vellum-ai 0.14.63__py3-none-any.whl → 1.13.5__py3-none-any.whl

vellum/client/resources/workflow_deployments/client.py

@@ -1,22 +1,22 @@
 # This file was auto-generated by Fern from our API Definition.
 
 import typing
-from ...core.client_wrapper import SyncClientWrapper
-from .types.workflow_deployments_list_request_status import WorkflowDeploymentsListRequestStatus
+
+from ...core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
 from ...core.request_options import RequestOptions
 from ...types.paginated_slim_workflow_deployment_list import PaginatedSlimWorkflowDeploymentList
-from ...core.pydantic_utilities import parse_obj_as
-from json.decoder import JSONDecodeError
-from ...core.api_error import ApiError
-from ...types.workflow_deployment_read import WorkflowDeploymentRead
-from ...core.jsonable_encoder import jsonable_encoder
+from ...types.paginated_workflow_deployment_release_list import PaginatedWorkflowDeploymentReleaseList
+from ...types.paginated_workflow_release_tag_read_list import PaginatedWorkflowReleaseTagReadList
 from ...types.workflow_deployment_event_executions_response import WorkflowDeploymentEventExecutionsResponse
-from ...types.workflow_event_execution_read import WorkflowEventExecutionRead
 from ...types.workflow_deployment_history_item import WorkflowDeploymentHistoryItem
-from .types.list_workflow_release_tags_request_source import ListWorkflowReleaseTagsRequestSource
-from ...types.paginated_workflow_release_tag_read_list import PaginatedWorkflowReleaseTagReadList
+from ...types.workflow_deployment_read import WorkflowDeploymentRead
+from ...types.workflow_deployment_release import WorkflowDeploymentRelease
+from ...types.workflow_event import WorkflowEvent
+from ...types.workflow_event_execution_read import WorkflowEventExecutionRead
 from ...types.workflow_release_tag_read import WorkflowReleaseTagRead
-from ...core.client_wrapper import AsyncClientWrapper
+from .raw_client import AsyncRawWorkflowDeploymentsClient, RawWorkflowDeploymentsClient
+from .types.list_workflow_release_tags_request_source import ListWorkflowReleaseTagsRequestSource
+from .types.workflow_deployments_list_request_status import WorkflowDeploymentsListRequestStatus
 
 # this is used as the default value for optional parameters
 OMIT = typing.cast(typing.Any, ...)
@@ -24,7 +24,22 @@ OMIT = typing.cast(typing.Any, ...)
 
 class WorkflowDeploymentsClient:
     def __init__(self, *, client_wrapper: SyncClientWrapper):
-        self._client_wrapper = client_wrapper
+        self._raw_client = RawWorkflowDeploymentsClient(client_wrapper=client_wrapper)
+
+    @property
+    def _client_wrapper(self) -> SyncClientWrapper:
+        return self._raw_client._client_wrapper
+
+    @property
+    def with_raw_response(self) -> RawWorkflowDeploymentsClient:
+        """
+        Retrieves a raw implementation of this client that returns raw responses.
+
+        Returns
+        -------
+        RawWorkflowDeploymentsClient
+        """
+        return self._raw_client
 
     def list(
         self,
@@ -65,35 +80,15 @@ class WorkflowDeploymentsClient:
         from vellum import Vellum
 
         client = Vellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
         client.workflow_deployments.list()
         """
-        _response = self._client_wrapper.httpx_client.request(
-            "v1/workflow-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(
-                    PaginatedSlimWorkflowDeploymentList,
-                    parse_obj_as(
-                        type_=PaginatedSlimWorkflowDeploymentList,  # 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) -> WorkflowDeploymentRead:
         """
@@ -117,31 +112,88 @@ class WorkflowDeploymentsClient:
         from vellum import Vellum
 
         client = Vellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
         client.workflow_deployments.retrieve(
             id="id",
         )
         """
-        _response = self._client_wrapper.httpx_client.request(
-            f"v1/workflow-deployments/{jsonable_encoder(id)}",
-            base_url=self._client_wrapper.get_environment().default,
-            method="GET",
-            request_options=request_options,
+        _response = self._raw_client.retrieve(id, request_options=request_options)
+        return _response.data
+
+    def execute_stream(
+        self,
+        id: str,
+        *,
+        inputs: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
+        trigger: typing.Optional[str] = OMIT,
+        release_tag: typing.Optional[str] = OMIT,
+        external_id: typing.Optional[str] = OMIT,
+        metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
+        previous_execution_id: typing.Optional[str] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> typing.Iterator[WorkflowEvent]:
+        """
+        Executes a deployed Workflow and streams back its results.
+
+        Parameters
+        ----------
+        id : str
+            Either the Workflow Deployment's ID or its unique name
+
+        inputs : typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]]
+            A mapping from input name to value.
+
+        trigger : typing.Optional[str]
+            The name or ID of a workflow trigger to use for this execution. If not specified, then a default manual trigger will be chosen.
+
+        release_tag : typing.Optional[str]
+            Optionally specify a release tag if you want to pin to a specific release of the Workflow Deployment
+
+        external_id : typing.Optional[str]
+            Optionally include a unique identifier for tracking purposes. Must be unique within a given Workspace.
+
+        metadata : typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]]
+            Arbitrary JSON metadata associated with this request. Can be used to capture additional monitoring data such as user id, session id, etc. for future analysis.
+
+        previous_execution_id : typing.Optional[str]
+            The ID of a previous workflow execution to reference for context.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Yields
+        ------
+        typing.Iterator[WorkflowEvent]
+
+
+        Examples
+        --------
+        from vellum import Vellum
+
+        client = Vellum(
+            api_version="YOUR_API_VERSION",
+            api_key="YOUR_API_KEY",
+        )
+        response = client.workflow_deployments.execute_stream(
+            id="my-workflow",
+            inputs={"question": "What is the capital of France?"},
         )
-        try:
-            if 200 <= _response.status_code < 300:
-                return typing.cast(
-                    WorkflowDeploymentRead,
-                    parse_obj_as(
-                        type_=WorkflowDeploymentRead,  # 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)
+        for chunk in response:
+            yield chunk
+        """
+        with self._raw_client.execute_stream(
+            id,
+            inputs=inputs,
+            trigger=trigger,
+            release_tag=release_tag,
+            external_id=external_id,
+            metadata=metadata,
+            previous_execution_id=previous_execution_id,
+            request_options=request_options,
+        ) as r:
+            yield from r.data
 
     def list_workflow_deployment_event_executions(
         self,
@@ -150,6 +202,7 @@ class WorkflowDeploymentsClient:
         filters: typing.Optional[str] = None,
         limit: typing.Optional[int] = None,
         offset: typing.Optional[int] = None,
+        ordering: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> WorkflowDeploymentEventExecutionsResponse:
         """
@@ -165,6 +218,8 @@ class WorkflowDeploymentsClient:
         offset : typing.Optional[int]
             The initial index from which to return the executions.
 
+        ordering : typing.Optional[str]
+
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
@@ -178,36 +233,17 @@ class WorkflowDeploymentsClient:
         from vellum import Vellum
 
         client = Vellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
         client.workflow_deployments.list_workflow_deployment_event_executions(
             id="id",
         )
         """
-        _response = self._client_wrapper.httpx_client.request(
-            f"v1/workflow-deployments/{jsonable_encoder(id)}/execution-events",
-            base_url=self._client_wrapper.get_environment().default,
-            method="GET",
-            params={
-                "filters": filters,
-                "limit": limit,
-                "offset": offset,
-            },
-            request_options=request_options,
+        _response = self._raw_client.list_workflow_deployment_event_executions(
+            id, filters=filters, limit=limit, offset=offset, ordering=ordering, request_options=request_options
         )
-        try:
-            if 200 <= _response.status_code < 300:
-                return typing.cast(
-                    WorkflowDeploymentEventExecutionsResponse,
-                    parse_obj_as(
-                        type_=WorkflowDeploymentEventExecutionsResponse,  # 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 workflow_deployment_event_execution(
         self, execution_id: str, id: str, *, request_options: typing.Optional[RequestOptions] = None
@@ -232,6 +268,7 @@ class WorkflowDeploymentsClient:
         from vellum import Vellum
 
         client = Vellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
         client.workflow_deployments.workflow_deployment_event_execution(
@@ -239,25 +276,10 @@ class WorkflowDeploymentsClient:
             id="id",
         )
         """
-        _response = self._client_wrapper.httpx_client.request(
-            f"v1/workflow-deployments/{jsonable_encoder(id)}/execution-events/{jsonable_encoder(execution_id)}",
-            base_url=self._client_wrapper.get_environment().default,
-            method="GET",
-            request_options=request_options,
+        _response = self._raw_client.workflow_deployment_event_execution(
+            execution_id, id, request_options=request_options
         )
-        try:
-            if 200 <= _response.status_code < 300:
-                return typing.cast(
-                    WorkflowEventExecutionRead,
-                    parse_obj_as(
-                        type_=WorkflowEventExecutionRead,  # 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 workflow_deployment_history_item_retrieve(
         self, history_id_or_release_tag: str, id: str, *, request_options: typing.Optional[RequestOptions] = None
@@ -287,6 +309,7 @@ class WorkflowDeploymentsClient:
         from vellum import Vellum
 
         client = Vellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
         client.workflow_deployments.workflow_deployment_history_item_retrieve(
@@ -294,25 +317,10 @@ class WorkflowDeploymentsClient:
             id="id",
         )
         """
-        _response = self._client_wrapper.httpx_client.request(
-            f"v1/workflow-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.workflow_deployment_history_item_retrieve(
+            history_id_or_release_tag, id, request_options=request_options
         )
-        try:
-            if 200 <= _response.status_code < 300:
-                return typing.cast(
-                    WorkflowDeploymentHistoryItem,
-                    parse_obj_as(
-                        type_=WorkflowDeploymentHistoryItem,  # 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_workflow_release_tags(
         self,
@@ -356,37 +364,17 @@ class WorkflowDeploymentsClient:
         from vellum import Vellum
 
         client = Vellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
         client.workflow_deployments.list_workflow_release_tags(
             id="id",
         )
         """
-        _response = self._client_wrapper.httpx_client.request(
-            f"v1/workflow-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_workflow_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(
-                    PaginatedWorkflowReleaseTagReadList,
-                    parse_obj_as(
-                        type_=PaginatedWorkflowReleaseTagReadList,  # 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_workflow_release_tag(
         self, id: str, name: str, *, request_options: typing.Optional[RequestOptions] = None
@@ -415,6 +403,7 @@ class WorkflowDeploymentsClient:
         from vellum import Vellum
 
         client = Vellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
         client.workflow_deployments.retrieve_workflow_release_tag(
@@ -422,25 +411,8 @@ class WorkflowDeploymentsClient:
             name="name",
         )
         """
-        _response = self._client_wrapper.httpx_client.request(
-            f"v1/workflow-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(
-                    WorkflowReleaseTagRead,
-                    parse_obj_as(
-                        type_=WorkflowReleaseTagRead,  # 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_workflow_release_tag(id, name, request_options=request_options)
+        return _response.data
 
     def update_workflow_release_tag(
         self,
@@ -477,6 +449,7 @@ class WorkflowDeploymentsClient:
         from vellum import Vellum
 
         client = Vellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
         client.workflow_deployments.update_workflow_release_tag(
@@ -484,37 +457,117 @@ class WorkflowDeploymentsClient:
             name="name",
         )
         """
-        _response = self._client_wrapper.httpx_client.request(
-            f"v1/workflow-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,
-            },
-            headers={
-                "content-type": "application/json",
-            },
-            request_options=request_options,
-            omit=OMIT,
+        _response = self._raw_client.update_workflow_release_tag(
+            id, name, history_item_id=history_item_id, request_options=request_options
         )
-        try:
-            if 200 <= _response.status_code < 300:
-                return typing.cast(
-                    WorkflowReleaseTagRead,
-                    parse_obj_as(
-                        type_=WorkflowReleaseTagRead,  # 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_workflow_deployment_releases(
+        self,
+        id: str,
+        *,
+        limit: typing.Optional[int] = None,
+        offset: typing.Optional[int] = None,
+        ordering: typing.Optional[str] = None,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> PaginatedWorkflowDeploymentReleaseList:
+        """
+        List the Releases of the specified Workflow Deployment for the current Environment.
+
+        Parameters
+        ----------
+        id : str
+            Either the Workflow Deployment's ID or its unique name
+
+        limit : typing.Optional[int]
+            Number of results to return per page.
+
+        offset : typing.Optional[int]
+            The initial index from which to return the results.
+
+        ordering : typing.Optional[str]
+            Which field to use when ordering the results.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        PaginatedWorkflowDeploymentReleaseList
+
+
+        Examples
+        --------
+        from vellum import Vellum
+
+        client = Vellum(
+            api_version="YOUR_API_VERSION",
+            api_key="YOUR_API_KEY",
+        )
+        client.workflow_deployments.list_workflow_deployment_releases(
+            id="id",
+        )
+        """
+        _response = self._raw_client.list_workflow_deployment_releases(
+            id, limit=limit, offset=offset, ordering=ordering, request_options=request_options
+        )
+        return _response.data
+
+    def retrieve_workflow_deployment_release(
+        self, id: str, release_id_or_release_tag: str, *, request_options: typing.Optional[RequestOptions] = None
+    ) -> WorkflowDeploymentRelease:
+        """
+        Retrieve a specific Workflow Deployment Release by either its UUID or the name of a Release Tag that points to it.
+
+        Parameters
+        ----------
+        id : str
+            Either the Workflow Deployment's ID or its unique name
+
+        release_id_or_release_tag : str
+            Either the UUID of Workflow Deployment Release you'd like to retrieve, or the name of a Release Tag that's pointing to the Workflow Deployment Release you'd like to retrieve.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        WorkflowDeploymentRelease
+
+
+        Examples
+        --------
+        from vellum import Vellum
+
+        client = Vellum(
+            api_version="YOUR_API_VERSION",
+            api_key="YOUR_API_KEY",
+        )
+        client.workflow_deployments.retrieve_workflow_deployment_release(
+            id="id",
+            release_id_or_release_tag="release_id_or_release_tag",
+        )
+        """
+        _response = self._raw_client.retrieve_workflow_deployment_release(
+            id, release_id_or_release_tag, request_options=request_options
+        )
+        return _response.data
 
 
 class AsyncWorkflowDeploymentsClient:
     def __init__(self, *, client_wrapper: AsyncClientWrapper):
-        self._client_wrapper = client_wrapper
+        self._raw_client = AsyncRawWorkflowDeploymentsClient(client_wrapper=client_wrapper)
+
+    @property
+    def with_raw_response(self) -> AsyncRawWorkflowDeploymentsClient:
+        """
+        Retrieves a raw implementation of this client that returns raw responses.
+
+        Returns
+        -------
+        AsyncRawWorkflowDeploymentsClient
+        """
+        return self._raw_client
 
     async def list(
         self,
@@ -557,6 +610,7 @@ class AsyncWorkflowDeploymentsClient:
         from vellum import AsyncVellum
 
         client = AsyncVellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
 
@@ -567,31 +621,10 @@ class AsyncWorkflowDeploymentsClient:
 
         asyncio.run(main())
         """
-        _response = await self._client_wrapper.httpx_client.request(
-            "v1/workflow-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(
-                    PaginatedSlimWorkflowDeploymentList,
-                    parse_obj_as(
-                        type_=PaginatedSlimWorkflowDeploymentList,  # 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
@@ -619,6 +652,7 @@ class AsyncWorkflowDeploymentsClient:
         from vellum import AsyncVellum
 
         client = AsyncVellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
 
@@ -631,25 +665,90 @@ class AsyncWorkflowDeploymentsClient:
 
         asyncio.run(main())
         """
-        _response = await self._client_wrapper.httpx_client.request(
-            f"v1/workflow-deployments/{jsonable_encoder(id)}",
-            base_url=self._client_wrapper.get_environment().default,
-            method="GET",
-            request_options=request_options,
+        _response = await self._raw_client.retrieve(id, request_options=request_options)
+        return _response.data
+
+    async def execute_stream(
+        self,
+        id: str,
+        *,
+        inputs: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
+        trigger: typing.Optional[str] = OMIT,
+        release_tag: typing.Optional[str] = OMIT,
+        external_id: typing.Optional[str] = OMIT,
+        metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
+        previous_execution_id: typing.Optional[str] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> typing.AsyncIterator[WorkflowEvent]:
+        """
+        Executes a deployed Workflow and streams back its results.
+
+        Parameters
+        ----------
+        id : str
+            Either the Workflow Deployment's ID or its unique name
+
+        inputs : typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]]
+            A mapping from input name to value.
+
+        trigger : typing.Optional[str]
+            The name or ID of a workflow trigger to use for this execution. If not specified, then a default manual trigger will be chosen.
+
+        release_tag : typing.Optional[str]
+            Optionally specify a release tag if you want to pin to a specific release of the Workflow Deployment
+
+        external_id : typing.Optional[str]
+            Optionally include a unique identifier for tracking purposes. Must be unique within a given Workspace.
+
+        metadata : typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]]
+            Arbitrary JSON metadata associated with this request. Can be used to capture additional monitoring data such as user id, session id, etc. for future analysis.
+
+        previous_execution_id : typing.Optional[str]
+            The ID of a previous workflow execution to reference for context.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Yields
+        ------
+        typing.AsyncIterator[WorkflowEvent]
+
+
+        Examples
+        --------
+        import asyncio
+
+        from vellum import AsyncVellum
+
+        client = AsyncVellum(
+            api_version="YOUR_API_VERSION",
+            api_key="YOUR_API_KEY",
         )
-        try:
-            if 200 <= _response.status_code < 300:
-                return typing.cast(
-                    WorkflowDeploymentRead,
-                    parse_obj_as(
-                        type_=WorkflowDeploymentRead,  # 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)
+
+
+        async def main() -> None:
+            response = await client.workflow_deployments.execute_stream(
+                id="my-workflow",
+                inputs={"question": "What is the capital of France?"},
+            )
+            async for chunk in response:
+                yield chunk
+
+
+        asyncio.run(main())
+        """
+        async with self._raw_client.execute_stream(
+            id,
+            inputs=inputs,
+            trigger=trigger,
+            release_tag=release_tag,
+            external_id=external_id,
+            metadata=metadata,
+            previous_execution_id=previous_execution_id,
+            request_options=request_options,
+        ) as r:
+            async for _chunk in r.data:
+                yield _chunk
 
     async def list_workflow_deployment_event_executions(
         self,
@@ -658,6 +757,7 @@ class AsyncWorkflowDeploymentsClient:
         filters: typing.Optional[str] = None,
         limit: typing.Optional[int] = None,
         offset: typing.Optional[int] = None,
+        ordering: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> WorkflowDeploymentEventExecutionsResponse:
         """
@@ -673,6 +773,8 @@ class AsyncWorkflowDeploymentsClient:
         offset : typing.Optional[int]
             The initial index from which to return the executions.
 
+        ordering : typing.Optional[str]
+
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
@@ -688,6 +790,7 @@ class AsyncWorkflowDeploymentsClient:
         from vellum import AsyncVellum
 
         client = AsyncVellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
 
@@ -700,30 +803,10 @@ class AsyncWorkflowDeploymentsClient:
 
         asyncio.run(main())
         """
-        _response = await self._client_wrapper.httpx_client.request(
-            f"v1/workflow-deployments/{jsonable_encoder(id)}/execution-events",
-            base_url=self._client_wrapper.get_environment().default,
-            method="GET",
-            params={
-                "filters": filters,
-                "limit": limit,
-                "offset": offset,
-            },
-            request_options=request_options,
+        _response = await self._raw_client.list_workflow_deployment_event_executions(
+            id, filters=filters, limit=limit, offset=offset, ordering=ordering, request_options=request_options
         )
-        try:
-            if 200 <= _response.status_code < 300:
-                return typing.cast(
-                    WorkflowDeploymentEventExecutionsResponse,
-                    parse_obj_as(
-                        type_=WorkflowDeploymentEventExecutionsResponse,  # 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 workflow_deployment_event_execution(
         self, execution_id: str, id: str, *, request_options: typing.Optional[RequestOptions] = None
@@ -750,6 +833,7 @@ class AsyncWorkflowDeploymentsClient:
         from vellum import AsyncVellum
 
         client = AsyncVellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
 
@@ -763,25 +847,10 @@ class AsyncWorkflowDeploymentsClient:
 
         asyncio.run(main())
         """
-        _response = await self._client_wrapper.httpx_client.request(
-            f"v1/workflow-deployments/{jsonable_encoder(id)}/execution-events/{jsonable_encoder(execution_id)}",
-            base_url=self._client_wrapper.get_environment().default,
-            method="GET",
-            request_options=request_options,
+        _response = await self._raw_client.workflow_deployment_event_execution(
+            execution_id, id, request_options=request_options
         )
-        try:
-            if 200 <= _response.status_code < 300:
-                return typing.cast(
-                    WorkflowEventExecutionRead,
-                    parse_obj_as(
-                        type_=WorkflowEventExecutionRead,  # 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 workflow_deployment_history_item_retrieve(
         self, history_id_or_release_tag: str, id: str, *, request_options: typing.Optional[RequestOptions] = None
@@ -813,6 +882,7 @@ class AsyncWorkflowDeploymentsClient:
         from vellum import AsyncVellum
 
         client = AsyncVellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
 
@@ -826,25 +896,10 @@ class AsyncWorkflowDeploymentsClient:
 
         asyncio.run(main())
         """
-        _response = await self._client_wrapper.httpx_client.request(
-            f"v1/workflow-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.workflow_deployment_history_item_retrieve(
+            history_id_or_release_tag, id, request_options=request_options
         )
-        try:
-            if 200 <= _response.status_code < 300:
-                return typing.cast(
-                    WorkflowDeploymentHistoryItem,
-                    parse_obj_as(
-                        type_=WorkflowDeploymentHistoryItem,  # 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_workflow_release_tags(
         self,
@@ -890,6 +945,7 @@ class AsyncWorkflowDeploymentsClient:
         from vellum import AsyncVellum
 
         client = AsyncVellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
 
@@ -902,31 +958,10 @@ class AsyncWorkflowDeploymentsClient:
 
         asyncio.run(main())
         """
-        _response = await self._client_wrapper.httpx_client.request(
-            f"v1/workflow-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_workflow_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(
-                    PaginatedWorkflowReleaseTagReadList,
-                    parse_obj_as(
-                        type_=PaginatedWorkflowReleaseTagReadList,  # 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_workflow_release_tag(
         self, id: str, name: str, *, request_options: typing.Optional[RequestOptions] = None
@@ -957,6 +992,7 @@ class AsyncWorkflowDeploymentsClient:
         from vellum import AsyncVellum
 
         client = AsyncVellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
 
@@ -970,25 +1006,8 @@ class AsyncWorkflowDeploymentsClient:
 
         asyncio.run(main())
         """
-        _response = await self._client_wrapper.httpx_client.request(
-            f"v1/workflow-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(
-                    WorkflowReleaseTagRead,
-                    parse_obj_as(
-                        type_=WorkflowReleaseTagRead,  # 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_workflow_release_tag(id, name, request_options=request_options)
+        return _response.data
 
     async def update_workflow_release_tag(
         self,
@@ -1027,6 +1046,7 @@ class AsyncWorkflowDeploymentsClient:
         from vellum import AsyncVellum
 
         client = AsyncVellum(
+            api_version="YOUR_API_VERSION",
             api_key="YOUR_API_KEY",
         )
 
@@ -1040,29 +1060,114 @@ class AsyncWorkflowDeploymentsClient:
 
         asyncio.run(main())
         """
-        _response = await self._client_wrapper.httpx_client.request(
-            f"v1/workflow-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,
-            },
-            headers={
-                "content-type": "application/json",
-            },
-            request_options=request_options,
-            omit=OMIT,
+        _response = await self._raw_client.update_workflow_release_tag(
+            id, name, history_item_id=history_item_id, request_options=request_options
+        )
+        return _response.data
+
+    async def list_workflow_deployment_releases(
+        self,
+        id: str,
+        *,
+        limit: typing.Optional[int] = None,
+        offset: typing.Optional[int] = None,
+        ordering: typing.Optional[str] = None,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> PaginatedWorkflowDeploymentReleaseList:
+        """
+        List the Releases of the specified Workflow Deployment for the current Environment.
+
+        Parameters
+        ----------
+        id : str
+            Either the Workflow Deployment's ID or its unique name
+
+        limit : typing.Optional[int]
+            Number of results to return per page.
+
+        offset : typing.Optional[int]
+            The initial index from which to return the results.
+
+        ordering : typing.Optional[str]
+            Which field to use when ordering the results.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        PaginatedWorkflowDeploymentReleaseList
+
+
+        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.workflow_deployments.list_workflow_deployment_releases(
+                id="id",
+            )
+
+
+        asyncio.run(main())
+        """
+        _response = await self._raw_client.list_workflow_deployment_releases(
+            id, limit=limit, offset=offset, ordering=ordering, request_options=request_options
+        )
+        return _response.data
+
+    async def retrieve_workflow_deployment_release(
+        self, id: str, release_id_or_release_tag: str, *, request_options: typing.Optional[RequestOptions] = None
+    ) -> WorkflowDeploymentRelease:
+        """
+        Retrieve a specific Workflow Deployment Release by either its UUID or the name of a Release Tag that points to it.
+
+        Parameters
+        ----------
+        id : str
+            Either the Workflow Deployment's ID or its unique name
+
+        release_id_or_release_tag : str
+            Either the UUID of Workflow Deployment Release you'd like to retrieve, or the name of a Release Tag that's pointing to the Workflow Deployment Release you'd like to retrieve.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        WorkflowDeploymentRelease
+
+
+        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.workflow_deployments.retrieve_workflow_deployment_release(
+                id="id",
+                release_id_or_release_tag="release_id_or_release_tag",
+            )
+
+
+        asyncio.run(main())
+        """
+        _response = await self._raw_client.retrieve_workflow_deployment_release(
+            id, release_id_or_release_tag, request_options=request_options
         )
-        try:
-            if 200 <= _response.status_code < 300:
-                return typing.cast(
-                    WorkflowReleaseTagRead,
-                    parse_obj_as(
-                        type_=WorkflowReleaseTagRead,  # 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