vellum-ai 0.9.16__py3-none-any.whl → 0.9.16rc4__py3-none-any.whl

vellum/client/resources/deployments/client.py

@@ -0,0 +1,975 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+from ...core.client_wrapper import SyncClientWrapper
+from .types.deployments_list_request_status import DeploymentsListRequestStatus
+from ...core.request_options import RequestOptions
+from ...types.paginated_slim_deployment_read_list import PaginatedSlimDeploymentReadList
+from ...core.pydantic_utilities import parse_obj_as
+from json.decoder import JSONDecodeError
+from ...core.api_error import ApiError
+from ...types.deployment_read import DeploymentRead
+from ...core.jsonable_encoder import jsonable_encoder
+from .types.list_deployment_release_tags_request_source import ListDeploymentReleaseTagsRequestSource
+from ...types.paginated_deployment_release_tag_read_list import PaginatedDeploymentReleaseTagReadList
+from ...types.deployment_release_tag_read import DeploymentReleaseTagRead
+from ...types.prompt_deployment_input_request import PromptDeploymentInputRequest
+from ...types.compile_prompt_deployment_expand_meta_request import CompilePromptDeploymentExpandMetaRequest
+from ...types.deployment_provider_payload_response import DeploymentProviderPayloadResponse
+from ...core.serialization import convert_and_respect_annotation_metadata
+from ...errors.bad_request_error import BadRequestError
+from ...errors.forbidden_error import ForbiddenError
+from ...errors.not_found_error import NotFoundError
+from ...errors.internal_server_error import InternalServerError
+from ...core.client_wrapper import AsyncClientWrapper
+
+# this is used as the default value for optional parameters
+OMIT = typing.cast(typing.Any, ...)
+
+
+class DeploymentsClient:
+    def __init__(self, *, client_wrapper: SyncClientWrapper):
+        self._client_wrapper = client_wrapper
+
+    def list(
+        self,
+        *,
+        limit: typing.Optional[int] = None,
+        offset: typing.Optional[int] = None,
+        ordering: typing.Optional[str] = None,
+        status: typing.Optional[DeploymentsListRequestStatus] = None,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> PaginatedSlimDeploymentReadList:
+        """
+        Used to list all Prompt Deployments.
+
+        Parameters
+        ----------
+        limit : typing.Optional[int]
+            Number of results to return per page.
+
+        offset : typing.Optional[int]
+            The initial index from which to return the results.
+
+        ordering : typing.Optional[str]
+            Which field to use when ordering the results.
+
+        status : typing.Optional[DeploymentsListRequestStatus]
+            status
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        PaginatedSlimDeploymentReadList
+
+
+        Examples
+        --------
+        from vellum import Vellum
+
+        client = Vellum(
+            api_key="YOUR_API_KEY",
+        )
+        client.deployments.list()
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "v1/deployments",
+            base_url=self._client_wrapper.get_environment().default,
+            method="GET",
+            params={
+                "limit": limit,
+                "offset": offset,
+                "ordering": ordering,
+                "status": status,
+            },
+            request_options=request_options,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    PaginatedSlimDeploymentReadList,
+                    parse_obj_as(
+                        type_=PaginatedSlimDeploymentReadList,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    def retrieve(self, id: str, *, request_options: typing.Optional[RequestOptions] = None) -> DeploymentRead:
+        """
+        Used to retrieve a Prompt Deployment given its ID or name.
+
+        Parameters
+        ----------
+        id : str
+            Either the Deployment's ID or its unique name
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        DeploymentRead
+
+
+        Examples
+        --------
+        from vellum import Vellum
+
+        client = Vellum(
+            api_key="YOUR_API_KEY",
+        )
+        client.deployments.retrieve(
+            id="id",
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            f"v1/deployments/{jsonable_encoder(id)}",
+            base_url=self._client_wrapper.get_environment().default,
+            method="GET",
+            request_options=request_options,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    DeploymentRead,
+                    parse_obj_as(
+                        type_=DeploymentRead,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    def list_deployment_release_tags(
+        self,
+        id: str,
+        *,
+        limit: typing.Optional[int] = None,
+        offset: typing.Optional[int] = None,
+        ordering: typing.Optional[str] = None,
+        source: typing.Optional[ListDeploymentReleaseTagsRequestSource] = None,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> PaginatedDeploymentReleaseTagReadList:
+        """
+        List Release Tags associated with the specified Prompt Deployment
+
+        Parameters
+        ----------
+        id : str
+            Either the Prompt Deployment's ID or its unique name
+
+        limit : typing.Optional[int]
+            Number of results to return per page.
+
+        offset : typing.Optional[int]
+            The initial index from which to return the results.
+
+        ordering : typing.Optional[str]
+            Which field to use when ordering the results.
+
+        source : typing.Optional[ListDeploymentReleaseTagsRequestSource]
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        PaginatedDeploymentReleaseTagReadList
+
+
+        Examples
+        --------
+        from vellum import Vellum
+
+        client = Vellum(
+            api_key="YOUR_API_KEY",
+        )
+        client.deployments.list_deployment_release_tags(
+            id="id",
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            f"v1/deployments/{jsonable_encoder(id)}/release-tags",
+            base_url=self._client_wrapper.get_environment().default,
+            method="GET",
+            params={
+                "limit": limit,
+                "offset": offset,
+                "ordering": ordering,
+                "source": source,
+            },
+            request_options=request_options,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    PaginatedDeploymentReleaseTagReadList,
+                    parse_obj_as(
+                        type_=PaginatedDeploymentReleaseTagReadList,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    def retrieve_deployment_release_tag(
+        self, id: str, name: str, *, request_options: typing.Optional[RequestOptions] = None
+    ) -> DeploymentReleaseTagRead:
+        """
+        Retrieve a Deployment Release Tag by tag name, associated with a specified Deployment.
+
+        Parameters
+        ----------
+        id : str
+            A UUID string identifying this deployment.
+
+        name : str
+            The name of the Release Tag associated with this Deployment that you'd like to retrieve.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        DeploymentReleaseTagRead
+
+
+        Examples
+        --------
+        from vellum import Vellum
+
+        client = Vellum(
+            api_key="YOUR_API_KEY",
+        )
+        client.deployments.retrieve_deployment_release_tag(
+            id="id",
+            name="name",
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            f"v1/deployments/{jsonable_encoder(id)}/release-tags/{jsonable_encoder(name)}",
+            base_url=self._client_wrapper.get_environment().default,
+            method="GET",
+            request_options=request_options,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    DeploymentReleaseTagRead,
+                    parse_obj_as(
+                        type_=DeploymentReleaseTagRead,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    def update_deployment_release_tag(
+        self,
+        id: str,
+        name: str,
+        *,
+        history_item_id: typing.Optional[str] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> DeploymentReleaseTagRead:
+        """
+        Updates an existing Release Tag associated with the specified Prompt Deployment.
+
+        Parameters
+        ----------
+        id : str
+            A UUID string identifying this deployment.
+
+        name : str
+            The name of the Release Tag associated with this Deployment that you'd like to update.
+
+        history_item_id : typing.Optional[str]
+            The ID of the Deployment History Item to tag
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        DeploymentReleaseTagRead
+
+
+        Examples
+        --------
+        from vellum import Vellum
+
+        client = Vellum(
+            api_key="YOUR_API_KEY",
+        )
+        client.deployments.update_deployment_release_tag(
+            id="id",
+            name="name",
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            f"v1/deployments/{jsonable_encoder(id)}/release-tags/{jsonable_encoder(name)}",
+            base_url=self._client_wrapper.get_environment().default,
+            method="PATCH",
+            json={
+                "history_item_id": history_item_id,
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    DeploymentReleaseTagRead,
+                    parse_obj_as(
+                        type_=DeploymentReleaseTagRead,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    def retrieve_provider_payload(
+        self,
+        *,
+        inputs: typing.Sequence[PromptDeploymentInputRequest],
+        deployment_id: typing.Optional[str] = OMIT,
+        deployment_name: typing.Optional[str] = OMIT,
+        release_tag: typing.Optional[str] = OMIT,
+        expand_meta: typing.Optional[CompilePromptDeploymentExpandMetaRequest] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> DeploymentProviderPayloadResponse:
+        """
+        Given a set of input variable values, compile the exact payload that Vellum would send to the configured model provider
+        for execution if the execute-prompt endpoint had been invoked. Note that this endpoint does not actually execute the
+        prompt or make an API call to the model provider.
+
+        This endpoint is useful if you don't want to proxy LLM provider requests through Vellum and prefer to send them directly
+        to the provider yourself. Note that no guarantees are made on the format of this API's response schema, other than
+        that it will be a valid payload for the configured model provider. It's not recommended that you try to parse or
+        derive meaning from the response body and instead, should simply pass it directly to the model provider as is.
+
+        We encourage you to seek advise from Vellum Support before integrating with this API for production use.
+
+        Parameters
+        ----------
+        inputs : typing.Sequence[PromptDeploymentInputRequest]
+            The list of inputs defined in the Prompt's deployment with their corresponding values.
+
+        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.
+
+        release_tag : typing.Optional[str]
+            Optionally specify a release tag if you want to pin to a specific release of the Workflow Deployment
+
+        expand_meta : typing.Optional[CompilePromptDeploymentExpandMetaRequest]
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        DeploymentProviderPayloadResponse
+
+
+        Examples
+        --------
+        from vellum import StringInputRequest, Vellum
+
+        client = Vellum(
+            api_key="YOUR_API_KEY",
+        )
+        client.deployments.retrieve_provider_payload(
+            inputs=[
+                StringInputRequest(
+                    name="name",
+                    value="value",
+                )
+            ],
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "v1/deployments/provider-payload",
+            base_url=self._client_wrapper.get_environment().default,
+            method="POST",
+            json={
+                "deployment_id": deployment_id,
+                "deployment_name": deployment_name,
+                "inputs": convert_and_respect_annotation_metadata(
+                    object_=inputs, annotation=typing.Sequence[PromptDeploymentInputRequest], direction="write"
+                ),
+                "release_tag": release_tag,
+                "expand_meta": convert_and_respect_annotation_metadata(
+                    object_=expand_meta, annotation=CompilePromptDeploymentExpandMetaRequest, direction="write"
+                ),
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    DeploymentProviderPayloadResponse,
+                    parse_obj_as(
+                        type_=DeploymentProviderPayloadResponse,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            if _response.status_code == 400:
+                raise BadRequestError(
+                    typing.cast(
+                        typing.Optional[typing.Any],
+                        parse_obj_as(
+                            type_=typing.Optional[typing.Any],  # type: ignore
+                            object_=_response.json(),
+                        ),
+                    )
+                )
+            if _response.status_code == 403:
+                raise ForbiddenError(
+                    typing.cast(
+                        typing.Optional[typing.Any],
+                        parse_obj_as(
+                            type_=typing.Optional[typing.Any],  # type: ignore
+                            object_=_response.json(),
+                        ),
+                    )
+                )
+            if _response.status_code == 404:
+                raise NotFoundError(
+                    typing.cast(
+                        typing.Optional[typing.Any],
+                        parse_obj_as(
+                            type_=typing.Optional[typing.Any],  # type: ignore
+                            object_=_response.json(),
+                        ),
+                    )
+                )
+            if _response.status_code == 500:
+                raise InternalServerError(
+                    typing.cast(
+                        typing.Optional[typing.Any],
+                        parse_obj_as(
+                            type_=typing.Optional[typing.Any],  # type: ignore
+                            object_=_response.json(),
+                        ),
+                    )
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+
+class AsyncDeploymentsClient:
+    def __init__(self, *, client_wrapper: AsyncClientWrapper):
+        self._client_wrapper = client_wrapper
+
+    async def list(
+        self,
+        *,
+        limit: typing.Optional[int] = None,
+        offset: typing.Optional[int] = None,
+        ordering: typing.Optional[str] = None,
+        status: typing.Optional[DeploymentsListRequestStatus] = None,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> PaginatedSlimDeploymentReadList:
+        """
+        Used to list all Prompt Deployments.
+
+        Parameters
+        ----------
+        limit : typing.Optional[int]
+            Number of results to return per page.
+
+        offset : typing.Optional[int]
+            The initial index from which to return the results.
+
+        ordering : typing.Optional[str]
+            Which field to use when ordering the results.
+
+        status : typing.Optional[DeploymentsListRequestStatus]
+            status
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        PaginatedSlimDeploymentReadList
+
+
+        Examples
+        --------
+        import asyncio
+
+        from vellum import AsyncVellum
+
+        client = AsyncVellum(
+            api_key="YOUR_API_KEY",
+        )
+
+
+        async def main() -> None:
+            await client.deployments.list()
+
+
+        asyncio.run(main())
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "v1/deployments",
+            base_url=self._client_wrapper.get_environment().default,
+            method="GET",
+            params={
+                "limit": limit,
+                "offset": offset,
+                "ordering": ordering,
+                "status": status,
+            },
+            request_options=request_options,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    PaginatedSlimDeploymentReadList,
+                    parse_obj_as(
+                        type_=PaginatedSlimDeploymentReadList,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    async def retrieve(self, id: str, *, request_options: typing.Optional[RequestOptions] = None) -> DeploymentRead:
+        """
+        Used to retrieve a Prompt Deployment given its ID or name.
+
+        Parameters
+        ----------
+        id : str
+            Either the Deployment's ID or its unique name
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        DeploymentRead
+
+
+        Examples
+        --------
+        import asyncio
+
+        from vellum import AsyncVellum
+
+        client = AsyncVellum(
+            api_key="YOUR_API_KEY",
+        )
+
+
+        async def main() -> None:
+            await client.deployments.retrieve(
+                id="id",
+            )
+
+
+        asyncio.run(main())
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            f"v1/deployments/{jsonable_encoder(id)}",
+            base_url=self._client_wrapper.get_environment().default,
+            method="GET",
+            request_options=request_options,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    DeploymentRead,
+                    parse_obj_as(
+                        type_=DeploymentRead,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    async def list_deployment_release_tags(
+        self,
+        id: str,
+        *,
+        limit: typing.Optional[int] = None,
+        offset: typing.Optional[int] = None,
+        ordering: typing.Optional[str] = None,
+        source: typing.Optional[ListDeploymentReleaseTagsRequestSource] = None,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> PaginatedDeploymentReleaseTagReadList:
+        """
+        List Release Tags associated with the specified Prompt Deployment
+
+        Parameters
+        ----------
+        id : str
+            Either the Prompt Deployment's ID or its unique name
+
+        limit : typing.Optional[int]
+            Number of results to return per page.
+
+        offset : typing.Optional[int]
+            The initial index from which to return the results.
+
+        ordering : typing.Optional[str]
+            Which field to use when ordering the results.
+
+        source : typing.Optional[ListDeploymentReleaseTagsRequestSource]
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        PaginatedDeploymentReleaseTagReadList
+
+
+        Examples
+        --------
+        import asyncio
+
+        from vellum import AsyncVellum
+
+        client = AsyncVellum(
+            api_key="YOUR_API_KEY",
+        )
+
+
+        async def main() -> None:
+            await client.deployments.list_deployment_release_tags(
+                id="id",
+            )
+
+
+        asyncio.run(main())
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            f"v1/deployments/{jsonable_encoder(id)}/release-tags",
+            base_url=self._client_wrapper.get_environment().default,
+            method="GET",
+            params={
+                "limit": limit,
+                "offset": offset,
+                "ordering": ordering,
+                "source": source,
+            },
+            request_options=request_options,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    PaginatedDeploymentReleaseTagReadList,
+                    parse_obj_as(
+                        type_=PaginatedDeploymentReleaseTagReadList,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    async def retrieve_deployment_release_tag(
+        self, id: str, name: str, *, request_options: typing.Optional[RequestOptions] = None
+    ) -> DeploymentReleaseTagRead:
+        """
+        Retrieve a Deployment Release Tag by tag name, associated with a specified Deployment.
+
+        Parameters
+        ----------
+        id : str
+            A UUID string identifying this deployment.
+
+        name : str
+            The name of the Release Tag associated with this Deployment that you'd like to retrieve.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        DeploymentReleaseTagRead
+
+
+        Examples
+        --------
+        import asyncio
+
+        from vellum import AsyncVellum
+
+        client = AsyncVellum(
+            api_key="YOUR_API_KEY",
+        )
+
+
+        async def main() -> None:
+            await client.deployments.retrieve_deployment_release_tag(
+                id="id",
+                name="name",
+            )
+
+
+        asyncio.run(main())
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            f"v1/deployments/{jsonable_encoder(id)}/release-tags/{jsonable_encoder(name)}",
+            base_url=self._client_wrapper.get_environment().default,
+            method="GET",
+            request_options=request_options,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    DeploymentReleaseTagRead,
+                    parse_obj_as(
+                        type_=DeploymentReleaseTagRead,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    async def update_deployment_release_tag(
+        self,
+        id: str,
+        name: str,
+        *,
+        history_item_id: typing.Optional[str] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> DeploymentReleaseTagRead:
+        """
+        Updates an existing Release Tag associated with the specified Prompt Deployment.
+
+        Parameters
+        ----------
+        id : str
+            A UUID string identifying this deployment.
+
+        name : str
+            The name of the Release Tag associated with this Deployment that you'd like to update.
+
+        history_item_id : typing.Optional[str]
+            The ID of the Deployment History Item to tag
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        DeploymentReleaseTagRead
+
+
+        Examples
+        --------
+        import asyncio
+
+        from vellum import AsyncVellum
+
+        client = AsyncVellum(
+            api_key="YOUR_API_KEY",
+        )
+
+
+        async def main() -> None:
+            await client.deployments.update_deployment_release_tag(
+                id="id",
+                name="name",
+            )
+
+
+        asyncio.run(main())
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            f"v1/deployments/{jsonable_encoder(id)}/release-tags/{jsonable_encoder(name)}",
+            base_url=self._client_wrapper.get_environment().default,
+            method="PATCH",
+            json={
+                "history_item_id": history_item_id,
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    DeploymentReleaseTagRead,
+                    parse_obj_as(
+                        type_=DeploymentReleaseTagRead,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    async def retrieve_provider_payload(
+        self,
+        *,
+        inputs: typing.Sequence[PromptDeploymentInputRequest],
+        deployment_id: typing.Optional[str] = OMIT,
+        deployment_name: typing.Optional[str] = OMIT,
+        release_tag: typing.Optional[str] = OMIT,
+        expand_meta: typing.Optional[CompilePromptDeploymentExpandMetaRequest] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> DeploymentProviderPayloadResponse:
+        """
+        Given a set of input variable values, compile the exact payload that Vellum would send to the configured model provider
+        for execution if the execute-prompt endpoint had been invoked. Note that this endpoint does not actually execute the
+        prompt or make an API call to the model provider.
+
+        This endpoint is useful if you don't want to proxy LLM provider requests through Vellum and prefer to send them directly
+        to the provider yourself. Note that no guarantees are made on the format of this API's response schema, other than
+        that it will be a valid payload for the configured model provider. It's not recommended that you try to parse or
+        derive meaning from the response body and instead, should simply pass it directly to the model provider as is.
+
+        We encourage you to seek advise from Vellum Support before integrating with this API for production use.
+
+        Parameters
+        ----------
+        inputs : typing.Sequence[PromptDeploymentInputRequest]
+            The list of inputs defined in the Prompt's deployment with their corresponding values.
+
+        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.
+
+        release_tag : typing.Optional[str]
+            Optionally specify a release tag if you want to pin to a specific release of the Workflow Deployment
+
+        expand_meta : typing.Optional[CompilePromptDeploymentExpandMetaRequest]
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        DeploymentProviderPayloadResponse
+
+
+        Examples
+        --------
+        import asyncio
+
+        from vellum import AsyncVellum, StringInputRequest
+
+        client = AsyncVellum(
+            api_key="YOUR_API_KEY",
+        )
+
+
+        async def main() -> None:
+            await client.deployments.retrieve_provider_payload(
+                inputs=[
+                    StringInputRequest(
+                        name="name",
+                        value="value",
+                    )
+                ],
+            )
+
+
+        asyncio.run(main())
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "v1/deployments/provider-payload",
+            base_url=self._client_wrapper.get_environment().default,
+            method="POST",
+            json={
+                "deployment_id": deployment_id,
+                "deployment_name": deployment_name,
+                "inputs": convert_and_respect_annotation_metadata(
+                    object_=inputs, annotation=typing.Sequence[PromptDeploymentInputRequest], direction="write"
+                ),
+                "release_tag": release_tag,
+                "expand_meta": convert_and_respect_annotation_metadata(
+                    object_=expand_meta, annotation=CompilePromptDeploymentExpandMetaRequest, direction="write"
+                ),
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    DeploymentProviderPayloadResponse,
+                    parse_obj_as(
+                        type_=DeploymentProviderPayloadResponse,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            if _response.status_code == 400:
+                raise BadRequestError(
+                    typing.cast(
+                        typing.Optional[typing.Any],
+                        parse_obj_as(
+                            type_=typing.Optional[typing.Any],  # type: ignore
+                            object_=_response.json(),
+                        ),
+                    )
+                )
+            if _response.status_code == 403:
+                raise ForbiddenError(
+                    typing.cast(
+                        typing.Optional[typing.Any],
+                        parse_obj_as(
+                            type_=typing.Optional[typing.Any],  # type: ignore
+                            object_=_response.json(),
+                        ),
+                    )
+                )
+            if _response.status_code == 404:
+                raise NotFoundError(
+                    typing.cast(
+                        typing.Optional[typing.Any],
+                        parse_obj_as(
+                            type_=typing.Optional[typing.Any],  # type: ignore
+                            object_=_response.json(),
+                        ),
+                    )
+                )
+            if _response.status_code == 500:
+                raise InternalServerError(
+                    typing.cast(
+                        typing.Optional[typing.Any],
+                        parse_obj_as(
+                            type_=typing.Optional[typing.Any],  # type: ignore
+                            object_=_response.json(),
+                        ),
+                    )
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)