vellum-ai 0.14.63__py3-none-any.whl → 1.11.2__py3-none-any.whl

vellum/client/raw_client.py

@@ -0,0 +1,2725 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import contextlib
+import json
+import typing
+from json.decoder import JSONDecodeError
+
+from .core.api_error import ApiError
+from .core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
+from .core.http_response import AsyncHttpResponse, HttpResponse
+from .core.pydantic_utilities import parse_obj_as
+from .core.request_options import RequestOptions
+from .core.serialization import convert_and_respect_annotation_metadata
+from .errors.bad_request_error import BadRequestError
+from .errors.forbidden_error import ForbiddenError
+from .errors.internal_server_error import InternalServerError
+from .errors.not_found_error import NotFoundError
+from .types.code_execution_package import CodeExecutionPackage
+from .types.code_execution_runtime import CodeExecutionRuntime
+from .types.code_executor_input import CodeExecutorInput
+from .types.code_executor_response import CodeExecutorResponse
+from .types.execute_api_request_bearer_token import ExecuteApiRequestBearerToken
+from .types.execute_api_request_body import ExecuteApiRequestBody
+from .types.execute_api_request_headers_value import ExecuteApiRequestHeadersValue
+from .types.execute_api_response import ExecuteApiResponse
+from .types.execute_prompt_event import ExecutePromptEvent
+from .types.execute_prompt_response import ExecutePromptResponse
+from .types.execute_workflow_async_response import ExecuteWorkflowAsyncResponse
+from .types.execute_workflow_response import ExecuteWorkflowResponse
+from .types.generate_options_request import GenerateOptionsRequest
+from .types.generate_request import GenerateRequest
+from .types.generate_response import GenerateResponse
+from .types.generate_stream_response import GenerateStreamResponse
+from .types.method_enum import MethodEnum
+from .types.prompt_deployment_expand_meta_request import PromptDeploymentExpandMetaRequest
+from .types.prompt_deployment_input_request import PromptDeploymentInputRequest
+from .types.raw_prompt_execution_overrides_request import RawPromptExecutionOverridesRequest
+from .types.search_request_options_request import SearchRequestOptionsRequest
+from .types.search_response import SearchResponse
+from .types.submit_completion_actual_request import SubmitCompletionActualRequest
+from .types.submit_workflow_execution_actual_request import SubmitWorkflowExecutionActualRequest
+from .types.vellum_variable_type import VellumVariableType
+from .types.workflow_execution_event_type import WorkflowExecutionEventType
+from .types.workflow_expand_meta_request import WorkflowExpandMetaRequest
+from .types.workflow_request_input_request import WorkflowRequestInputRequest
+from .types.workflow_stream_event import WorkflowStreamEvent
+
+# this is used as the default value for optional parameters
+OMIT = typing.cast(typing.Any, ...)
+
+
+class RawVellum:
+    def __init__(self, *, client_wrapper: SyncClientWrapper):
+        self._client_wrapper = client_wrapper
+
+    def execute_api(
+        self,
+        *,
+        url: str,
+        method: typing.Optional[MethodEnum] = OMIT,
+        body: typing.Optional[ExecuteApiRequestBody] = OMIT,
+        headers: typing.Optional[typing.Dict[str, ExecuteApiRequestHeadersValue]] = OMIT,
+        bearer_token: typing.Optional[ExecuteApiRequestBearerToken] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> HttpResponse[ExecuteApiResponse]:
+        """
+        Parameters
+        ----------
+        url : str
+
+        method : typing.Optional[MethodEnum]
+
+        body : typing.Optional[ExecuteApiRequestBody]
+
+        headers : typing.Optional[typing.Dict[str, ExecuteApiRequestHeadersValue]]
+
+        bearer_token : typing.Optional[ExecuteApiRequestBearerToken]
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        HttpResponse[ExecuteApiResponse]
+
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "v1/execute-api",
+            base_url=self._client_wrapper.get_environment().default,
+            method="POST",
+            json={
+                "url": url,
+                "method": method,
+                "body": convert_and_respect_annotation_metadata(
+                    object_=body, annotation=typing.Optional[ExecuteApiRequestBody], direction="write"
+                ),
+                "headers": convert_and_respect_annotation_metadata(
+                    object_=headers, annotation=typing.Dict[str, ExecuteApiRequestHeadersValue], direction="write"
+                ),
+                "bearer_token": convert_and_respect_annotation_metadata(
+                    object_=bearer_token, annotation=typing.Optional[ExecuteApiRequestBearerToken], direction="write"
+                ),
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                _data = typing.cast(
+                    ExecuteApiResponse,
+                    parse_obj_as(
+                        type_=ExecuteApiResponse,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+                return HttpResponse(response=_response, data=_data)
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+    def execute_code(
+        self,
+        *,
+        code: str,
+        runtime: CodeExecutionRuntime,
+        input_values: typing.Sequence[CodeExecutorInput],
+        packages: typing.Sequence[CodeExecutionPackage],
+        output_type: VellumVariableType,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> HttpResponse[CodeExecutorResponse]:
+        """
+        Parameters
+        ----------
+        code : str
+
+        runtime : CodeExecutionRuntime
+
+        input_values : typing.Sequence[CodeExecutorInput]
+
+        packages : typing.Sequence[CodeExecutionPackage]
+
+        output_type : VellumVariableType
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        HttpResponse[CodeExecutorResponse]
+
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "v1/execute-code",
+            base_url=self._client_wrapper.get_environment().predict,
+            method="POST",
+            json={
+                "code": code,
+                "runtime": runtime,
+                "input_values": convert_and_respect_annotation_metadata(
+                    object_=input_values, annotation=typing.Sequence[CodeExecutorInput], direction="write"
+                ),
+                "packages": convert_and_respect_annotation_metadata(
+                    object_=packages, annotation=typing.Sequence[CodeExecutionPackage], direction="write"
+                ),
+                "output_type": output_type,
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                _data = typing.cast(
+                    CodeExecutorResponse,
+                    parse_obj_as(
+                        type_=CodeExecutorResponse,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+                return HttpResponse(response=_response, data=_data)
+            if _response.status_code == 400:
+                raise BadRequestError(
+                    headers=dict(_response.headers),
+                    body=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, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+    def execute_prompt(
+        self,
+        *,
+        inputs: typing.Sequence[PromptDeploymentInputRequest],
+        prompt_deployment_id: typing.Optional[str] = OMIT,
+        prompt_deployment_name: typing.Optional[str] = OMIT,
+        release_tag: typing.Optional[str] = OMIT,
+        external_id: typing.Optional[str] = OMIT,
+        expand_meta: typing.Optional[PromptDeploymentExpandMetaRequest] = OMIT,
+        raw_overrides: typing.Optional[RawPromptExecutionOverridesRequest] = OMIT,
+        expand_raw: typing.Optional[typing.Sequence[str]] = OMIT,
+        metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> HttpResponse[ExecutePromptResponse]:
+        """
+        Executes a deployed Prompt and returns the result.
+
+        Parameters
+        ----------
+        inputs : typing.Sequence[PromptDeploymentInputRequest]
+            A list consisting of the Prompt Deployment's input variables and their values.
+
+        prompt_deployment_id : typing.Optional[str]
+            The ID of the Prompt Deployment. Must provide either this or prompt_deployment_name.
+
+        prompt_deployment_name : typing.Optional[str]
+            The unique name of the Prompt Deployment. Must provide either this or prompt_deployment_id.
+
+        release_tag : typing.Optional[str]
+            Optionally specify a release tag if you want to pin to a specific release of the Prompt Deployment
+
+        external_id : typing.Optional[str]
+            Optionally include a unique identifier for tracking purposes. Must be unique within a given Workspace.
+
+        expand_meta : typing.Optional[PromptDeploymentExpandMetaRequest]
+            An optionally specified configuration used to opt in to including additional metadata about this prompt execution in the API response. Corresponding values will be returned under the `meta` key of the API response.
+
+        raw_overrides : typing.Optional[RawPromptExecutionOverridesRequest]
+            Overrides for the raw API request sent to the model host. Combined with `expand_raw`, it can be used to access new features from models.
+
+        expand_raw : typing.Optional[typing.Sequence[str]]
+            A list of keys whose values you'd like to directly return from the JSON response of the model provider. Useful if you need lower-level info returned by model providers that Vellum would otherwise omit. Corresponding key/value pairs will be returned under the `raw` key of the API response.
+
+        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.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        HttpResponse[ExecutePromptResponse]
+
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "v1/execute-prompt",
+            base_url=self._client_wrapper.get_environment().predict,
+            method="POST",
+            json={
+                "inputs": convert_and_respect_annotation_metadata(
+                    object_=inputs, annotation=typing.Sequence[PromptDeploymentInputRequest], direction="write"
+                ),
+                "prompt_deployment_id": prompt_deployment_id,
+                "prompt_deployment_name": prompt_deployment_name,
+                "release_tag": release_tag,
+                "external_id": external_id,
+                "expand_meta": convert_and_respect_annotation_metadata(
+                    object_=expand_meta,
+                    annotation=typing.Optional[PromptDeploymentExpandMetaRequest],
+                    direction="write",
+                ),
+                "raw_overrides": convert_and_respect_annotation_metadata(
+                    object_=raw_overrides,
+                    annotation=typing.Optional[RawPromptExecutionOverridesRequest],
+                    direction="write",
+                ),
+                "expand_raw": expand_raw,
+                "metadata": metadata,
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                _data = typing.cast(
+                    ExecutePromptResponse,
+                    parse_obj_as(
+                        type_=ExecutePromptResponse,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+                return HttpResponse(response=_response, data=_data)
+            if _response.status_code == 400:
+                raise BadRequestError(
+                    headers=dict(_response.headers),
+                    body=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(
+                    headers=dict(_response.headers),
+                    body=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(
+                    headers=dict(_response.headers),
+                    body=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(
+                    headers=dict(_response.headers),
+                    body=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, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+    @contextlib.contextmanager
+    def execute_prompt_stream(
+        self,
+        *,
+        inputs: typing.Sequence[PromptDeploymentInputRequest],
+        prompt_deployment_id: typing.Optional[str] = OMIT,
+        prompt_deployment_name: typing.Optional[str] = OMIT,
+        release_tag: typing.Optional[str] = OMIT,
+        external_id: typing.Optional[str] = OMIT,
+        expand_meta: typing.Optional[PromptDeploymentExpandMetaRequest] = OMIT,
+        raw_overrides: typing.Optional[RawPromptExecutionOverridesRequest] = OMIT,
+        expand_raw: typing.Optional[typing.Sequence[str]] = OMIT,
+        metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> typing.Iterator[HttpResponse[typing.Iterator[ExecutePromptEvent]]]:
+        """
+        Executes a deployed Prompt and streams back the results.
+
+        Parameters
+        ----------
+        inputs : typing.Sequence[PromptDeploymentInputRequest]
+            A list consisting of the Prompt Deployment's input variables and their values.
+
+        prompt_deployment_id : typing.Optional[str]
+            The ID of the Prompt Deployment. Must provide either this or prompt_deployment_name.
+
+        prompt_deployment_name : typing.Optional[str]
+            The unique name of the Prompt Deployment. Must provide either this or prompt_deployment_id.
+
+        release_tag : typing.Optional[str]
+            Optionally specify a release tag if you want to pin to a specific release of the Prompt Deployment
+
+        external_id : typing.Optional[str]
+            Optionally include a unique identifier for tracking purposes. Must be unique within a given Workspace.
+
+        expand_meta : typing.Optional[PromptDeploymentExpandMetaRequest]
+            An optionally specified configuration used to opt in to including additional metadata about this prompt execution in the API response. Corresponding values will be returned under the `meta` key of the API response.
+
+        raw_overrides : typing.Optional[RawPromptExecutionOverridesRequest]
+            Overrides for the raw API request sent to the model host. Combined with `expand_raw`, it can be used to access new features from models.
+
+        expand_raw : typing.Optional[typing.Sequence[str]]
+            A list of keys whose values you'd like to directly return from the JSON response of the model provider. Useful if you need lower-level info returned by model providers that Vellum would otherwise omit. Corresponding key/value pairs will be returned under the `raw` key of the API response.
+
+        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.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Yields
+        ------
+        typing.Iterator[HttpResponse[typing.Iterator[ExecutePromptEvent]]]
+
+        """
+        with self._client_wrapper.httpx_client.stream(
+            "v1/execute-prompt-stream",
+            base_url=self._client_wrapper.get_environment().predict,
+            method="POST",
+            json={
+                "inputs": convert_and_respect_annotation_metadata(
+                    object_=inputs, annotation=typing.Sequence[PromptDeploymentInputRequest], direction="write"
+                ),
+                "prompt_deployment_id": prompt_deployment_id,
+                "prompt_deployment_name": prompt_deployment_name,
+                "release_tag": release_tag,
+                "external_id": external_id,
+                "expand_meta": convert_and_respect_annotation_metadata(
+                    object_=expand_meta,
+                    annotation=typing.Optional[PromptDeploymentExpandMetaRequest],
+                    direction="write",
+                ),
+                "raw_overrides": convert_and_respect_annotation_metadata(
+                    object_=raw_overrides,
+                    annotation=typing.Optional[RawPromptExecutionOverridesRequest],
+                    direction="write",
+                ),
+                "expand_raw": expand_raw,
+                "metadata": metadata,
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        ) as _response:
+
+            def _stream() -> HttpResponse[typing.Iterator[ExecutePromptEvent]]:
+                try:
+                    if 200 <= _response.status_code < 300:
+
+                        def _iter():
+                            for _text in _response.iter_lines():
+                                try:
+                                    if len(_text) == 0:
+                                        continue
+                                    yield typing.cast(
+                                        ExecutePromptEvent,
+                                        parse_obj_as(
+                                            type_=ExecutePromptEvent,  # type: ignore
+                                            object_=json.loads(_text),
+                                        ),
+                                    )
+                                except Exception:
+                                    pass
+                            return
+
+                        return HttpResponse(response=_response, data=_iter())
+                    _response.read()
+                    if _response.status_code == 400:
+                        raise BadRequestError(
+                            headers=dict(_response.headers),
+                            body=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(
+                            headers=dict(_response.headers),
+                            body=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(
+                            headers=dict(_response.headers),
+                            body=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(
+                            headers=dict(_response.headers),
+                            body=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, headers=dict(_response.headers), body=_response.text
+                    )
+                raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+            yield _stream()
+
+    def execute_workflow(
+        self,
+        *,
+        inputs: typing.Sequence[WorkflowRequestInputRequest],
+        expand_meta: typing.Optional[WorkflowExpandMetaRequest] = OMIT,
+        workflow_deployment_id: typing.Optional[str] = OMIT,
+        workflow_deployment_name: 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,
+    ) -> HttpResponse[ExecuteWorkflowResponse]:
+        """
+        Executes a deployed Workflow and returns its outputs.
+
+        Parameters
+        ----------
+        inputs : typing.Sequence[WorkflowRequestInputRequest]
+            The list of inputs defined in the Workflow's Deployment with their corresponding values.
+
+        expand_meta : typing.Optional[WorkflowExpandMetaRequest]
+            An optionally specified configuration used to opt in to including additional metadata about this workflow execution in the API response. Corresponding values will be returned under the `execution_meta` key within NODE events in the response stream.
+
+        workflow_deployment_id : typing.Optional[str]
+            The ID of the Workflow Deployment. Must provide either this or workflow_deployment_name.
+
+        workflow_deployment_name : typing.Optional[str]
+            The name of the Workflow Deployment. Must provide either this or workflow_deployment_id.
+
+        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 initial State loading.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        HttpResponse[ExecuteWorkflowResponse]
+
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "v1/execute-workflow",
+            base_url=self._client_wrapper.get_environment().predict,
+            method="POST",
+            json={
+                "inputs": convert_and_respect_annotation_metadata(
+                    object_=inputs, annotation=typing.Sequence[WorkflowRequestInputRequest], direction="write"
+                ),
+                "expand_meta": convert_and_respect_annotation_metadata(
+                    object_=expand_meta, annotation=typing.Optional[WorkflowExpandMetaRequest], direction="write"
+                ),
+                "workflow_deployment_id": workflow_deployment_id,
+                "workflow_deployment_name": workflow_deployment_name,
+                "release_tag": release_tag,
+                "external_id": external_id,
+                "metadata": metadata,
+                "previous_execution_id": previous_execution_id,
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                _data = typing.cast(
+                    ExecuteWorkflowResponse,
+                    parse_obj_as(
+                        type_=ExecuteWorkflowResponse,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+                return HttpResponse(response=_response, data=_data)
+            if _response.status_code == 400:
+                raise BadRequestError(
+                    headers=dict(_response.headers),
+                    body=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(
+                    headers=dict(_response.headers),
+                    body=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(
+                    headers=dict(_response.headers),
+                    body=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, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+    def execute_workflow_async(
+        self,
+        *,
+        inputs: typing.Sequence[WorkflowRequestInputRequest],
+        workflow_deployment_id: typing.Optional[str] = OMIT,
+        workflow_deployment_name: typing.Optional[str] = OMIT,
+        release_tag: typing.Optional[str] = OMIT,
+        external_id: typing.Optional[str] = OMIT,
+        previous_execution_id: typing.Optional[str] = OMIT,
+        metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> HttpResponse[ExecuteWorkflowAsyncResponse]:
+        """
+        Executes a deployed Workflow asynchronously and returns the execution ID.
+
+        Parameters
+        ----------
+        inputs : typing.Sequence[WorkflowRequestInputRequest]
+            The list of inputs defined in the Workflow's Deployment with their corresponding values.
+
+        workflow_deployment_id : typing.Optional[str]
+            The ID of the Workflow Deployment. Must provide either this or workflow_deployment_name.
+
+        workflow_deployment_name : typing.Optional[str]
+            The name of the Workflow Deployment. Must provide either this or workflow_deployment_id.
+
+        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.
+
+        previous_execution_id : typing.Optional[str]
+            The ID of a previous Workflow Execution to reference for initial State loading.
+
+        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.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        HttpResponse[ExecuteWorkflowAsyncResponse]
+
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "v1/execute-workflow-async",
+            base_url=self._client_wrapper.get_environment().predict,
+            method="POST",
+            json={
+                "inputs": convert_and_respect_annotation_metadata(
+                    object_=inputs, annotation=typing.Sequence[WorkflowRequestInputRequest], direction="write"
+                ),
+                "workflow_deployment_id": workflow_deployment_id,
+                "workflow_deployment_name": workflow_deployment_name,
+                "release_tag": release_tag,
+                "external_id": external_id,
+                "previous_execution_id": previous_execution_id,
+                "metadata": metadata,
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                _data = typing.cast(
+                    ExecuteWorkflowAsyncResponse,
+                    parse_obj_as(
+                        type_=ExecuteWorkflowAsyncResponse,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+                return HttpResponse(response=_response, data=_data)
+            if _response.status_code == 400:
+                raise BadRequestError(
+                    headers=dict(_response.headers),
+                    body=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(
+                    headers=dict(_response.headers),
+                    body=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(
+                    headers=dict(_response.headers),
+                    body=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, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+    @contextlib.contextmanager
+    def execute_workflow_stream(
+        self,
+        *,
+        inputs: typing.Sequence[WorkflowRequestInputRequest],
+        expand_meta: typing.Optional[WorkflowExpandMetaRequest] = OMIT,
+        workflow_deployment_id: typing.Optional[str] = OMIT,
+        workflow_deployment_name: typing.Optional[str] = OMIT,
+        release_tag: typing.Optional[str] = OMIT,
+        external_id: typing.Optional[str] = OMIT,
+        event_types: typing.Optional[typing.Sequence[WorkflowExecutionEventType]] = 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[HttpResponse[typing.Iterator[WorkflowStreamEvent]]]:
+        """
+        Executes a deployed Workflow and streams back its results.
+
+        Parameters
+        ----------
+        inputs : typing.Sequence[WorkflowRequestInputRequest]
+            The list of inputs defined in the Workflow's Deployment with their corresponding values.
+
+        expand_meta : typing.Optional[WorkflowExpandMetaRequest]
+            An optionally specified configuration used to opt in to including additional metadata about this workflow execution in the API response. Corresponding values will be returned under the `execution_meta` key within NODE events in the response stream.
+
+        workflow_deployment_id : typing.Optional[str]
+            The ID of the Workflow Deployment. Must provide either this or workflow_deployment_name.
+
+        workflow_deployment_name : typing.Optional[str]
+            The name of the Workflow Deployment. Must provide either this or workflow_deployment_id.
+
+        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.
+
+        event_types : typing.Optional[typing.Sequence[WorkflowExecutionEventType]]
+            Optionally specify which events you want to receive. Defaults to only WORKFLOW events. Note that the schema of non-WORKFLOW events is unstable and should be used with caution.
+
+        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 initial State loading.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Yields
+        ------
+        typing.Iterator[HttpResponse[typing.Iterator[WorkflowStreamEvent]]]
+
+        """
+        with self._client_wrapper.httpx_client.stream(
+            "v1/execute-workflow-stream",
+            base_url=self._client_wrapper.get_environment().predict,
+            method="POST",
+            json={
+                "inputs": convert_and_respect_annotation_metadata(
+                    object_=inputs, annotation=typing.Sequence[WorkflowRequestInputRequest], direction="write"
+                ),
+                "expand_meta": convert_and_respect_annotation_metadata(
+                    object_=expand_meta, annotation=typing.Optional[WorkflowExpandMetaRequest], direction="write"
+                ),
+                "workflow_deployment_id": workflow_deployment_id,
+                "workflow_deployment_name": workflow_deployment_name,
+                "release_tag": release_tag,
+                "external_id": external_id,
+                "event_types": event_types,
+                "metadata": metadata,
+                "previous_execution_id": previous_execution_id,
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        ) as _response:
+
+            def _stream() -> HttpResponse[typing.Iterator[WorkflowStreamEvent]]:
+                try:
+                    if 200 <= _response.status_code < 300:
+
+                        def _iter():
+                            for _text in _response.iter_lines():
+                                try:
+                                    if len(_text) == 0:
+                                        continue
+                                    yield typing.cast(
+                                        WorkflowStreamEvent,
+                                        parse_obj_as(
+                                            type_=WorkflowStreamEvent,  # type: ignore
+                                            object_=json.loads(_text),
+                                        ),
+                                    )
+                                except Exception:
+                                    pass
+                            return
+
+                        return HttpResponse(response=_response, data=_iter())
+                    _response.read()
+                    if _response.status_code == 400:
+                        raise BadRequestError(
+                            headers=dict(_response.headers),
+                            body=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(
+                            headers=dict(_response.headers),
+                            body=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(
+                            headers=dict(_response.headers),
+                            body=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, headers=dict(_response.headers), body=_response.text
+                    )
+                raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+            yield _stream()
+
+    def generate(
+        self,
+        *,
+        requests: typing.Sequence[GenerateRequest],
+        deployment_id: typing.Optional[str] = OMIT,
+        deployment_name: typing.Optional[str] = OMIT,
+        options: typing.Optional[GenerateOptionsRequest] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> HttpResponse[GenerateResponse]:
+        """
+        Generate a completion using a previously defined deployment.
+
+        Important: This endpoint is DEPRECATED and has been superseded by
+        [execute-prompt](/api-reference/api-reference/execute-prompt).
+
+        Parameters
+        ----------
+        requests : typing.Sequence[GenerateRequest]
+            The generation request to make. Bulk requests are no longer supported, this field must be an array of length 1.
+
+        deployment_id : typing.Optional[str]
+            The ID of the deployment. Must provide either this or deployment_name.
+
+        deployment_name : typing.Optional[str]
+            The name of the deployment. Must provide either this or deployment_id.
+
+        options : typing.Optional[GenerateOptionsRequest]
+            Additional configuration that can be used to control what's included in the response.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        HttpResponse[GenerateResponse]
+
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "v1/generate",
+            base_url=self._client_wrapper.get_environment().predict,
+            method="POST",
+            json={
+                "deployment_id": deployment_id,
+                "deployment_name": deployment_name,
+                "requests": convert_and_respect_annotation_metadata(
+                    object_=requests, annotation=typing.Sequence[GenerateRequest], direction="write"
+                ),
+                "options": convert_and_respect_annotation_metadata(
+                    object_=options, annotation=typing.Optional[GenerateOptionsRequest], direction="write"
+                ),
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                _data = typing.cast(
+                    GenerateResponse,
+                    parse_obj_as(
+                        type_=GenerateResponse,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+                return HttpResponse(response=_response, data=_data)
+            if _response.status_code == 400:
+                raise BadRequestError(
+                    headers=dict(_response.headers),
+                    body=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(
+                    headers=dict(_response.headers),
+                    body=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(
+                    headers=dict(_response.headers),
+                    body=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(
+                    headers=dict(_response.headers),
+                    body=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, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+    @contextlib.contextmanager
+    def generate_stream(
+        self,
+        *,
+        requests: typing.Sequence[GenerateRequest],
+        deployment_id: typing.Optional[str] = OMIT,
+        deployment_name: typing.Optional[str] = OMIT,
+        options: typing.Optional[GenerateOptionsRequest] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> typing.Iterator[HttpResponse[typing.Iterator[GenerateStreamResponse]]]:
+        """
+        Generate a stream of completions using a previously defined deployment.
+
+        Important: This endpoint is DEPRECATED and has been superseded by
+        [execute-prompt-stream](/api-reference/api-reference/execute-prompt-stream).
+
+        Parameters
+        ----------
+        requests : typing.Sequence[GenerateRequest]
+            The generation request to make. Bulk requests are no longer supported, this field must be an array of length 1.
+
+        deployment_id : typing.Optional[str]
+            The ID of the deployment. Must provide either this or deployment_name.
+
+        deployment_name : typing.Optional[str]
+            The name of the deployment. Must provide either this or deployment_id.
+
+        options : typing.Optional[GenerateOptionsRequest]
+            Additional configuration that can be used to control what's included in the response.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Yields
+        ------
+        typing.Iterator[HttpResponse[typing.Iterator[GenerateStreamResponse]]]
+
+        """
+        with self._client_wrapper.httpx_client.stream(
+            "v1/generate-stream",
+            base_url=self._client_wrapper.get_environment().predict,
+            method="POST",
+            json={
+                "deployment_id": deployment_id,
+                "deployment_name": deployment_name,
+                "requests": convert_and_respect_annotation_metadata(
+                    object_=requests, annotation=typing.Sequence[GenerateRequest], direction="write"
+                ),
+                "options": convert_and_respect_annotation_metadata(
+                    object_=options, annotation=typing.Optional[GenerateOptionsRequest], direction="write"
+                ),
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        ) as _response:
+
+            def _stream() -> HttpResponse[typing.Iterator[GenerateStreamResponse]]:
+                try:
+                    if 200 <= _response.status_code < 300:
+
+                        def _iter():
+                            for _text in _response.iter_lines():
+                                try:
+                                    if len(_text) == 0:
+                                        continue
+                                    yield typing.cast(
+                                        GenerateStreamResponse,
+                                        parse_obj_as(
+                                            type_=GenerateStreamResponse,  # type: ignore
+                                            object_=json.loads(_text),
+                                        ),
+                                    )
+                                except Exception:
+                                    pass
+                            return
+
+                        return HttpResponse(response=_response, data=_iter())
+                    _response.read()
+                    if _response.status_code == 400:
+                        raise BadRequestError(
+                            headers=dict(_response.headers),
+                            body=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(
+                            headers=dict(_response.headers),
+                            body=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(
+                            headers=dict(_response.headers),
+                            body=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(
+                            headers=dict(_response.headers),
+                            body=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, headers=dict(_response.headers), body=_response.text
+                    )
+                raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+            yield _stream()
+
+    def search(
+        self,
+        *,
+        query: str,
+        index_id: typing.Optional[str] = OMIT,
+        index_name: typing.Optional[str] = OMIT,
+        options: typing.Optional[SearchRequestOptionsRequest] = OMIT,
+        document_index: typing.Optional[str] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> HttpResponse[SearchResponse]:
+        """
+        Perform a search against a document index.
+
+        Parameters
+        ----------
+        query : str
+            The query to search for.
+
+        index_id : typing.Optional[str]
+            The ID of the index to search against. Must provide either this, index_name or document_index.
+
+        index_name : typing.Optional[str]
+            The name of the index to search against. Must provide either this, index_id or document_index.
+
+        options : typing.Optional[SearchRequestOptionsRequest]
+            Configuration options for the search.
+
+        document_index : typing.Optional[str]
+            Either the index name or index ID to search against. Must provide either this, index_id or index_name.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        HttpResponse[SearchResponse]
+
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "v1/search",
+            base_url=self._client_wrapper.get_environment().predict,
+            method="POST",
+            json={
+                "index_id": index_id,
+                "index_name": index_name,
+                "query": query,
+                "options": convert_and_respect_annotation_metadata(
+                    object_=options, annotation=typing.Optional[SearchRequestOptionsRequest], direction="write"
+                ),
+                "document_index": document_index,
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                _data = typing.cast(
+                    SearchResponse,
+                    parse_obj_as(
+                        type_=SearchResponse,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+                return HttpResponse(response=_response, data=_data)
+            if _response.status_code == 400:
+                raise BadRequestError(
+                    headers=dict(_response.headers),
+                    body=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(
+                    headers=dict(_response.headers),
+                    body=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(
+                    headers=dict(_response.headers),
+                    body=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, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+    def submit_completion_actuals(
+        self,
+        *,
+        actuals: typing.Sequence[SubmitCompletionActualRequest],
+        deployment_id: typing.Optional[str] = OMIT,
+        deployment_name: typing.Optional[str] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> HttpResponse[None]:
+        """
+        Used to submit feedback regarding the quality of previously generated completions.
+
+        Parameters
+        ----------
+        actuals : typing.Sequence[SubmitCompletionActualRequest]
+            Feedback regarding the quality of previously generated completions
+
+        deployment_id : typing.Optional[str]
+            The ID of the deployment. Must provide either this or deployment_name.
+
+        deployment_name : typing.Optional[str]
+            The name of the deployment. Must provide either this or deployment_id.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        HttpResponse[None]
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "v1/submit-completion-actuals",
+            base_url=self._client_wrapper.get_environment().predict,
+            method="POST",
+            json={
+                "deployment_id": deployment_id,
+                "deployment_name": deployment_name,
+                "actuals": convert_and_respect_annotation_metadata(
+                    object_=actuals, annotation=typing.Sequence[SubmitCompletionActualRequest], direction="write"
+                ),
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return HttpResponse(response=_response, data=None)
+            if _response.status_code == 400:
+                raise BadRequestError(
+                    headers=dict(_response.headers),
+                    body=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(
+                    headers=dict(_response.headers),
+                    body=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(
+                    headers=dict(_response.headers),
+                    body=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, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+    def submit_workflow_execution_actuals(
+        self,
+        *,
+        actuals: typing.Sequence[SubmitWorkflowExecutionActualRequest],
+        execution_id: typing.Optional[str] = OMIT,
+        external_id: typing.Optional[str] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> HttpResponse[None]:
+        """
+            Used to submit feedback regarding the quality of previous workflow execution and its outputs.
+
+            **Note:** Uses a base url of `https://predict.vellum.ai`.
+
+        Parameters
+        ----------
+        actuals : typing.Sequence[SubmitWorkflowExecutionActualRequest]
+            Feedback regarding the quality of an output on a previously executed workflow.
+
+        execution_id : typing.Optional[str]
+            The Vellum-generated ID of a previously executed workflow. Must provide either this or external_id.
+
+        external_id : typing.Optional[str]
+            The external ID that was originally provided by when executing the workflow, if applicable, that you'd now like to submit actuals for. Must provide either this or execution_id.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        HttpResponse[None]
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "v1/submit-workflow-execution-actuals",
+            base_url=self._client_wrapper.get_environment().predict,
+            method="POST",
+            json={
+                "actuals": convert_and_respect_annotation_metadata(
+                    object_=actuals, annotation=typing.Sequence[SubmitWorkflowExecutionActualRequest], direction="write"
+                ),
+                "execution_id": execution_id,
+                "external_id": external_id,
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return HttpResponse(response=_response, data=None)
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+
+class AsyncRawVellum:
+    def __init__(self, *, client_wrapper: AsyncClientWrapper):
+        self._client_wrapper = client_wrapper
+
+    async def execute_api(
+        self,
+        *,
+        url: str,
+        method: typing.Optional[MethodEnum] = OMIT,
+        body: typing.Optional[ExecuteApiRequestBody] = OMIT,
+        headers: typing.Optional[typing.Dict[str, ExecuteApiRequestHeadersValue]] = OMIT,
+        bearer_token: typing.Optional[ExecuteApiRequestBearerToken] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> AsyncHttpResponse[ExecuteApiResponse]:
+        """
+        Parameters
+        ----------
+        url : str
+
+        method : typing.Optional[MethodEnum]
+
+        body : typing.Optional[ExecuteApiRequestBody]
+
+        headers : typing.Optional[typing.Dict[str, ExecuteApiRequestHeadersValue]]
+
+        bearer_token : typing.Optional[ExecuteApiRequestBearerToken]
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        AsyncHttpResponse[ExecuteApiResponse]
+
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "v1/execute-api",
+            base_url=self._client_wrapper.get_environment().default,
+            method="POST",
+            json={
+                "url": url,
+                "method": method,
+                "body": convert_and_respect_annotation_metadata(
+                    object_=body, annotation=typing.Optional[ExecuteApiRequestBody], direction="write"
+                ),
+                "headers": convert_and_respect_annotation_metadata(
+                    object_=headers, annotation=typing.Dict[str, ExecuteApiRequestHeadersValue], direction="write"
+                ),
+                "bearer_token": convert_and_respect_annotation_metadata(
+                    object_=bearer_token, annotation=typing.Optional[ExecuteApiRequestBearerToken], direction="write"
+                ),
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                _data = typing.cast(
+                    ExecuteApiResponse,
+                    parse_obj_as(
+                        type_=ExecuteApiResponse,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+                return AsyncHttpResponse(response=_response, data=_data)
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+    async def execute_code(
+        self,
+        *,
+        code: str,
+        runtime: CodeExecutionRuntime,
+        input_values: typing.Sequence[CodeExecutorInput],
+        packages: typing.Sequence[CodeExecutionPackage],
+        output_type: VellumVariableType,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> AsyncHttpResponse[CodeExecutorResponse]:
+        """
+        Parameters
+        ----------
+        code : str
+
+        runtime : CodeExecutionRuntime
+
+        input_values : typing.Sequence[CodeExecutorInput]
+
+        packages : typing.Sequence[CodeExecutionPackage]
+
+        output_type : VellumVariableType
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        AsyncHttpResponse[CodeExecutorResponse]
+
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "v1/execute-code",
+            base_url=self._client_wrapper.get_environment().predict,
+            method="POST",
+            json={
+                "code": code,
+                "runtime": runtime,
+                "input_values": convert_and_respect_annotation_metadata(
+                    object_=input_values, annotation=typing.Sequence[CodeExecutorInput], direction="write"
+                ),
+                "packages": convert_and_respect_annotation_metadata(
+                    object_=packages, annotation=typing.Sequence[CodeExecutionPackage], direction="write"
+                ),
+                "output_type": output_type,
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                _data = typing.cast(
+                    CodeExecutorResponse,
+                    parse_obj_as(
+                        type_=CodeExecutorResponse,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+                return AsyncHttpResponse(response=_response, data=_data)
+            if _response.status_code == 400:
+                raise BadRequestError(
+                    headers=dict(_response.headers),
+                    body=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, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+    async def execute_prompt(
+        self,
+        *,
+        inputs: typing.Sequence[PromptDeploymentInputRequest],
+        prompt_deployment_id: typing.Optional[str] = OMIT,
+        prompt_deployment_name: typing.Optional[str] = OMIT,
+        release_tag: typing.Optional[str] = OMIT,
+        external_id: typing.Optional[str] = OMIT,
+        expand_meta: typing.Optional[PromptDeploymentExpandMetaRequest] = OMIT,
+        raw_overrides: typing.Optional[RawPromptExecutionOverridesRequest] = OMIT,
+        expand_raw: typing.Optional[typing.Sequence[str]] = OMIT,
+        metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> AsyncHttpResponse[ExecutePromptResponse]:
+        """
+        Executes a deployed Prompt and returns the result.
+
+        Parameters
+        ----------
+        inputs : typing.Sequence[PromptDeploymentInputRequest]
+            A list consisting of the Prompt Deployment's input variables and their values.
+
+        prompt_deployment_id : typing.Optional[str]
+            The ID of the Prompt Deployment. Must provide either this or prompt_deployment_name.
+
+        prompt_deployment_name : typing.Optional[str]
+            The unique name of the Prompt Deployment. Must provide either this or prompt_deployment_id.
+
+        release_tag : typing.Optional[str]
+            Optionally specify a release tag if you want to pin to a specific release of the Prompt Deployment
+
+        external_id : typing.Optional[str]
+            Optionally include a unique identifier for tracking purposes. Must be unique within a given Workspace.
+
+        expand_meta : typing.Optional[PromptDeploymentExpandMetaRequest]
+            An optionally specified configuration used to opt in to including additional metadata about this prompt execution in the API response. Corresponding values will be returned under the `meta` key of the API response.
+
+        raw_overrides : typing.Optional[RawPromptExecutionOverridesRequest]
+            Overrides for the raw API request sent to the model host. Combined with `expand_raw`, it can be used to access new features from models.
+
+        expand_raw : typing.Optional[typing.Sequence[str]]
+            A list of keys whose values you'd like to directly return from the JSON response of the model provider. Useful if you need lower-level info returned by model providers that Vellum would otherwise omit. Corresponding key/value pairs will be returned under the `raw` key of the API response.
+
+        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.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        AsyncHttpResponse[ExecutePromptResponse]
+
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "v1/execute-prompt",
+            base_url=self._client_wrapper.get_environment().predict,
+            method="POST",
+            json={
+                "inputs": convert_and_respect_annotation_metadata(
+                    object_=inputs, annotation=typing.Sequence[PromptDeploymentInputRequest], direction="write"
+                ),
+                "prompt_deployment_id": prompt_deployment_id,
+                "prompt_deployment_name": prompt_deployment_name,
+                "release_tag": release_tag,
+                "external_id": external_id,
+                "expand_meta": convert_and_respect_annotation_metadata(
+                    object_=expand_meta,
+                    annotation=typing.Optional[PromptDeploymentExpandMetaRequest],
+                    direction="write",
+                ),
+                "raw_overrides": convert_and_respect_annotation_metadata(
+                    object_=raw_overrides,
+                    annotation=typing.Optional[RawPromptExecutionOverridesRequest],
+                    direction="write",
+                ),
+                "expand_raw": expand_raw,
+                "metadata": metadata,
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                _data = typing.cast(
+                    ExecutePromptResponse,
+                    parse_obj_as(
+                        type_=ExecutePromptResponse,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+                return AsyncHttpResponse(response=_response, data=_data)
+            if _response.status_code == 400:
+                raise BadRequestError(
+                    headers=dict(_response.headers),
+                    body=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(
+                    headers=dict(_response.headers),
+                    body=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(
+                    headers=dict(_response.headers),
+                    body=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(
+                    headers=dict(_response.headers),
+                    body=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, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+    @contextlib.asynccontextmanager
+    async def execute_prompt_stream(
+        self,
+        *,
+        inputs: typing.Sequence[PromptDeploymentInputRequest],
+        prompt_deployment_id: typing.Optional[str] = OMIT,
+        prompt_deployment_name: typing.Optional[str] = OMIT,
+        release_tag: typing.Optional[str] = OMIT,
+        external_id: typing.Optional[str] = OMIT,
+        expand_meta: typing.Optional[PromptDeploymentExpandMetaRequest] = OMIT,
+        raw_overrides: typing.Optional[RawPromptExecutionOverridesRequest] = OMIT,
+        expand_raw: typing.Optional[typing.Sequence[str]] = OMIT,
+        metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> typing.AsyncIterator[AsyncHttpResponse[typing.AsyncIterator[ExecutePromptEvent]]]:
+        """
+        Executes a deployed Prompt and streams back the results.
+
+        Parameters
+        ----------
+        inputs : typing.Sequence[PromptDeploymentInputRequest]
+            A list consisting of the Prompt Deployment's input variables and their values.
+
+        prompt_deployment_id : typing.Optional[str]
+            The ID of the Prompt Deployment. Must provide either this or prompt_deployment_name.
+
+        prompt_deployment_name : typing.Optional[str]
+            The unique name of the Prompt Deployment. Must provide either this or prompt_deployment_id.
+
+        release_tag : typing.Optional[str]
+            Optionally specify a release tag if you want to pin to a specific release of the Prompt Deployment
+
+        external_id : typing.Optional[str]
+            Optionally include a unique identifier for tracking purposes. Must be unique within a given Workspace.
+
+        expand_meta : typing.Optional[PromptDeploymentExpandMetaRequest]
+            An optionally specified configuration used to opt in to including additional metadata about this prompt execution in the API response. Corresponding values will be returned under the `meta` key of the API response.
+
+        raw_overrides : typing.Optional[RawPromptExecutionOverridesRequest]
+            Overrides for the raw API request sent to the model host. Combined with `expand_raw`, it can be used to access new features from models.
+
+        expand_raw : typing.Optional[typing.Sequence[str]]
+            A list of keys whose values you'd like to directly return from the JSON response of the model provider. Useful if you need lower-level info returned by model providers that Vellum would otherwise omit. Corresponding key/value pairs will be returned under the `raw` key of the API response.
+
+        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.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Yields
+        ------
+        typing.AsyncIterator[AsyncHttpResponse[typing.AsyncIterator[ExecutePromptEvent]]]
+
+        """
+        async with self._client_wrapper.httpx_client.stream(
+            "v1/execute-prompt-stream",
+            base_url=self._client_wrapper.get_environment().predict,
+            method="POST",
+            json={
+                "inputs": convert_and_respect_annotation_metadata(
+                    object_=inputs, annotation=typing.Sequence[PromptDeploymentInputRequest], direction="write"
+                ),
+                "prompt_deployment_id": prompt_deployment_id,
+                "prompt_deployment_name": prompt_deployment_name,
+                "release_tag": release_tag,
+                "external_id": external_id,
+                "expand_meta": convert_and_respect_annotation_metadata(
+                    object_=expand_meta,
+                    annotation=typing.Optional[PromptDeploymentExpandMetaRequest],
+                    direction="write",
+                ),
+                "raw_overrides": convert_and_respect_annotation_metadata(
+                    object_=raw_overrides,
+                    annotation=typing.Optional[RawPromptExecutionOverridesRequest],
+                    direction="write",
+                ),
+                "expand_raw": expand_raw,
+                "metadata": metadata,
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        ) as _response:
+
+            async def _stream() -> AsyncHttpResponse[typing.AsyncIterator[ExecutePromptEvent]]:
+                try:
+                    if 200 <= _response.status_code < 300:
+
+                        async def _iter():
+                            async for _text in _response.aiter_lines():
+                                try:
+                                    if len(_text) == 0:
+                                        continue
+                                    yield typing.cast(
+                                        ExecutePromptEvent,
+                                        parse_obj_as(
+                                            type_=ExecutePromptEvent,  # type: ignore
+                                            object_=json.loads(_text),
+                                        ),
+                                    )
+                                except Exception:
+                                    pass
+                            return
+
+                        return AsyncHttpResponse(response=_response, data=_iter())
+                    await _response.aread()
+                    if _response.status_code == 400:
+                        raise BadRequestError(
+                            headers=dict(_response.headers),
+                            body=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(
+                            headers=dict(_response.headers),
+                            body=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(
+                            headers=dict(_response.headers),
+                            body=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(
+                            headers=dict(_response.headers),
+                            body=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, headers=dict(_response.headers), body=_response.text
+                    )
+                raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+            yield await _stream()
+
+    async def execute_workflow(
+        self,
+        *,
+        inputs: typing.Sequence[WorkflowRequestInputRequest],
+        expand_meta: typing.Optional[WorkflowExpandMetaRequest] = OMIT,
+        workflow_deployment_id: typing.Optional[str] = OMIT,
+        workflow_deployment_name: 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,
+    ) -> AsyncHttpResponse[ExecuteWorkflowResponse]:
+        """
+        Executes a deployed Workflow and returns its outputs.
+
+        Parameters
+        ----------
+        inputs : typing.Sequence[WorkflowRequestInputRequest]
+            The list of inputs defined in the Workflow's Deployment with their corresponding values.
+
+        expand_meta : typing.Optional[WorkflowExpandMetaRequest]
+            An optionally specified configuration used to opt in to including additional metadata about this workflow execution in the API response. Corresponding values will be returned under the `execution_meta` key within NODE events in the response stream.
+
+        workflow_deployment_id : typing.Optional[str]
+            The ID of the Workflow Deployment. Must provide either this or workflow_deployment_name.
+
+        workflow_deployment_name : typing.Optional[str]
+            The name of the Workflow Deployment. Must provide either this or workflow_deployment_id.
+
+        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 initial State loading.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        AsyncHttpResponse[ExecuteWorkflowResponse]
+
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "v1/execute-workflow",
+            base_url=self._client_wrapper.get_environment().predict,
+            method="POST",
+            json={
+                "inputs": convert_and_respect_annotation_metadata(
+                    object_=inputs, annotation=typing.Sequence[WorkflowRequestInputRequest], direction="write"
+                ),
+                "expand_meta": convert_and_respect_annotation_metadata(
+                    object_=expand_meta, annotation=typing.Optional[WorkflowExpandMetaRequest], direction="write"
+                ),
+                "workflow_deployment_id": workflow_deployment_id,
+                "workflow_deployment_name": workflow_deployment_name,
+                "release_tag": release_tag,
+                "external_id": external_id,
+                "metadata": metadata,
+                "previous_execution_id": previous_execution_id,
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                _data = typing.cast(
+                    ExecuteWorkflowResponse,
+                    parse_obj_as(
+                        type_=ExecuteWorkflowResponse,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+                return AsyncHttpResponse(response=_response, data=_data)
+            if _response.status_code == 400:
+                raise BadRequestError(
+                    headers=dict(_response.headers),
+                    body=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(
+                    headers=dict(_response.headers),
+                    body=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(
+                    headers=dict(_response.headers),
+                    body=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, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+    async def execute_workflow_async(
+        self,
+        *,
+        inputs: typing.Sequence[WorkflowRequestInputRequest],
+        workflow_deployment_id: typing.Optional[str] = OMIT,
+        workflow_deployment_name: typing.Optional[str] = OMIT,
+        release_tag: typing.Optional[str] = OMIT,
+        external_id: typing.Optional[str] = OMIT,
+        previous_execution_id: typing.Optional[str] = OMIT,
+        metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> AsyncHttpResponse[ExecuteWorkflowAsyncResponse]:
+        """
+        Executes a deployed Workflow asynchronously and returns the execution ID.
+
+        Parameters
+        ----------
+        inputs : typing.Sequence[WorkflowRequestInputRequest]
+            The list of inputs defined in the Workflow's Deployment with their corresponding values.
+
+        workflow_deployment_id : typing.Optional[str]
+            The ID of the Workflow Deployment. Must provide either this or workflow_deployment_name.
+
+        workflow_deployment_name : typing.Optional[str]
+            The name of the Workflow Deployment. Must provide either this or workflow_deployment_id.
+
+        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.
+
+        previous_execution_id : typing.Optional[str]
+            The ID of a previous Workflow Execution to reference for initial State loading.
+
+        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.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        AsyncHttpResponse[ExecuteWorkflowAsyncResponse]
+
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "v1/execute-workflow-async",
+            base_url=self._client_wrapper.get_environment().predict,
+            method="POST",
+            json={
+                "inputs": convert_and_respect_annotation_metadata(
+                    object_=inputs, annotation=typing.Sequence[WorkflowRequestInputRequest], direction="write"
+                ),
+                "workflow_deployment_id": workflow_deployment_id,
+                "workflow_deployment_name": workflow_deployment_name,
+                "release_tag": release_tag,
+                "external_id": external_id,
+                "previous_execution_id": previous_execution_id,
+                "metadata": metadata,
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                _data = typing.cast(
+                    ExecuteWorkflowAsyncResponse,
+                    parse_obj_as(
+                        type_=ExecuteWorkflowAsyncResponse,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+                return AsyncHttpResponse(response=_response, data=_data)
+            if _response.status_code == 400:
+                raise BadRequestError(
+                    headers=dict(_response.headers),
+                    body=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(
+                    headers=dict(_response.headers),
+                    body=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(
+                    headers=dict(_response.headers),
+                    body=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, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+    @contextlib.asynccontextmanager
+    async def execute_workflow_stream(
+        self,
+        *,
+        inputs: typing.Sequence[WorkflowRequestInputRequest],
+        expand_meta: typing.Optional[WorkflowExpandMetaRequest] = OMIT,
+        workflow_deployment_id: typing.Optional[str] = OMIT,
+        workflow_deployment_name: typing.Optional[str] = OMIT,
+        release_tag: typing.Optional[str] = OMIT,
+        external_id: typing.Optional[str] = OMIT,
+        event_types: typing.Optional[typing.Sequence[WorkflowExecutionEventType]] = 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[AsyncHttpResponse[typing.AsyncIterator[WorkflowStreamEvent]]]:
+        """
+        Executes a deployed Workflow and streams back its results.
+
+        Parameters
+        ----------
+        inputs : typing.Sequence[WorkflowRequestInputRequest]
+            The list of inputs defined in the Workflow's Deployment with their corresponding values.
+
+        expand_meta : typing.Optional[WorkflowExpandMetaRequest]
+            An optionally specified configuration used to opt in to including additional metadata about this workflow execution in the API response. Corresponding values will be returned under the `execution_meta` key within NODE events in the response stream.
+
+        workflow_deployment_id : typing.Optional[str]
+            The ID of the Workflow Deployment. Must provide either this or workflow_deployment_name.
+
+        workflow_deployment_name : typing.Optional[str]
+            The name of the Workflow Deployment. Must provide either this or workflow_deployment_id.
+
+        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.
+
+        event_types : typing.Optional[typing.Sequence[WorkflowExecutionEventType]]
+            Optionally specify which events you want to receive. Defaults to only WORKFLOW events. Note that the schema of non-WORKFLOW events is unstable and should be used with caution.
+
+        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 initial State loading.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Yields
+        ------
+        typing.AsyncIterator[AsyncHttpResponse[typing.AsyncIterator[WorkflowStreamEvent]]]
+
+        """
+        async with self._client_wrapper.httpx_client.stream(
+            "v1/execute-workflow-stream",
+            base_url=self._client_wrapper.get_environment().predict,
+            method="POST",
+            json={
+                "inputs": convert_and_respect_annotation_metadata(
+                    object_=inputs, annotation=typing.Sequence[WorkflowRequestInputRequest], direction="write"
+                ),
+                "expand_meta": convert_and_respect_annotation_metadata(
+                    object_=expand_meta, annotation=typing.Optional[WorkflowExpandMetaRequest], direction="write"
+                ),
+                "workflow_deployment_id": workflow_deployment_id,
+                "workflow_deployment_name": workflow_deployment_name,
+                "release_tag": release_tag,
+                "external_id": external_id,
+                "event_types": event_types,
+                "metadata": metadata,
+                "previous_execution_id": previous_execution_id,
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        ) as _response:
+
+            async def _stream() -> AsyncHttpResponse[typing.AsyncIterator[WorkflowStreamEvent]]:
+                try:
+                    if 200 <= _response.status_code < 300:
+
+                        async def _iter():
+                            async for _text in _response.aiter_lines():
+                                try:
+                                    if len(_text) == 0:
+                                        continue
+                                    yield typing.cast(
+                                        WorkflowStreamEvent,
+                                        parse_obj_as(
+                                            type_=WorkflowStreamEvent,  # type: ignore
+                                            object_=json.loads(_text),
+                                        ),
+                                    )
+                                except Exception:
+                                    pass
+                            return
+
+                        return AsyncHttpResponse(response=_response, data=_iter())
+                    await _response.aread()
+                    if _response.status_code == 400:
+                        raise BadRequestError(
+                            headers=dict(_response.headers),
+                            body=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(
+                            headers=dict(_response.headers),
+                            body=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(
+                            headers=dict(_response.headers),
+                            body=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, headers=dict(_response.headers), body=_response.text
+                    )
+                raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+            yield await _stream()
+
+    async def generate(
+        self,
+        *,
+        requests: typing.Sequence[GenerateRequest],
+        deployment_id: typing.Optional[str] = OMIT,
+        deployment_name: typing.Optional[str] = OMIT,
+        options: typing.Optional[GenerateOptionsRequest] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> AsyncHttpResponse[GenerateResponse]:
+        """
+        Generate a completion using a previously defined deployment.
+
+        Important: This endpoint is DEPRECATED and has been superseded by
+        [execute-prompt](/api-reference/api-reference/execute-prompt).
+
+        Parameters
+        ----------
+        requests : typing.Sequence[GenerateRequest]
+            The generation request to make. Bulk requests are no longer supported, this field must be an array of length 1.
+
+        deployment_id : typing.Optional[str]
+            The ID of the deployment. Must provide either this or deployment_name.
+
+        deployment_name : typing.Optional[str]
+            The name of the deployment. Must provide either this or deployment_id.
+
+        options : typing.Optional[GenerateOptionsRequest]
+            Additional configuration that can be used to control what's included in the response.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        AsyncHttpResponse[GenerateResponse]
+
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "v1/generate",
+            base_url=self._client_wrapper.get_environment().predict,
+            method="POST",
+            json={
+                "deployment_id": deployment_id,
+                "deployment_name": deployment_name,
+                "requests": convert_and_respect_annotation_metadata(
+                    object_=requests, annotation=typing.Sequence[GenerateRequest], direction="write"
+                ),
+                "options": convert_and_respect_annotation_metadata(
+                    object_=options, annotation=typing.Optional[GenerateOptionsRequest], direction="write"
+                ),
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                _data = typing.cast(
+                    GenerateResponse,
+                    parse_obj_as(
+                        type_=GenerateResponse,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+                return AsyncHttpResponse(response=_response, data=_data)
+            if _response.status_code == 400:
+                raise BadRequestError(
+                    headers=dict(_response.headers),
+                    body=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(
+                    headers=dict(_response.headers),
+                    body=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(
+                    headers=dict(_response.headers),
+                    body=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(
+                    headers=dict(_response.headers),
+                    body=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, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+    @contextlib.asynccontextmanager
+    async def generate_stream(
+        self,
+        *,
+        requests: typing.Sequence[GenerateRequest],
+        deployment_id: typing.Optional[str] = OMIT,
+        deployment_name: typing.Optional[str] = OMIT,
+        options: typing.Optional[GenerateOptionsRequest] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> typing.AsyncIterator[AsyncHttpResponse[typing.AsyncIterator[GenerateStreamResponse]]]:
+        """
+        Generate a stream of completions using a previously defined deployment.
+
+        Important: This endpoint is DEPRECATED and has been superseded by
+        [execute-prompt-stream](/api-reference/api-reference/execute-prompt-stream).
+
+        Parameters
+        ----------
+        requests : typing.Sequence[GenerateRequest]
+            The generation request to make. Bulk requests are no longer supported, this field must be an array of length 1.
+
+        deployment_id : typing.Optional[str]
+            The ID of the deployment. Must provide either this or deployment_name.
+
+        deployment_name : typing.Optional[str]
+            The name of the deployment. Must provide either this or deployment_id.
+
+        options : typing.Optional[GenerateOptionsRequest]
+            Additional configuration that can be used to control what's included in the response.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Yields
+        ------
+        typing.AsyncIterator[AsyncHttpResponse[typing.AsyncIterator[GenerateStreamResponse]]]
+
+        """
+        async with self._client_wrapper.httpx_client.stream(
+            "v1/generate-stream",
+            base_url=self._client_wrapper.get_environment().predict,
+            method="POST",
+            json={
+                "deployment_id": deployment_id,
+                "deployment_name": deployment_name,
+                "requests": convert_and_respect_annotation_metadata(
+                    object_=requests, annotation=typing.Sequence[GenerateRequest], direction="write"
+                ),
+                "options": convert_and_respect_annotation_metadata(
+                    object_=options, annotation=typing.Optional[GenerateOptionsRequest], direction="write"
+                ),
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        ) as _response:
+
+            async def _stream() -> AsyncHttpResponse[typing.AsyncIterator[GenerateStreamResponse]]:
+                try:
+                    if 200 <= _response.status_code < 300:
+
+                        async def _iter():
+                            async for _text in _response.aiter_lines():
+                                try:
+                                    if len(_text) == 0:
+                                        continue
+                                    yield typing.cast(
+                                        GenerateStreamResponse,
+                                        parse_obj_as(
+                                            type_=GenerateStreamResponse,  # type: ignore
+                                            object_=json.loads(_text),
+                                        ),
+                                    )
+                                except Exception:
+                                    pass
+                            return
+
+                        return AsyncHttpResponse(response=_response, data=_iter())
+                    await _response.aread()
+                    if _response.status_code == 400:
+                        raise BadRequestError(
+                            headers=dict(_response.headers),
+                            body=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(
+                            headers=dict(_response.headers),
+                            body=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(
+                            headers=dict(_response.headers),
+                            body=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(
+                            headers=dict(_response.headers),
+                            body=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, headers=dict(_response.headers), body=_response.text
+                    )
+                raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+            yield await _stream()
+
+    async def search(
+        self,
+        *,
+        query: str,
+        index_id: typing.Optional[str] = OMIT,
+        index_name: typing.Optional[str] = OMIT,
+        options: typing.Optional[SearchRequestOptionsRequest] = OMIT,
+        document_index: typing.Optional[str] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> AsyncHttpResponse[SearchResponse]:
+        """
+        Perform a search against a document index.
+
+        Parameters
+        ----------
+        query : str
+            The query to search for.
+
+        index_id : typing.Optional[str]
+            The ID of the index to search against. Must provide either this, index_name or document_index.
+
+        index_name : typing.Optional[str]
+            The name of the index to search against. Must provide either this, index_id or document_index.
+
+        options : typing.Optional[SearchRequestOptionsRequest]
+            Configuration options for the search.
+
+        document_index : typing.Optional[str]
+            Either the index name or index ID to search against. Must provide either this, index_id or index_name.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        AsyncHttpResponse[SearchResponse]
+
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "v1/search",
+            base_url=self._client_wrapper.get_environment().predict,
+            method="POST",
+            json={
+                "index_id": index_id,
+                "index_name": index_name,
+                "query": query,
+                "options": convert_and_respect_annotation_metadata(
+                    object_=options, annotation=typing.Optional[SearchRequestOptionsRequest], direction="write"
+                ),
+                "document_index": document_index,
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                _data = typing.cast(
+                    SearchResponse,
+                    parse_obj_as(
+                        type_=SearchResponse,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+                return AsyncHttpResponse(response=_response, data=_data)
+            if _response.status_code == 400:
+                raise BadRequestError(
+                    headers=dict(_response.headers),
+                    body=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(
+                    headers=dict(_response.headers),
+                    body=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(
+                    headers=dict(_response.headers),
+                    body=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, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+    async def submit_completion_actuals(
+        self,
+        *,
+        actuals: typing.Sequence[SubmitCompletionActualRequest],
+        deployment_id: typing.Optional[str] = OMIT,
+        deployment_name: typing.Optional[str] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> AsyncHttpResponse[None]:
+        """
+        Used to submit feedback regarding the quality of previously generated completions.
+
+        Parameters
+        ----------
+        actuals : typing.Sequence[SubmitCompletionActualRequest]
+            Feedback regarding the quality of previously generated completions
+
+        deployment_id : typing.Optional[str]
+            The ID of the deployment. Must provide either this or deployment_name.
+
+        deployment_name : typing.Optional[str]
+            The name of the deployment. Must provide either this or deployment_id.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        AsyncHttpResponse[None]
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "v1/submit-completion-actuals",
+            base_url=self._client_wrapper.get_environment().predict,
+            method="POST",
+            json={
+                "deployment_id": deployment_id,
+                "deployment_name": deployment_name,
+                "actuals": convert_and_respect_annotation_metadata(
+                    object_=actuals, annotation=typing.Sequence[SubmitCompletionActualRequest], direction="write"
+                ),
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return AsyncHttpResponse(response=_response, data=None)
+            if _response.status_code == 400:
+                raise BadRequestError(
+                    headers=dict(_response.headers),
+                    body=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(
+                    headers=dict(_response.headers),
+                    body=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(
+                    headers=dict(_response.headers),
+                    body=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, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+    async def submit_workflow_execution_actuals(
+        self,
+        *,
+        actuals: typing.Sequence[SubmitWorkflowExecutionActualRequest],
+        execution_id: typing.Optional[str] = OMIT,
+        external_id: typing.Optional[str] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> AsyncHttpResponse[None]:
+        """
+            Used to submit feedback regarding the quality of previous workflow execution and its outputs.
+
+            **Note:** Uses a base url of `https://predict.vellum.ai`.
+
+        Parameters
+        ----------
+        actuals : typing.Sequence[SubmitWorkflowExecutionActualRequest]
+            Feedback regarding the quality of an output on a previously executed workflow.
+
+        execution_id : typing.Optional[str]
+            The Vellum-generated ID of a previously executed workflow. Must provide either this or external_id.
+
+        external_id : typing.Optional[str]
+            The external ID that was originally provided by when executing the workflow, if applicable, that you'd now like to submit actuals for. Must provide either this or execution_id.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        AsyncHttpResponse[None]
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "v1/submit-workflow-execution-actuals",
+            base_url=self._client_wrapper.get_environment().predict,
+            method="POST",
+            json={
+                "actuals": convert_and_respect_annotation_metadata(
+                    object_=actuals, annotation=typing.Sequence[SubmitWorkflowExecutionActualRequest], direction="write"
+                ),
+                "execution_id": execution_id,
+                "external_id": external_id,
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return AsyncHttpResponse(response=_response, data=None)
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)