vellum-ai 0.7.2__py3-none-any.whl → 0.7.5__py3-none-any.whl

vellum/resources/deployments/client.py

@@ -1,19 +1,18 @@
 # This file was auto-generated by Fern from our API Definition.
 
 import typing
-import urllib.parse
 from json.decoder import JSONDecodeError
 
 from ...core.api_error import ApiError
 from ...core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
 from ...core.jsonable_encoder import jsonable_encoder
 from ...core.pydantic_utilities import pydantic_v1
-from ...core.remove_none_from_dict import remove_none_from_dict
 from ...core.request_options import RequestOptions
 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.compile_prompt_deployment_expand_meta_request import CompilePromptDeploymentExpandMetaRequest
 from ...types.deployment_provider_payload_response import DeploymentProviderPayloadResponse
 from ...types.deployment_read import DeploymentRead
 from ...types.deployment_release_tag_read import DeploymentReleaseTagRead
@@ -39,17 +38,32 @@ class DeploymentsClient:
         request_options: typing.Optional[RequestOptions] = None,
     ) -> PaginatedSlimDeploymentReadList:
         """
-        Parameters:
-            - limit: typing.Optional[int]. Number of results to return per page.
+        Used to list all Prompt Deployments.
 
-            - offset: typing.Optional[int]. The initial index from which to return the results.
+        Parameters
+        ----------
+        limit : typing.Optional[int]
+            Number of results to return per page.
 
-            - ordering: typing.Optional[str]. Which field to use when ordering the results.
+        offset : typing.Optional[int]
+            The initial index from which to return the results.
 
-            - status: typing.Optional[DeploymentsListRequestStatus]. status
+        ordering : typing.Optional[str]
+            Which field to use when ordering the results.
 
-            - request_options: typing.Optional[RequestOptions]. Request-specific configuration.
-        ---
+        status : typing.Optional[DeploymentsListRequestStatus]
+            status
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        PaginatedSlimDeploymentReadList
+
+
+        Examples
+        --------
         from vellum.client import Vellum
 
         client = Vellum(
@@ -58,40 +72,15 @@ class DeploymentsClient:
         client.deployments.list()
         """
         _response = self._client_wrapper.httpx_client.request(
+            "v1/deployments",
+            base_url=self._client_wrapper.get_environment().default,
             method="GET",
-            url=urllib.parse.urljoin(f"{self._client_wrapper.get_environment().default}/", "v1/deployments"),
-            params=jsonable_encoder(
-                remove_none_from_dict(
-                    {
-                        "limit": limit,
-                        "offset": offset,
-                        "ordering": ordering,
-                        "status": status,
-                        **(
-                            request_options.get("additional_query_parameters", {})
-                            if request_options is not None
-                            else {}
-                        ),
-                    }
-                )
-            ),
-            headers=jsonable_encoder(
-                remove_none_from_dict(
-                    {
-                        **self._client_wrapper.get_headers(),
-                        **(request_options.get("additional_headers", {}) if request_options is not None else {}),
-                    }
-                )
-            ),
-            timeout=request_options.get("timeout_in_seconds")
-            if request_options is not None and request_options.get("timeout_in_seconds") is not None
-            else self._client_wrapper.get_timeout(),
-            retries=0,
-            max_retries=request_options.get("max_retries") if request_options is not None else 0,  # type: ignore
+            params={"limit": limit, "offset": offset, "ordering": ordering, "status": status},
+            request_options=request_options,
         )
-        if 200 <= _response.status_code < 300:
-            return pydantic_v1.parse_obj_as(PaginatedSlimDeploymentReadList, _response.json())  # type: ignore
         try:
+            if 200 <= _response.status_code < 300:
+                return pydantic_v1.parse_obj_as(PaginatedSlimDeploymentReadList, _response.json())  # type: ignore
             _response_json = _response.json()
         except JSONDecodeError:
             raise ApiError(status_code=_response.status_code, body=_response.text)
@@ -99,13 +88,23 @@ class DeploymentsClient:
 
     def retrieve(self, id: str, *, request_options: typing.Optional[RequestOptions] = None) -> DeploymentRead:
         """
-        Used to retrieve a deployment given its ID or name.
+        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.
 
-        Parameters:
-            - id: str. Either the Deployment's ID or its unique name
+        Returns
+        -------
+        DeploymentRead
 
-            - request_options: typing.Optional[RequestOptions]. Request-specific configuration.
-        ---
+
+        Examples
+        --------
         from vellum.client import Vellum
 
         client = Vellum(
@@ -116,30 +115,14 @@ class DeploymentsClient:
         )
         """
         _response = self._client_wrapper.httpx_client.request(
+            f"v1/deployments/{jsonable_encoder(id)}",
+            base_url=self._client_wrapper.get_environment().default,
             method="GET",
-            url=urllib.parse.urljoin(
-                f"{self._client_wrapper.get_environment().default}/", f"v1/deployments/{jsonable_encoder(id)}"
-            ),
-            params=jsonable_encoder(
-                request_options.get("additional_query_parameters") if request_options is not None else None
-            ),
-            headers=jsonable_encoder(
-                remove_none_from_dict(
-                    {
-                        **self._client_wrapper.get_headers(),
-                        **(request_options.get("additional_headers", {}) if request_options is not None else {}),
-                    }
-                )
-            ),
-            timeout=request_options.get("timeout_in_seconds")
-            if request_options is not None and request_options.get("timeout_in_seconds") is not None
-            else self._client_wrapper.get_timeout(),
-            retries=0,
-            max_retries=request_options.get("max_retries") if request_options is not None else 0,  # type: ignore
+            request_options=request_options,
         )
-        if 200 <= _response.status_code < 300:
-            return pydantic_v1.parse_obj_as(DeploymentRead, _response.json())  # type: ignore
         try:
+            if 200 <= _response.status_code < 300:
+                return pydantic_v1.parse_obj_as(DeploymentRead, _response.json())  # type: ignore
             _response_json = _response.json()
         except JSONDecodeError:
             raise ApiError(status_code=_response.status_code, body=_response.text)
@@ -151,13 +134,24 @@ class DeploymentsClient:
         """
         Retrieve a Deployment Release Tag by tag name, associated with a specified Deployment.
 
-        Parameters:
-            - id: str. A UUID string identifying this 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.
 
-            - name: str. The name of the Release Tag associated with this Deployment that you'd like to retrieve.
+        Returns
+        -------
+        DeploymentReleaseTagRead
 
-            - request_options: typing.Optional[RequestOptions]. Request-specific configuration.
-        ---
+
+        Examples
+        --------
         from vellum.client import Vellum
 
         client = Vellum(
@@ -169,31 +163,14 @@ class DeploymentsClient:
         )
         """
         _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",
-            url=urllib.parse.urljoin(
-                f"{self._client_wrapper.get_environment().default}/",
-                f"v1/deployments/{jsonable_encoder(id)}/release-tags/{jsonable_encoder(name)}",
-            ),
-            params=jsonable_encoder(
-                request_options.get("additional_query_parameters") if request_options is not None else None
-            ),
-            headers=jsonable_encoder(
-                remove_none_from_dict(
-                    {
-                        **self._client_wrapper.get_headers(),
-                        **(request_options.get("additional_headers", {}) if request_options is not None else {}),
-                    }
-                )
-            ),
-            timeout=request_options.get("timeout_in_seconds")
-            if request_options is not None and request_options.get("timeout_in_seconds") is not None
-            else self._client_wrapper.get_timeout(),
-            retries=0,
-            max_retries=request_options.get("max_retries") if request_options is not None else 0,  # type: ignore
+            request_options=request_options,
         )
-        if 200 <= _response.status_code < 300:
-            return pydantic_v1.parse_obj_as(DeploymentReleaseTagRead, _response.json())  # type: ignore
         try:
+            if 200 <= _response.status_code < 300:
+                return pydantic_v1.parse_obj_as(DeploymentReleaseTagRead, _response.json())  # type: ignore
             _response_json = _response.json()
         except JSONDecodeError:
             raise ApiError(status_code=_response.status_code, body=_response.text)
@@ -210,15 +187,27 @@ class DeploymentsClient:
         """
         Updates an existing Release Tag associated with the specified Deployment.
 
-        Parameters:
-            - id: str. A UUID string identifying this 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.
 
-            - 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
 
-            - history_item_id: typing.Optional[str]. The ID of the Deployment History Item to tag
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
 
-            - request_options: typing.Optional[RequestOptions]. Request-specific configuration.
-        ---
+        Returns
+        -------
+        DeploymentReleaseTagRead
+
+
+        Examples
+        --------
         from vellum.client import Vellum
 
         client = Vellum(
@@ -229,41 +218,17 @@ class DeploymentsClient:
             name="name",
         )
         """
-        _request: typing.Dict[str, typing.Any] = {}
-        if history_item_id is not OMIT:
-            _request["history_item_id"] = history_item_id
         _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",
-            url=urllib.parse.urljoin(
-                f"{self._client_wrapper.get_environment().default}/",
-                f"v1/deployments/{jsonable_encoder(id)}/release-tags/{jsonable_encoder(name)}",
-            ),
-            params=jsonable_encoder(
-                request_options.get("additional_query_parameters") if request_options is not None else None
-            ),
-            json=jsonable_encoder(_request)
-            if request_options is None or request_options.get("additional_body_parameters") is None
-            else {
-                **jsonable_encoder(_request),
-                **(jsonable_encoder(remove_none_from_dict(request_options.get("additional_body_parameters", {})))),
-            },
-            headers=jsonable_encoder(
-                remove_none_from_dict(
-                    {
-                        **self._client_wrapper.get_headers(),
-                        **(request_options.get("additional_headers", {}) if request_options is not None else {}),
-                    }
-                )
-            ),
-            timeout=request_options.get("timeout_in_seconds")
-            if request_options is not None and request_options.get("timeout_in_seconds") is not None
-            else self._client_wrapper.get_timeout(),
-            retries=0,
-            max_retries=request_options.get("max_retries") if request_options is not None else 0,  # type: ignore
+            json={"history_item_id": history_item_id},
+            request_options=request_options,
+            omit=OMIT,
         )
-        if 200 <= _response.status_code < 300:
-            return pydantic_v1.parse_obj_as(DeploymentReleaseTagRead, _response.json())  # type: ignore
         try:
+            if 200 <= _response.status_code < 300:
+                return pydantic_v1.parse_obj_as(DeploymentReleaseTagRead, _response.json())  # type: ignore
             _response_json = _response.json()
         except JSONDecodeError:
             raise ApiError(status_code=_response.status_code, body=_response.text)
@@ -272,24 +237,51 @@ class DeploymentsClient:
     def retrieve_provider_payload(
         self,
         *,
+        inputs: typing.Sequence[PromptDeploymentInputRequest],
         deployment_id: typing.Optional[str] = OMIT,
         deployment_name: typing.Optional[str] = OMIT,
-        inputs: typing.Sequence[PromptDeploymentInputRequest],
         release_tag: typing.Optional[str] = OMIT,
+        expand_meta: typing.Optional[CompilePromptDeploymentExpandMetaRequest] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> DeploymentProviderPayloadResponse:
         """
-        Parameters:
-            - deployment_id: typing.Optional[str]. The ID of the deployment. Must provide either this or deployment_name.
+        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.
 
-            - 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
 
-            - inputs: typing.Sequence[PromptDeploymentInputRequest]. The list of inputs defined in the Prompt's deployment with their corresponding values.
+        expand_meta : typing.Optional[CompilePromptDeploymentExpandMetaRequest]
 
-            - release_tag: typing.Optional[str]. Optionally specify a release tag if you want to pin to a specific release of the Workflow Deployment
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
 
-            - request_options: typing.Optional[RequestOptions]. Request-specific configuration.
-        ---
+        Returns
+        -------
+        DeploymentProviderPayloadResponse
+
+
+        Examples
+        --------
         from vellum.client import Vellum
 
         client = Vellum(
@@ -299,52 +291,31 @@ class DeploymentsClient:
             inputs=[],
         )
         """
-        _request: typing.Dict[str, typing.Any] = {"inputs": inputs}
-        if deployment_id is not OMIT:
-            _request["deployment_id"] = deployment_id
-        if deployment_name is not OMIT:
-            _request["deployment_name"] = deployment_name
-        if release_tag is not OMIT:
-            _request["release_tag"] = release_tag
         _response = self._client_wrapper.httpx_client.request(
+            "v1/deployments/provider-payload",
+            base_url=self._client_wrapper.get_environment().default,
             method="POST",
-            url=urllib.parse.urljoin(
-                f"{self._client_wrapper.get_environment().default}/", "v1/deployments/provider-payload"
-            ),
-            params=jsonable_encoder(
-                request_options.get("additional_query_parameters") if request_options is not None else None
-            ),
-            json=jsonable_encoder(_request)
-            if request_options is None or request_options.get("additional_body_parameters") is None
-            else {
-                **jsonable_encoder(_request),
-                **(jsonable_encoder(remove_none_from_dict(request_options.get("additional_body_parameters", {})))),
+            json={
+                "deployment_id": deployment_id,
+                "deployment_name": deployment_name,
+                "inputs": inputs,
+                "release_tag": release_tag,
+                "expand_meta": expand_meta,
             },
-            headers=jsonable_encoder(
-                remove_none_from_dict(
-                    {
-                        **self._client_wrapper.get_headers(),
-                        **(request_options.get("additional_headers", {}) if request_options is not None else {}),
-                    }
-                )
-            ),
-            timeout=request_options.get("timeout_in_seconds")
-            if request_options is not None and request_options.get("timeout_in_seconds") is not None
-            else self._client_wrapper.get_timeout(),
-            retries=0,
-            max_retries=request_options.get("max_retries") if request_options is not None else 0,  # type: ignore
+            request_options=request_options,
+            omit=OMIT,
         )
-        if 200 <= _response.status_code < 300:
-            return pydantic_v1.parse_obj_as(DeploymentProviderPayloadResponse, _response.json())  # type: ignore
-        if _response.status_code == 400:
-            raise BadRequestError(pydantic_v1.parse_obj_as(typing.Any, _response.json()))  # type: ignore
-        if _response.status_code == 403:
-            raise ForbiddenError(pydantic_v1.parse_obj_as(typing.Any, _response.json()))  # type: ignore
-        if _response.status_code == 404:
-            raise NotFoundError(pydantic_v1.parse_obj_as(typing.Any, _response.json()))  # type: ignore
-        if _response.status_code == 500:
-            raise InternalServerError(pydantic_v1.parse_obj_as(typing.Any, _response.json()))  # type: ignore
         try:
+            if 200 <= _response.status_code < 300:
+                return pydantic_v1.parse_obj_as(DeploymentProviderPayloadResponse, _response.json())  # type: ignore
+            if _response.status_code == 400:
+                raise BadRequestError(pydantic_v1.parse_obj_as(typing.Any, _response.json()))  # type: ignore
+            if _response.status_code == 403:
+                raise ForbiddenError(pydantic_v1.parse_obj_as(typing.Any, _response.json()))  # type: ignore
+            if _response.status_code == 404:
+                raise NotFoundError(pydantic_v1.parse_obj_as(typing.Any, _response.json()))  # type: ignore
+            if _response.status_code == 500:
+                raise InternalServerError(pydantic_v1.parse_obj_as(typing.Any, _response.json()))  # type: ignore
             _response_json = _response.json()
         except JSONDecodeError:
             raise ApiError(status_code=_response.status_code, body=_response.text)
@@ -365,59 +336,57 @@ class AsyncDeploymentsClient:
         request_options: typing.Optional[RequestOptions] = None,
     ) -> PaginatedSlimDeploymentReadList:
         """
-        Parameters:
-            - limit: typing.Optional[int]. Number of results to return per page.
+        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.
 
-            - offset: typing.Optional[int]. The initial index from which to return the results.
+        status : typing.Optional[DeploymentsListRequestStatus]
+            status
 
-            - ordering: typing.Optional[str]. Which field to use when ordering the results.
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
 
-            - status: typing.Optional[DeploymentsListRequestStatus]. status
+        Returns
+        -------
+        PaginatedSlimDeploymentReadList
+
+
+        Examples
+        --------
+        import asyncio
 
-            - request_options: typing.Optional[RequestOptions]. Request-specific configuration.
-        ---
         from vellum.client import AsyncVellum
 
         client = AsyncVellum(
             api_key="YOUR_API_KEY",
         )
-        await client.deployments.list()
+
+
+        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",
-            url=urllib.parse.urljoin(f"{self._client_wrapper.get_environment().default}/", "v1/deployments"),
-            params=jsonable_encoder(
-                remove_none_from_dict(
-                    {
-                        "limit": limit,
-                        "offset": offset,
-                        "ordering": ordering,
-                        "status": status,
-                        **(
-                            request_options.get("additional_query_parameters", {})
-                            if request_options is not None
-                            else {}
-                        ),
-                    }
-                )
-            ),
-            headers=jsonable_encoder(
-                remove_none_from_dict(
-                    {
-                        **self._client_wrapper.get_headers(),
-                        **(request_options.get("additional_headers", {}) if request_options is not None else {}),
-                    }
-                )
-            ),
-            timeout=request_options.get("timeout_in_seconds")
-            if request_options is not None and request_options.get("timeout_in_seconds") is not None
-            else self._client_wrapper.get_timeout(),
-            retries=0,
-            max_retries=request_options.get("max_retries") if request_options is not None else 0,  # type: ignore
+            params={"limit": limit, "offset": offset, "ordering": ordering, "status": status},
+            request_options=request_options,
         )
-        if 200 <= _response.status_code < 300:
-            return pydantic_v1.parse_obj_as(PaginatedSlimDeploymentReadList, _response.json())  # type: ignore
         try:
+            if 200 <= _response.status_code < 300:
+                return pydantic_v1.parse_obj_as(PaginatedSlimDeploymentReadList, _response.json())  # type: ignore
             _response_json = _response.json()
         except JSONDecodeError:
             raise ApiError(status_code=_response.status_code, body=_response.text)
@@ -425,47 +394,49 @@ class AsyncDeploymentsClient:
 
     async def retrieve(self, id: str, *, request_options: typing.Optional[RequestOptions] = None) -> DeploymentRead:
         """
-        Used to retrieve a deployment given its ID or name.
+        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
+
 
-        Parameters:
-            - id: str. Either the Deployment's ID or its unique name
+        Examples
+        --------
+        import asyncio
 
-            - request_options: typing.Optional[RequestOptions]. Request-specific configuration.
-        ---
         from vellum.client import AsyncVellum
 
         client = AsyncVellum(
             api_key="YOUR_API_KEY",
         )
-        await client.deployments.retrieve(
-            id="id",
-        )
+
+
+        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",
-            url=urllib.parse.urljoin(
-                f"{self._client_wrapper.get_environment().default}/", f"v1/deployments/{jsonable_encoder(id)}"
-            ),
-            params=jsonable_encoder(
-                request_options.get("additional_query_parameters") if request_options is not None else None
-            ),
-            headers=jsonable_encoder(
-                remove_none_from_dict(
-                    {
-                        **self._client_wrapper.get_headers(),
-                        **(request_options.get("additional_headers", {}) if request_options is not None else {}),
-                    }
-                )
-            ),
-            timeout=request_options.get("timeout_in_seconds")
-            if request_options is not None and request_options.get("timeout_in_seconds") is not None
-            else self._client_wrapper.get_timeout(),
-            retries=0,
-            max_retries=request_options.get("max_retries") if request_options is not None else 0,  # type: ignore
+            request_options=request_options,
         )
-        if 200 <= _response.status_code < 300:
-            return pydantic_v1.parse_obj_as(DeploymentRead, _response.json())  # type: ignore
         try:
+            if 200 <= _response.status_code < 300:
+                return pydantic_v1.parse_obj_as(DeploymentRead, _response.json())  # type: ignore
             _response_json = _response.json()
         except JSONDecodeError:
             raise ApiError(status_code=_response.status_code, body=_response.text)
@@ -477,49 +448,51 @@ class AsyncDeploymentsClient:
         """
         Retrieve a Deployment Release Tag by tag name, associated with a specified Deployment.
 
-        Parameters:
-            - id: str. A UUID string identifying this 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
+
 
-            - name: str. The name of the Release Tag associated with this Deployment that you'd like to retrieve.
+        Examples
+        --------
+        import asyncio
 
-            - request_options: typing.Optional[RequestOptions]. Request-specific configuration.
-        ---
         from vellum.client import AsyncVellum
 
         client = AsyncVellum(
             api_key="YOUR_API_KEY",
         )
-        await client.deployments.retrieve_deployment_release_tag(
-            id="id",
-            name="name",
-        )
+
+
+        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",
-            url=urllib.parse.urljoin(
-                f"{self._client_wrapper.get_environment().default}/",
-                f"v1/deployments/{jsonable_encoder(id)}/release-tags/{jsonable_encoder(name)}",
-            ),
-            params=jsonable_encoder(
-                request_options.get("additional_query_parameters") if request_options is not None else None
-            ),
-            headers=jsonable_encoder(
-                remove_none_from_dict(
-                    {
-                        **self._client_wrapper.get_headers(),
-                        **(request_options.get("additional_headers", {}) if request_options is not None else {}),
-                    }
-                )
-            ),
-            timeout=request_options.get("timeout_in_seconds")
-            if request_options is not None and request_options.get("timeout_in_seconds") is not None
-            else self._client_wrapper.get_timeout(),
-            retries=0,
-            max_retries=request_options.get("max_retries") if request_options is not None else 0,  # type: ignore
+            request_options=request_options,
         )
-        if 200 <= _response.status_code < 300:
-            return pydantic_v1.parse_obj_as(DeploymentReleaseTagRead, _response.json())  # type: ignore
         try:
+            if 200 <= _response.status_code < 300:
+                return pydantic_v1.parse_obj_as(DeploymentReleaseTagRead, _response.json())  # type: ignore
             _response_json = _response.json()
         except JSONDecodeError:
             raise ApiError(status_code=_response.status_code, body=_response.text)
@@ -536,60 +509,56 @@ class AsyncDeploymentsClient:
         """
         Updates an existing Release Tag associated with the specified Deployment.
 
-        Parameters:
-            - id: str. A UUID string identifying this 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.
 
-            - name: str. The name of the Release Tag associated with this Deployment that you'd like to update.
+        Returns
+        -------
+        DeploymentReleaseTagRead
 
-            - history_item_id: typing.Optional[str]. The ID of the Deployment History Item to tag
 
-            - request_options: typing.Optional[RequestOptions]. Request-specific configuration.
-        ---
+        Examples
+        --------
+        import asyncio
+
         from vellum.client import AsyncVellum
 
         client = AsyncVellum(
             api_key="YOUR_API_KEY",
         )
-        await client.deployments.update_deployment_release_tag(
-            id="id",
-            name="name",
-        )
+
+
+        async def main() -> None:
+            await client.deployments.update_deployment_release_tag(
+                id="id",
+                name="name",
+            )
+
+
+        asyncio.run(main())
         """
-        _request: typing.Dict[str, typing.Any] = {}
-        if history_item_id is not OMIT:
-            _request["history_item_id"] = history_item_id
         _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",
-            url=urllib.parse.urljoin(
-                f"{self._client_wrapper.get_environment().default}/",
-                f"v1/deployments/{jsonable_encoder(id)}/release-tags/{jsonable_encoder(name)}",
-            ),
-            params=jsonable_encoder(
-                request_options.get("additional_query_parameters") if request_options is not None else None
-            ),
-            json=jsonable_encoder(_request)
-            if request_options is None or request_options.get("additional_body_parameters") is None
-            else {
-                **jsonable_encoder(_request),
-                **(jsonable_encoder(remove_none_from_dict(request_options.get("additional_body_parameters", {})))),
-            },
-            headers=jsonable_encoder(
-                remove_none_from_dict(
-                    {
-                        **self._client_wrapper.get_headers(),
-                        **(request_options.get("additional_headers", {}) if request_options is not None else {}),
-                    }
-                )
-            ),
-            timeout=request_options.get("timeout_in_seconds")
-            if request_options is not None and request_options.get("timeout_in_seconds") is not None
-            else self._client_wrapper.get_timeout(),
-            retries=0,
-            max_retries=request_options.get("max_retries") if request_options is not None else 0,  # type: ignore
+            json={"history_item_id": history_item_id},
+            request_options=request_options,
+            omit=OMIT,
         )
-        if 200 <= _response.status_code < 300:
-            return pydantic_v1.parse_obj_as(DeploymentReleaseTagRead, _response.json())  # type: ignore
         try:
+            if 200 <= _response.status_code < 300:
+                return pydantic_v1.parse_obj_as(DeploymentReleaseTagRead, _response.json())  # type: ignore
             _response_json = _response.json()
         except JSONDecodeError:
             raise ApiError(status_code=_response.status_code, body=_response.text)
@@ -598,79 +567,93 @@ class AsyncDeploymentsClient:
     async def retrieve_provider_payload(
         self,
         *,
+        inputs: typing.Sequence[PromptDeploymentInputRequest],
         deployment_id: typing.Optional[str] = OMIT,
         deployment_name: typing.Optional[str] = OMIT,
-        inputs: typing.Sequence[PromptDeploymentInputRequest],
         release_tag: typing.Optional[str] = OMIT,
+        expand_meta: typing.Optional[CompilePromptDeploymentExpandMetaRequest] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> DeploymentProviderPayloadResponse:
         """
-        Parameters:
-            - deployment_id: typing.Optional[str]. The ID of the deployment. Must provide either this or deployment_name.
+        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.
+        deployment_name : typing.Optional[str]
+            The name of the deployment. Must provide either this or deployment_id.
 
-            - inputs: typing.Sequence[PromptDeploymentInputRequest]. The list of inputs defined in the Prompt's deployment with their corresponding values.
+        release_tag : typing.Optional[str]
+            Optionally specify a release tag if you want to pin to a specific release of the Workflow Deployment
 
-            - 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
 
-            - request_options: typing.Optional[RequestOptions]. Request-specific configuration.
-        ---
         from vellum.client import AsyncVellum
 
         client = AsyncVellum(
             api_key="YOUR_API_KEY",
         )
-        await client.deployments.retrieve_provider_payload(
-            inputs=[],
-        )
+
+
+        async def main() -> None:
+            await client.deployments.retrieve_provider_payload(
+                inputs=[],
+            )
+
+
+        asyncio.run(main())
         """
-        _request: typing.Dict[str, typing.Any] = {"inputs": inputs}
-        if deployment_id is not OMIT:
-            _request["deployment_id"] = deployment_id
-        if deployment_name is not OMIT:
-            _request["deployment_name"] = deployment_name
-        if release_tag is not OMIT:
-            _request["release_tag"] = release_tag
         _response = await self._client_wrapper.httpx_client.request(
+            "v1/deployments/provider-payload",
+            base_url=self._client_wrapper.get_environment().default,
             method="POST",
-            url=urllib.parse.urljoin(
-                f"{self._client_wrapper.get_environment().default}/", "v1/deployments/provider-payload"
-            ),
-            params=jsonable_encoder(
-                request_options.get("additional_query_parameters") if request_options is not None else None
-            ),
-            json=jsonable_encoder(_request)
-            if request_options is None or request_options.get("additional_body_parameters") is None
-            else {
-                **jsonable_encoder(_request),
-                **(jsonable_encoder(remove_none_from_dict(request_options.get("additional_body_parameters", {})))),
+            json={
+                "deployment_id": deployment_id,
+                "deployment_name": deployment_name,
+                "inputs": inputs,
+                "release_tag": release_tag,
+                "expand_meta": expand_meta,
             },
-            headers=jsonable_encoder(
-                remove_none_from_dict(
-                    {
-                        **self._client_wrapper.get_headers(),
-                        **(request_options.get("additional_headers", {}) if request_options is not None else {}),
-                    }
-                )
-            ),
-            timeout=request_options.get("timeout_in_seconds")
-            if request_options is not None and request_options.get("timeout_in_seconds") is not None
-            else self._client_wrapper.get_timeout(),
-            retries=0,
-            max_retries=request_options.get("max_retries") if request_options is not None else 0,  # type: ignore
+            request_options=request_options,
+            omit=OMIT,
         )
-        if 200 <= _response.status_code < 300:
-            return pydantic_v1.parse_obj_as(DeploymentProviderPayloadResponse, _response.json())  # type: ignore
-        if _response.status_code == 400:
-            raise BadRequestError(pydantic_v1.parse_obj_as(typing.Any, _response.json()))  # type: ignore
-        if _response.status_code == 403:
-            raise ForbiddenError(pydantic_v1.parse_obj_as(typing.Any, _response.json()))  # type: ignore
-        if _response.status_code == 404:
-            raise NotFoundError(pydantic_v1.parse_obj_as(typing.Any, _response.json()))  # type: ignore
-        if _response.status_code == 500:
-            raise InternalServerError(pydantic_v1.parse_obj_as(typing.Any, _response.json()))  # type: ignore
         try:
+            if 200 <= _response.status_code < 300:
+                return pydantic_v1.parse_obj_as(DeploymentProviderPayloadResponse, _response.json())  # type: ignore
+            if _response.status_code == 400:
+                raise BadRequestError(pydantic_v1.parse_obj_as(typing.Any, _response.json()))  # type: ignore
+            if _response.status_code == 403:
+                raise ForbiddenError(pydantic_v1.parse_obj_as(typing.Any, _response.json()))  # type: ignore
+            if _response.status_code == 404:
+                raise NotFoundError(pydantic_v1.parse_obj_as(typing.Any, _response.json()))  # type: ignore
+            if _response.status_code == 500:
+                raise InternalServerError(pydantic_v1.parse_obj_as(typing.Any, _response.json()))  # type: ignore
             _response_json = _response.json()
         except JSONDecodeError:
             raise ApiError(status_code=_response.status_code, body=_response.text)