, RawDeploymentsClient
+from .types.deployments_list_request_status import DeploymentsListRequestStatus
+from .types.list_deployment_release_tags_request_source import ListDeploymentReleaseTagsRequestSource
 
 # this is used as the default value for optional parameters
 OMIT = typing.cast(typing.Any, ...)
@@ -30,7 +23,22 @@ OMIT = typing.cast(typing.Any, ...)
 
 class DeploymentsClient:
     def __init__(self, *, client_wrapper: SyncClientWrapper):
-        self._client_wrapper = client_wrapper
+        self._raw_client = RawDeploymentsClient(client_wrapper=client_wrapper)
+
+    @property
+    def _client_wrapper(self) -> SyncClientWrapper:
+        return self._raw_client._client_wrapper
+
+    @property
+    def with_raw_response(self) -> RawDeploymentsClient:
+        """
+        Retrieves a raw implementation of this client that returns raw responses.
+
+        Returns
+        -------
+        RawDeploymentsClient
+        """
+        return self._raw_client
 
     def list(
         self,
@@ -71,35 +79,15 @@ class DeploymentsClient:
         from vellum import Vellum
 
         client = Vellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
         client.deployments.list()
         """
-        _response = self._client_wrapper.httpx_client.request(
-            "v1/deployments",
-            base_url=self._client_wrapper.get_environment().default,
-            method="GET",
-            params={
-                "limit": limit,
-                "offset": offset,
-                "ordering": ordering,
-                "status": status,
-            },
-            request_options=request_options,
+        _response = self._raw_client.list(
+            limit=limit, offset=offset, ordering=ordering, status=status, request_options=request_options
         )
-        try:
-            if 200 <= _response.status_code < 300:
-                return typing.cast(
-                    PaginatedSlimDeploymentReadList,
-                    parse_obj_as(
-                        type_=PaginatedSlimDeploymentReadList,  # type: ignore
-                        object_=_response.json(),
-                    ),
-                )
-            _response_json = _response.json()
-        except JSONDecodeError:
-            raise ApiError(status_code=_response.status_code, body=_response.text)
-        raise ApiError(status_code=_response.status_code, body=_response_json)
+        return _response.data
 
     def retrieve(self, id: str, *, request_options: typing.Optional[RequestOptions] = None) -> DeploymentRead:
         """
@@ -108,7 +96,7 @@ class DeploymentsClient:
         Parameters
         ----------
         id : str
-            Either the Deployment's ID or its unique name
+            Either the Prompt Deployment's ID or its unique name
 
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
@@ -123,37 +111,22 @@ class DeploymentsClient:
         from vellum import Vellum
 
         client = Vellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
         client.deployments.retrieve(
             id="id",
         )
         """
-        _response = self._client_wrapper.httpx_client.request(
-            f"v1/deployments/{jsonable_encoder(id)}",
-            base_url=self._client_wrapper.get_environment().default,
-            method="GET",
-            request_options=request_options,
-        )
-        try:
-            if 200 <= _response.status_code < 300:
-                return typing.cast(
-                    DeploymentRead,
-                    parse_obj_as(
-                        type_=DeploymentRead,  # type: ignore
-                        object_=_response.json(),
-                    ),
-                )
-            _response_json = _response.json()
-        except JSONDecodeError:
-            raise ApiError(status_code=_response.status_code, body=_response.text)
-        raise ApiError(status_code=_response.status_code, body=_response_json)
+        _response = self._raw_client.retrieve(id, request_options=request_options)
+        return _response.data
 
     def deployment_history_item_retrieve(
         self, history_id_or_release_tag: str, id: str, *, request_options: typing.Optional[RequestOptions] = None
     ) -> DeploymentHistoryItem:
         """
-        Retrieve a specific Deployment History Item by either its UUID or the name of a Release Tag that points to it.
+        DEPRECATED: This endpoint is deprecated and will be removed in a future release. Please use the
+        `retrieve_prompt_deployment_release` xendpoint instead.
 
         Parameters
         ----------
@@ -161,7 +134,7 @@ class DeploymentsClient:
             Either the UUID of Deployment History Item you'd like to retrieve, or the name of a Release Tag that's pointing to the Deployment History Item you'd like to retrieve.
 
         id : str
-            A UUID string identifying this deployment.
+            Either the Prompt Deployment's ID or its unique name
 
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
@@ -176,6 +149,7 @@ class DeploymentsClient:
         from vellum import Vellum
 
         client = Vellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
         client.deployments.deployment_history_item_retrieve(
@@ -183,25 +157,10 @@ class DeploymentsClient:
             id="id",
         )
         """
-        _response = self._client_wrapper.httpx_client.request(
-            f"v1/deployments/{jsonable_encoder(id)}/history/{jsonable_encoder(history_id_or_release_tag)}",
-            base_url=self._client_wrapper.get_environment().default,
-            method="GET",
-            request_options=request_options,
+        _response = self._raw_client.deployment_history_item_retrieve(
+            history_id_or_release_tag, id, request_options=request_options
         )
-        try:
-            if 200 <= _response.status_code < 300:
-                return typing.cast(
-                    DeploymentHistoryItem,
-                    parse_obj_as(
-                        type_=DeploymentHistoryItem,  # type: ignore
-                        object_=_response.json(),
-                    ),
-                )
-            _response_json = _response.json()
-        except JSONDecodeError:
-            raise ApiError(status_code=_response.status_code, body=_response.text)
-        raise ApiError(status_code=_response.status_code, body=_response_json)
+        return _response.data
 
     def list_deployment_release_tags(
         self,
@@ -245,37 +204,17 @@ class DeploymentsClient:
         from vellum import Vellum
 
         client = Vellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
         client.deployments.list_deployment_release_tags(
             id="id",
         )
         """
-        _response = self._client_wrapper.httpx_client.request(
-            f"v1/deployments/{jsonable_encoder(id)}/release-tags",
-            base_url=self._client_wrapper.get_environment().default,
-            method="GET",
-            params={
-                "limit": limit,
-                "offset": offset,
-                "ordering": ordering,
-                "source": source,
-            },
-            request_options=request_options,
+        _response = self._raw_client.list_deployment_release_tags(
+            id, limit=limit, offset=offset, ordering=ordering, source=source, request_options=request_options
         )
-        try:
-            if 200 <= _response.status_code < 300:
-                return typing.cast(
-                    PaginatedDeploymentReleaseTagReadList,
-                    parse_obj_as(
-                        type_=PaginatedDeploymentReleaseTagReadList,  # type: ignore
-                        object_=_response.json(),
-                    ),
-                )
-            _response_json = _response.json()
-        except JSONDecodeError:
-            raise ApiError(status_code=_response.status_code, body=_response.text)
-        raise ApiError(status_code=_response.status_code, body=_response_json)
+        return _response.data
 
     def retrieve_deployment_release_tag(
         self, id: str, name: str, *, request_options: typing.Optional[RequestOptions] = None
@@ -286,7 +225,7 @@ class DeploymentsClient:
         Parameters
         ----------
         id : str
-            A UUID string identifying this deployment.
+            Either the Prompt Deployment's ID or its unique name
 
         name : str
             The name of the Release Tag associated with this Deployment that you'd like to retrieve.
@@ -304,6 +243,7 @@ class DeploymentsClient:
         from vellum import Vellum
 
         client = Vellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
         client.deployments.retrieve_deployment_release_tag(
@@ -311,25 +251,8 @@ class DeploymentsClient:
             name="name",
         )
         """
-        _response = self._client_wrapper.httpx_client.request(
-            f"v1/deployments/{jsonable_encoder(id)}/release-tags/{jsonable_encoder(name)}",
-            base_url=self._client_wrapper.get_environment().default,
-            method="GET",
-            request_options=request_options,
-        )
-        try:
-            if 200 <= _response.status_code < 300:
-                return typing.cast(
-                    DeploymentReleaseTagRead,
-                    parse_obj_as(
-                        type_=DeploymentReleaseTagRead,  # type: ignore
-                        object_=_response.json(),
-                    ),
-                )
-            _response_json = _response.json()
-        except JSONDecodeError:
-            raise ApiError(status_code=_response.status_code, body=_response.text)
-        raise ApiError(status_code=_response.status_code, body=_response_json)
+        _response = self._raw_client.retrieve_deployment_release_tag(id, name, request_options=request_options)
+        return _response.data
 
     def update_deployment_release_tag(
         self,
@@ -345,7 +268,7 @@ class DeploymentsClient:
         Parameters
         ----------
         id : str
-            A UUID string identifying this deployment.
+            Either the Prompt Deployment's ID or its unique name
 
         name : str
             The name of the Release Tag associated with this Deployment that you'd like to update.
@@ -366,6 +289,7 @@ class DeploymentsClient:
         from vellum import Vellum
 
         client = Vellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
         client.deployments.update_deployment_release_tag(
@@ -373,29 +297,50 @@ class DeploymentsClient:
             name="name",
         )
         """
-        _response = self._client_wrapper.httpx_client.request(
-            f"v1/deployments/{jsonable_encoder(id)}/release-tags/{jsonable_encoder(name)}",
-            base_url=self._client_wrapper.get_environment().default,
-            method="PATCH",
-            json={
-                "history_item_id": history_item_id,
-            },
-            request_options=request_options,
-            omit=OMIT,
+        _response = self._raw_client.update_deployment_release_tag(
+            id, name, history_item_id=history_item_id, request_options=request_options
         )
-        try:
-            if 200 <= _response.status_code < 300:
-                return typing.cast(
-                    DeploymentReleaseTagRead,
-                    parse_obj_as(
-                        type_=DeploymentReleaseTagRead,  # type: ignore
-                        object_=_response.json(),
-                    ),
-                )
-            _response_json = _response.json()
-        except JSONDecodeError:
-            raise ApiError(status_code=_response.status_code, body=_response.text)
-        raise ApiError(status_code=_response.status_code, body=_response_json)
+        return _response.data
+
+    def retrieve_prompt_deployment_release(
+        self, id: str, release_id_or_release_tag: str, *, request_options: typing.Optional[RequestOptions] = None
+    ) -> PromptDeploymentRelease:
+        """
+        Retrieve a specific Prompt Deployment Release by either its UUID or the name of a Release Tag that points to it.
+
+        Parameters
+        ----------
+        id : str
+            Either the Prompt Deployment's ID or its unique name
+
+        release_id_or_release_tag : str
+            Either the UUID of Prompt Deployment Release you'd like to retrieve, or the name of a Release Tag that's pointing to the Prompt Deployment Release you'd like to retrieve.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        PromptDeploymentRelease
+
+
+        Examples
+        --------
+        from vellum import Vellum
+
+        client = Vellum(
+            api_version="YOUR_API_VERSION",
+            api_key="YOUR_API_KEY",
+        )
+        client.deployments.retrieve_prompt_deployment_release(
+            id="id",
+            release_id_or_release_tag="release_id_or_release_tag",
+        )
+        """
+        _response = self._raw_client.retrieve_prompt_deployment_release(
+            id, release_id_or_release_tag, request_options=request_options
+        )
+        return _response.data
 
     def retrieve_provider_payload(
         self,
@@ -448,93 +393,47 @@ class DeploymentsClient:
         from vellum import StringInputRequest, Vellum
 
         client = Vellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
         client.deployments.retrieve_provider_payload(
             inputs=[
                 StringInputRequest(
-                    name="name",
+                    name="x",
+                    value="value",
+                ),
+                StringInputRequest(
+                    name="x",
                     value="value",
-                )
+                ),
             ],
         )
         """
-        _response = self._client_wrapper.httpx_client.request(
-            "v1/deployments/provider-payload",
-            base_url=self._client_wrapper.get_environment().default,
-            method="POST",
-            json={
-                "deployment_id": deployment_id,
-                "deployment_name": deployment_name,
-                "inputs": convert_and_respect_annotation_metadata(
-                    object_=inputs, annotation=typing.Sequence[PromptDeploymentInputRequest], direction="write"
-                ),
-                "release_tag": release_tag,
-                "expand_meta": convert_and_respect_annotation_metadata(
-                    object_=expand_meta, annotation=CompilePromptDeploymentExpandMetaRequest, direction="write"
-                ),
-            },
+        _response = self._raw_client.retrieve_provider_payload(
+            inputs=inputs,
+            deployment_id=deployment_id,
+            deployment_name=deployment_name,
+            release_tag=release_tag,
+            expand_meta=expand_meta,
             request_options=request_options,
-            omit=OMIT,
         )
-        try:
-            if 200 <= _response.status_code < 300:
-                return typing.cast(
-                    DeploymentProviderPayloadResponse,
-                    parse_obj_as(
-                        type_=DeploymentProviderPayloadResponse,  # type: ignore
-                        object_=_response.json(),
-                    ),
-                )
-            if _response.status_code == 400:
-                raise BadRequestError(
-                    typing.cast(
-                        typing.Optional[typing.Any],
-                        parse_obj_as(
-                            type_=typing.Optional[typing.Any],  # type: ignore
-                            object_=_response.json(),
-                        ),
-                    )
-                )
-            if _response.status_code == 403:
-                raise ForbiddenError(
-                    typing.cast(
-                        typing.Optional[typing.Any],
-                        parse_obj_as(
-                            type_=typing.Optional[typing.Any],  # type: ignore
-                            object_=_response.json(),
-                        ),
-                    )
-                )
-            if _response.status_code == 404:
-                raise NotFoundError(
-                    typing.cast(
-                        typing.Optional[typing.Any],
-                        parse_obj_as(
-                            type_=typing.Optional[typing.Any],  # type: ignore
-                            object_=_response.json(),
-                        ),
-                    )
-                )
-            if _response.status_code == 500:
-                raise InternalServerError(
-                    typing.cast(
-                        typing.Optional[typing.Any],
-                        parse_obj_as(
-                            type_=typing.Optional[typing.Any],  # type: ignore
-                            object_=_response.json(),
-                        ),
-                    )
-                )
-            _response_json = _response.json()
-        except JSONDecodeError:
-            raise ApiError(status_code=_response.status_code, body=_response.text)
-        raise ApiError(status_code=_response.status_code, body=_response_json)
+        return _response.data
 
 
 class AsyncDeploymentsClient:
     def __init__(self, *, client_wrapper: AsyncClientWrapper):
-        self._client_wrapper = client_wrapper
+        self._raw_client = AsyncRawDeploymentsClient(client_wrapper=client_wrapper)
+
+    @property
+    def with_raw_response(self) -> AsyncRawDeploymentsClient:
+        """
+        Retrieves a raw implementation of this client that returns raw responses.
+
+        Returns
+        -------
+        AsyncRawDeploymentsClient
+        """
+        return self._raw_client
 
     async def list(
         self,
@@ -577,6 +476,7 @@ class AsyncDeploymentsClient:
         from vellum import AsyncVellum
 
         client = AsyncVellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
 
@@ -587,31 +487,10 @@ class AsyncDeploymentsClient:
 
         asyncio.run(main())
         """
-        _response = await self._client_wrapper.httpx_client.request(
-            "v1/deployments",
-            base_url=self._client_wrapper.get_environment().default,
-            method="GET",
-            params={
-                "limit": limit,
-                "offset": offset,
-                "ordering": ordering,
-                "status": status,
-            },
-            request_options=request_options,
+        _response = await self._raw_client.list(
+            limit=limit, offset=offset, ordering=ordering, status=status, request_options=request_options
         )
-        try:
-            if 200 <= _response.status_code < 300:
-                return typing.cast(
-                    PaginatedSlimDeploymentReadList,
-                    parse_obj_as(
-                        type_=PaginatedSlimDeploymentReadList,  # type: ignore
-                        object_=_response.json(),
-                    ),
-                )
-            _response_json = _response.json()
-        except JSONDecodeError:
-            raise ApiError(status_code=_response.status_code, body=_response.text)
-        raise ApiError(status_code=_response.status_code, body=_response_json)
+        return _response.data
 
     async def retrieve(self, id: str, *, request_options: typing.Optional[RequestOptions] = None) -> DeploymentRead:
         """
@@ -620,7 +499,7 @@ class AsyncDeploymentsClient:
         Parameters
         ----------
         id : str
-            Either the Deployment's ID or its unique name
+            Either the Prompt Deployment's ID or its unique name
 
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
@@ -637,6 +516,7 @@ class AsyncDeploymentsClient:
         from vellum import AsyncVellum
 
         client = AsyncVellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
 
@@ -649,31 +529,15 @@ class AsyncDeploymentsClient:
 
         asyncio.run(main())
         """
-        _response = await self._client_wrapper.httpx_client.request(
-            f"v1/deployments/{jsonable_encoder(id)}",
-            base_url=self._client_wrapper.get_environment().default,
-            method="GET",
-            request_options=request_options,
-        )
-        try:
-            if 200 <= _response.status_code < 300:
-                return typing.cast(
-                    DeploymentRead,
-                    parse_obj_as(
-                        type_=DeploymentRead,  # type: ignore
-                        object_=_response.json(),
-                    ),
-                )
-            _response_json = _response.json()
-        except JSONDecodeError:
-            raise ApiError(status_code=_response.status_code, body=_response.text)
-        raise ApiError(status_code=_response.status_code, body=_response_json)
+        _response = await self._raw_client.retrieve(id, request_options=request_options)
+        return _response.data
 
     async def deployment_history_item_retrieve(
         self, history_id_or_release_tag: str, id: str, *, request_options: typing.Optional[RequestOptions] = None
     ) -> DeploymentHistoryItem:
         """
-        Retrieve a specific Deployment History Item by either its UUID or the name of a Release Tag that points to it.
+        DEPRECATED: This endpoint is deprecated and will be removed in a future release. Please use the
+        `retrieve_prompt_deployment_release` xendpoint instead.
 
         Parameters
         ----------
@@ -681,7 +545,7 @@ class AsyncDeploymentsClient:
             Either the UUID of Deployment History Item you'd like to retrieve, or the name of a Release Tag that's pointing to the Deployment History Item you'd like to retrieve.
 
         id : str
-            A UUID string identifying this deployment.
+            Either the Prompt Deployment's ID or its unique name
 
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
@@ -698,6 +562,7 @@ class AsyncDeploymentsClient:
         from vellum import AsyncVellum
 
         client = AsyncVellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
 
@@ -711,25 +576,10 @@ class AsyncDeploymentsClient:
 
         asyncio.run(main())
         """
-        _response = await self._client_wrapper.httpx_client.request(
-            f"v1/deployments/{jsonable_encoder(id)}/history/{jsonable_encoder(history_id_or_release_tag)}",
-            base_url=self._client_wrapper.get_environment().default,
-            method="GET",
-            request_options=request_options,
+        _response = await self._raw_client.deployment_history_item_retrieve(
+            history_id_or_release_tag, id, request_options=request_options
         )
-        try:
-            if 200 <= _response.status_code < 300:
-                return typing.cast(
-                    DeploymentHistoryItem,
-                    parse_obj_as(
-                        type_=DeploymentHistoryItem,  # type: ignore
-                        object_=_response.json(),
-                    ),
-                )
-            _response_json = _response.json()
-        except JSONDecodeError:
-            raise ApiError(status_code=_response.status_code, body=_response.text)
-        raise ApiError(status_code=_response.status_code, body=_response_json)
+        return _response.data
 
     async def list_deployment_release_tags(
         self,
@@ -775,6 +625,7 @@ class AsyncDeploymentsClient:
         from vellum import AsyncVellum
 
         client = AsyncVellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
 
@@ -787,31 +638,10 @@ class AsyncDeploymentsClient:
 
         asyncio.run(main())
         """
-        _response = await self._client_wrapper.httpx_client.request(
-            f"v1/deployments/{jsonable_encoder(id)}/release-tags",
-            base_url=self._client_wrapper.get_environment().default,
-            method="GET",
-            params={
-                "limit": limit,
-                "offset": offset,
-                "ordering": ordering,
-                "source": source,
-            },
-            request_options=request_options,
+        _response = await self._raw_client.list_deployment_release_tags(
+            id, limit=limit, offset=offset, ordering=ordering, source=source, request_options=request_options
         )
-        try:
-            if 200 <= _response.status_code < 300:
-                return typing.cast(
-                    PaginatedDeploymentReleaseTagReadList,
-                    parse_obj_as(
-                        type_=PaginatedDeploymentReleaseTagReadList,  # type: ignore
-                        object_=_response.json(),
-                    ),
-                )
-            _response_json = _response.json()
-        except JSONDecodeError:
-            raise ApiError(status_code=_response.status_code, body=_response.text)
-        raise ApiError(status_code=_response.status_code, body=_response_json)
+        return _response.data
 
     async def retrieve_deployment_release_tag(
         self, id: str, name: str, *, request_options: typing.Optional[RequestOptions] = None
@@ -822,7 +652,7 @@ class AsyncDeploymentsClient:
         Parameters
         ----------
         id : str
-            A UUID string identifying this deployment.
+            Either the Prompt Deployment's ID or its unique name
 
         name : str
             The name of the Release Tag associated with this Deployment that you'd like to retrieve.
@@ -842,6 +672,7 @@ class AsyncDeploymentsClient:
         from vellum import AsyncVellum
 
         client = AsyncVellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
 
@@ -855,25 +686,8 @@ class AsyncDeploymentsClient:
 
         asyncio.run(main())
         """
-        _response = await self._client_wrapper.httpx_client.request(
-            f"v1/deployments/{jsonable_encoder(id)}/release-tags/{jsonable_encoder(name)}",
-            base_url=self._client_wrapper.get_environment().default,
-            method="GET",
-            request_options=request_options,
-        )
-        try:
-            if 200 <= _response.status_code < 300:
-                return typing.cast(
-                    DeploymentReleaseTagRead,
-                    parse_obj_as(
-                        type_=DeploymentReleaseTagRead,  # type: ignore
-                        object_=_response.json(),
-                    ),
-                )
-            _response_json = _response.json()
-        except JSONDecodeError:
-            raise ApiError(status_code=_response.status_code, body=_response.text)
-        raise ApiError(status_code=_response.status_code, body=_response_json)
+        _response = await self._raw_client.retrieve_deployment_release_tag(id, name, request_options=request_options)
+        return _response.data
 
     async def update_deployment_release_tag(
         self,
@@ -889,7 +703,7 @@ class AsyncDeploymentsClient:
         Parameters
         ----------
         id : str
-            A UUID string identifying this deployment.
+            Either the Prompt Deployment's ID or its unique name
 
         name : str
             The name of the Release Tag associated with this Deployment that you'd like to update.
@@ -912,6 +726,7 @@ class AsyncDeploymentsClient:
         from vellum import AsyncVellum
 
         client = AsyncVellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
 
@@ -925,29 +740,58 @@ class AsyncDeploymentsClient:
 
         asyncio.run(main())
         """
-        _response = await self._client_wrapper.httpx_client.request(
-            f"v1/deployments/{jsonable_encoder(id)}/release-tags/{jsonable_encoder(name)}",
-            base_url=self._client_wrapper.get_environment().default,
-            method="PATCH",
-            json={
-                "history_item_id": history_item_id,
-            },
-            request_options=request_options,
-            omit=OMIT,
+        _response = await self._raw_client.update_deployment_release_tag(
+            id, name, history_item_id=history_item_id, request_options=request_options
         )
-        try:
-            if 200 <= _response.status_code < 300:
-                return typing.cast(
-                    DeploymentReleaseTagRead,
-                    parse_obj_as(
-                        type_=DeploymentReleaseTagRead,  # type: ignore
-                        object_=_response.json(),
-                    ),
-                )
-            _response_json = _response.json()
-        except JSONDecodeError:
-            raise ApiError(status_code=_response.status_code, body=_response.text)
-        raise ApiError(status_code=_response.status_code, body=_response_json)
+        return _response.data
+
+    async def retrieve_prompt_deployment_release(
+        self, id: str, release_id_or_release_tag: str, *, request_options: typing.Optional[RequestOptions] = None
+    ) -> PromptDeploymentRelease:
+        """
+        Retrieve a specific Prompt Deployment Release by either its UUID or the name of a Release Tag that points to it.
+
+        Parameters
+        ----------
+        id : str
+            Either the Prompt Deployment's ID or its unique name
+
+        release_id_or_release_tag : str
+            Either the UUID of Prompt Deployment Release you'd like to retrieve, or the name of a Release Tag that's pointing to the Prompt Deployment Release you'd like to retrieve.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        PromptDeploymentRelease
+
+
+        Examples
+        --------
+        import asyncio
+
+        from vellum import AsyncVellum
+
+        client = AsyncVellum(
+            api_version="YOUR_API_VERSION",
+            api_key="YOUR_API_KEY",
+        )
+
+
+        async def main() -> None:
+            await client.deployments.retrieve_prompt_deployment_release(
+                id="id",
+                release_id_or_release_tag="release_id_or_release_tag",
+            )
+
+
+        asyncio.run(main())
+        """
+        _response = await self._raw_client.retrieve_prompt_deployment_release(
+            id, release_id_or_release_tag, request_options=request_options
+        )
+        return _response.data
 
     async def retrieve_provider_payload(
         self,
@@ -1002,6 +846,7 @@ class AsyncDeploymentsClient:
         from vellum import AsyncVellum, StringInputRequest
 
         client = AsyncVellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
 
@@ -1010,83 +855,25 @@ class AsyncDeploymentsClient:
             await client.deployments.retrieve_provider_payload(
                 inputs=[
                     StringInputRequest(
-                        name="name",
+                        name="x",
+                        value="value",
+                    ),
+                    StringInputRequest(
+                        name="x",
                         value="value",
-                    )
+                    ),
                 ],
             )
 
 
         asyncio.run(main())
         """
-        _response = await self._client_wrapper.httpx_client.request(
-            "v1/deployments/provider-payload",
-            base_url=self._client_wrapper.get_environment().default,
-            method="POST",
-            json={
-                "deployment_id": deployment_id,
-                "deployment_name": deployment_name,
-                "inputs": convert_and_respect_annotation_metadata(
-                    object_=inputs, annotation=typing.Sequence[PromptDeploymentInputRequest], direction="write"
-                ),
-                "release_tag": release_tag,
-                "expand_meta": convert_and_respect_annotation_metadata(
-                    object_=expand_meta, annotation=CompilePromptDeploymentExpandMetaRequest, direction="write"
-                ),
-            },
+        _response = await self._raw_client.retrieve_provider_payload(
+            inputs=inputs,
+            deployment_id=deployment_id,
+            deployment_name=deployment_name,
+            release_tag=release_tag,
+            expand_meta=expand_meta,
             request_options=request_options,
-            omit=OMIT,
         )
-        try:
-            if 200 <= _response.status_code < 300:
-                return typing.cast(
-                    DeploymentProviderPayloadResponse,
-                    parse_obj_as(
-                        type_=DeploymentProviderPayloadResponse,  # type: ignore
-                        object_=_response.json(),
-                    ),
-                )
-            if _response.status_code == 400:
-                raise BadRequestError(
-                    typing.cast(
-                        typing.Optional[typing.Any],
-                        parse_obj_as(
-                            type_=typing.Optional[typing.Any],  # type: ignore
-                            object_=_response.json(),
-                        ),
-                    )
-                )
-            if _response.status_code == 403:
-                raise ForbiddenError(
-                    typing.cast(
-                        typing.Optional[typing.Any],
-                        parse_obj_as(
-                            type_=typing.Optional[typing.Any],  # type: ignore
-                            object_=_response.json(),
-                        ),
-                    )
-                )
-            if _response.status_code == 404:
-                raise NotFoundError(
-                    typing.cast(
-                        typing.Optional[typing.Any],
-                        parse_obj_as(
-                            type_=typing.Optional[typing.Any],  # type: ignore
-                            object_=_response.json(),
-                        ),
-                    )
-                )
-            if _response.status_code == 500:
-                raise InternalServerError(
-                    typing.cast(
-                        typing.Optional[typing.Any],
-                        parse_obj_as(
-                            type_=typing.Optional[typing.Any],  # type: ignore
-                            object_=_response.json(),
-                        ),
-                    )
-                )
-            _response_json = _response.json()
-        except JSONDecodeError:
-            raise ApiError(status_code=_response.status_code, body=_response.text)
-        raise ApiError(status_code=_response.status_code, body=_response_json)
+        return _response.data