vellum-ai 0.1.5__tar.gz → 0.1.7__tar.gz

{vellum_ai-0.1.5 → vellum_ai-0.1.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vellum-ai
-Version: 0.1.5
+Version: 0.1.7
 Summary: 
 Requires-Python: >=3.7,<4.0
 Classifier: Programming Language :: Python :: 3

{vellum_ai-0.1.5 → vellum_ai-0.1.7}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "vellum-ai"
-version = "v0.1.5"
+version = "0.1.7"
 description = ""
 readme = "README.md"
 authors = []

{vellum_ai-0.1.5 → vellum_ai-0.1.7}/src/vellum/__init__.py

@@ -10,6 +10,7 @@ from .types import (
     ChatMessageRole,
     ConditionalNodeResult,
     ConditionalNodeResultData,
+    DeploymentProviderPayloadResponse,
     DeploymentRead,
     DeploymentStatus,
     DocumentDocumentToDocumentIndex,
@@ -23,12 +24,19 @@ from .types import (
     EvaluationParams,
     EvaluationParamsRequest,
     ExecutePromptApiErrorResponse,
+    ExecutePromptRequest,
     ExecutePromptResponse,
     ExecutePromptResponse_Error,
     ExecutePromptResponse_Json,
     ExecutePromptResponse_String,
+    ExecutePromptStreamingResponse,
+    ExecutePromptStreamingResponse_Fulfilled,
+    ExecutePromptStreamingResponse_Initiated,
+    ExecutePromptStreamingResponse_Rejected,
+    ExecutePromptStreamingResponse_Streaming,
     ExecuteWorkflowStreamErrorResponse,
     FinishReasonEnum,
+    FulfilledExecutePromptStreamingResponse,
     GenerateErrorResponse,
     GenerateOptionsRequest,
     GenerateRequest,
@@ -40,6 +48,8 @@ from .types import (
     GenerateStreamResult,
     GenerateStreamResultData,
     IndexingStateEnum,
+    InitiatedExecutePromptResponse,
+    InitiatedExecutePromptStreamingResponse,
     JsonExecutePromptResponse,
     JsonInputRequest,
     LogicalOperator,
@@ -94,6 +104,8 @@ from .types import (
     RegisteredPromptModelVersion,
     RegisteredPromptSandbox,
     RegisteredPromptSandboxSnapshot,
+    RejectedExecutePromptResponse,
+    RejectedExecutePromptStreamingResponse,
     SandboxMetricInputParams,
     SandboxMetricInputParamsRequest,
     SandboxScenario,
@@ -113,6 +125,7 @@ from .types import (
     SearchResultRequest,
     SearchWeightsRequest,
     SlimDocument,
+    StreamingExecutePromptStreamingResponse,
     StringExecutePromptResponse,
     StringInputRequest,
     SubmitCompletionActualRequest,
@@ -251,6 +264,7 @@ __all__ = [
     "ConditionalNodeResult",
     "ConditionalNodeResultData",
     "ConflictError",
+    "DeploymentProviderPayloadResponse",
     "DeploymentRead",
     "DeploymentStatus",
     "DocumentDocumentToDocumentIndex",
@@ -264,13 +278,20 @@ __all__ = [
     "EvaluationParams",
     "EvaluationParamsRequest",
     "ExecutePromptApiErrorResponse",
+    "ExecutePromptRequest",
     "ExecutePromptResponse",
     "ExecutePromptResponse_Error",
     "ExecutePromptResponse_Json",
     "ExecutePromptResponse_String",
+    "ExecutePromptStreamingResponse",
+    "ExecutePromptStreamingResponse_Fulfilled",
+    "ExecutePromptStreamingResponse_Initiated",
+    "ExecutePromptStreamingResponse_Rejected",
+    "ExecutePromptStreamingResponse_Streaming",
     "ExecuteWorkflowStreamErrorResponse",
     "FinishReasonEnum",
     "ForbiddenError",
+    "FulfilledExecutePromptStreamingResponse",
     "GenerateErrorResponse",
     "GenerateOptionsRequest",
     "GenerateRequest",
@@ -282,6 +303,8 @@ __all__ = [
     "GenerateStreamResult",
     "GenerateStreamResultData",
     "IndexingStateEnum",
+    "InitiatedExecutePromptResponse",
+    "InitiatedExecutePromptStreamingResponse",
     "InternalServerError",
     "JsonExecutePromptResponse",
     "JsonInputRequest",
@@ -338,6 +361,8 @@ __all__ = [
     "RegisteredPromptModelVersion",
     "RegisteredPromptSandbox",
     "RegisteredPromptSandboxSnapshot",
+    "RejectedExecutePromptResponse",
+    "RejectedExecutePromptStreamingResponse",
     "SandboxMetricInputParams",
     "SandboxMetricInputParamsRequest",
     "SandboxScenario",
@@ -357,6 +382,7 @@ __all__ = [
     "SearchResultRequest",
     "SearchWeightsRequest",
     "SlimDocument",
+    "StreamingExecutePromptStreamingResponse",
     "StringExecutePromptResponse",
     "StringInputRequest",
     "SubmitCompletionActualRequest",

{vellum_ai-0.1.5 → vellum_ai-0.1.7}/src/vellum/client.py

@@ -22,12 +22,13 @@ from .resources.model_versions.client import AsyncModelVersionsClient, ModelVers
 from .resources.registered_prompts.client import AsyncRegisteredPromptsClient, RegisteredPromptsClient
 from .resources.sandboxes.client import AsyncSandboxesClient, SandboxesClient
 from .resources.test_suites.client import AsyncTestSuitesClient, TestSuitesClient
+from .types.execute_prompt_request import ExecutePromptRequest
 from .types.execute_prompt_response import ExecutePromptResponse
+from .types.execute_prompt_streaming_response import ExecutePromptStreamingResponse
 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.prompt_deployment_input_request import PromptDeploymentInputRequest
 from .types.search_request_options_request import SearchRequestOptionsRequest
 from .types.search_response import SearchResponse
 from .types.submit_completion_actual_request import SubmitCompletionActualRequest
@@ -67,42 +68,17 @@ class Vellum:
         self.sandboxes = SandboxesClient(client_wrapper=self._client_wrapper)
         self.test_suites = TestSuitesClient(client_wrapper=self._client_wrapper)
 
-    def execute_prompt(
-        self,
-        *,
-        inputs: typing.List[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,
-    ) -> ExecutePromptResponse:
+    def execute_prompt(self, *, request: ExecutePromptRequest) -> ExecutePromptResponse:
         """
         Executes a deployed Prompt and returns the result.
 
         Parameters:
-            - inputs: typing.List[PromptDeploymentInputRequest].
-
-            - 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 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].
+            - request: ExecutePromptRequest.
         """
-        _request: typing.Dict[str, typing.Any] = {"inputs": inputs}
-        if prompt_deployment_id is not OMIT:
-            _request["prompt_deployment_id"] = prompt_deployment_id
-        if prompt_deployment_name is not OMIT:
-            _request["prompt_deployment_name"] = prompt_deployment_name
-        if release_tag is not OMIT:
-            _request["release_tag"] = release_tag
-        if external_id is not OMIT:
-            _request["external_id"] = external_id
         _response = self._client_wrapper.httpx_client.request(
             "POST",
             urllib.parse.urljoin(f"{self._client_wrapper.get_environment().default}/", "v1/execute-prompt"),
-            json=jsonable_encoder(_request),
+            json=jsonable_encoder(request),
             headers=self._client_wrapper.get_headers(),
             timeout=None,
         )
@@ -122,6 +98,36 @@ class Vellum:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    def execute_prompt_stream(self, *, request: ExecutePromptRequest) -> ExecutePromptStreamingResponse:
+        """
+        Executes a deployed Prompt and streams back the results.
+
+        Parameters:
+            - request: ExecutePromptRequest.
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "POST",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_environment().default}/", "v1/execute-prompt-stream"),
+            json=jsonable_encoder(request),
+            headers=self._client_wrapper.get_headers(),
+            timeout=None,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ExecutePromptStreamingResponse, _response.json())  # type: ignore
+        if _response.status_code == 400:
+            raise BadRequestError(pydantic.parse_obj_as(typing.Any, _response.json()))  # type: ignore
+        if _response.status_code == 403:
+            raise ForbiddenError(pydantic.parse_obj_as(typing.Any, _response.json()))  # type: ignore
+        if _response.status_code == 404:
+            raise NotFoundError(pydantic.parse_obj_as(typing.Any, _response.json()))  # type: ignore
+        if _response.status_code == 500:
+            raise InternalServerError(pydantic.parse_obj_as(typing.Any, _response.json()))  # type: ignore
+        try:
+            _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 execute_workflow_stream(
         self,
         *,
@@ -488,42 +494,17 @@ class AsyncVellum:
         self.sandboxes = AsyncSandboxesClient(client_wrapper=self._client_wrapper)
         self.test_suites = AsyncTestSuitesClient(client_wrapper=self._client_wrapper)
 
-    async def execute_prompt(
-        self,
-        *,
-        inputs: typing.List[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,
-    ) -> ExecutePromptResponse:
+    async def execute_prompt(self, *, request: ExecutePromptRequest) -> ExecutePromptResponse:
         """
         Executes a deployed Prompt and returns the result.
 
         Parameters:
-            - inputs: typing.List[PromptDeploymentInputRequest].
-
-            - 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 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].
+            - request: ExecutePromptRequest.
         """
-        _request: typing.Dict[str, typing.Any] = {"inputs": inputs}
-        if prompt_deployment_id is not OMIT:
-            _request["prompt_deployment_id"] = prompt_deployment_id
-        if prompt_deployment_name is not OMIT:
-            _request["prompt_deployment_name"] = prompt_deployment_name
-        if release_tag is not OMIT:
-            _request["release_tag"] = release_tag
-        if external_id is not OMIT:
-            _request["external_id"] = external_id
         _response = await self._client_wrapper.httpx_client.request(
             "POST",
             urllib.parse.urljoin(f"{self._client_wrapper.get_environment().default}/", "v1/execute-prompt"),
-            json=jsonable_encoder(_request),
+            json=jsonable_encoder(request),
             headers=self._client_wrapper.get_headers(),
             timeout=None,
         )
@@ -543,6 +524,36 @@ class AsyncVellum:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    async def execute_prompt_stream(self, *, request: ExecutePromptRequest) -> ExecutePromptStreamingResponse:
+        """
+        Executes a deployed Prompt and streams back the results.
+
+        Parameters:
+            - request: ExecutePromptRequest.
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "POST",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_environment().default}/", "v1/execute-prompt-stream"),
+            json=jsonable_encoder(request),
+            headers=self._client_wrapper.get_headers(),
+            timeout=None,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ExecutePromptStreamingResponse, _response.json())  # type: ignore
+        if _response.status_code == 400:
+            raise BadRequestError(pydantic.parse_obj_as(typing.Any, _response.json()))  # type: ignore
+        if _response.status_code == 403:
+            raise ForbiddenError(pydantic.parse_obj_as(typing.Any, _response.json()))  # type: ignore
+        if _response.status_code == 404:
+            raise NotFoundError(pydantic.parse_obj_as(typing.Any, _response.json()))  # type: ignore
+        if _response.status_code == 500:
+            raise InternalServerError(pydantic.parse_obj_as(typing.Any, _response.json()))  # type: ignore
+        try:
+            _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 execute_workflow_stream(
         self,
         *,

{vellum_ai-0.1.5 → vellum_ai-0.1.7}/src/vellum/core/client_wrapper.py

@@ -16,7 +16,7 @@ class BaseClientWrapper:
         headers: typing.Dict[str, str] = {
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "vellum-ai",
-            "X-Fern-SDK-Version": "v0.1.5",
+            "X-Fern-SDK-Version": "0.1.7",
         }
         headers["X_API_KEY"] = self.api_key
         return headers

vellum_ai-0.1.7/src/vellum/resources/deployments/client.py

@@ -0,0 +1,164 @@
+# 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 ...types.deployment_provider_payload_response import DeploymentProviderPayloadResponse
+from ...types.deployment_read import DeploymentRead
+from ...types.prompt_deployment_input_request import PromptDeploymentInputRequest
+
+try:
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+# 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 retrieve(self, id: str) -> DeploymentRead:
+        """
+        Used to retrieve a deployment given its ID or name.
+
+        Parameters:
+            - id: str. Either the Deployment's ID or its unique name
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_environment().default}/", f"v1/deployments/{id}"),
+            headers=self._client_wrapper.get_headers(),
+            timeout=None,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(DeploymentRead, _response.json())  # type: ignore
+        try:
+            _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,
+        *,
+        deployment_id: typing.Optional[str] = OMIT,
+        deployment_name: typing.Optional[str] = OMIT,
+        inputs: typing.List[PromptDeploymentInputRequest],
+    ) -> DeploymentProviderPayloadResponse:
+        """
+        Parameters:
+            - 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.
+
+            - inputs: typing.List[PromptDeploymentInputRequest].
+        ---
+        from vellum.client import Vellum
+
+        client = Vellum(
+            api_key="YOUR_API_KEY",
+        )
+        client.deployments.retrieve_provider_payload(
+            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
+        _response = self._client_wrapper.httpx_client.request(
+            "POST",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_environment().default}/", "v1/deployments/provider-payload"
+            ),
+            json=jsonable_encoder(_request),
+            headers=self._client_wrapper.get_headers(),
+            timeout=None,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(DeploymentProviderPayloadResponse, _response.json())  # type: ignore
+        try:
+            _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 retrieve(self, id: str) -> DeploymentRead:
+        """
+        Used to retrieve a deployment given its ID or name.
+
+        Parameters:
+            - id: str. Either the Deployment's ID or its unique name
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_environment().default}/", f"v1/deployments/{id}"),
+            headers=self._client_wrapper.get_headers(),
+            timeout=None,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(DeploymentRead, _response.json())  # type: ignore
+        try:
+            _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,
+        *,
+        deployment_id: typing.Optional[str] = OMIT,
+        deployment_name: typing.Optional[str] = OMIT,
+        inputs: typing.List[PromptDeploymentInputRequest],
+    ) -> DeploymentProviderPayloadResponse:
+        """
+        Parameters:
+            - 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.
+
+            - inputs: typing.List[PromptDeploymentInputRequest].
+        ---
+        from vellum.client import AsyncVellum
+
+        client = AsyncVellum(
+            api_key="YOUR_API_KEY",
+        )
+        await client.deployments.retrieve_provider_payload(
+            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
+        _response = await self._client_wrapper.httpx_client.request(
+            "POST",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_environment().default}/", "v1/deployments/provider-payload"
+            ),
+            json=jsonable_encoder(_request),
+            headers=self._client_wrapper.get_headers(),
+            timeout=None,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(DeploymentProviderPayloadResponse, _response.json())  # type: ignore
+        try:
+            _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)

{vellum_ai-0.1.5 → vellum_ai-0.1.7}/src/vellum/resources/model_versions/client.py

@@ -19,7 +19,7 @@ class ModelVersionsClient:
 
     def retrieve(self, id: str) -> ModelVersionRead:
         """
-        Used to retrieve a model version given its ID.
+        Deprecated. Use the `deployments/provider-payload` endpoint to fetch information that we send to Model providers.
 
         Parameters:
             - id: str. A UUID string identifying this model version.
@@ -45,7 +45,7 @@ class AsyncModelVersionsClient:
 
     async def retrieve(self, id: str) -> ModelVersionRead:
         """
-        Used to retrieve a model version given its ID.
+        Deprecated. Use the `deployments/provider-payload` endpoint to fetch information that we send to Model providers.
 
         Parameters:
             - id: str. A UUID string identifying this model version.

{vellum_ai-0.1.5 → vellum_ai-0.1.7}/src/vellum/types/__init__.py

@@ -9,6 +9,7 @@ from .chat_message_request import ChatMessageRequest
 from .chat_message_role import ChatMessageRole
 from .conditional_node_result import ConditionalNodeResult
 from .conditional_node_result_data import ConditionalNodeResultData
+from .deployment_provider_payload_response import DeploymentProviderPayloadResponse
 from .deployment_read import DeploymentRead
 from .deployment_status import DeploymentStatus
 from .document_document_to_document_index import DocumentDocumentToDocumentIndex
@@ -22,14 +23,23 @@ from .error_execute_prompt_response import ErrorExecutePromptResponse
 from .evaluation_params import EvaluationParams
 from .evaluation_params_request import EvaluationParamsRequest
 from .execute_prompt_api_error_response import ExecutePromptApiErrorResponse
+from .execute_prompt_request import ExecutePromptRequest
 from .execute_prompt_response import (
     ExecutePromptResponse,
     ExecutePromptResponse_Error,
     ExecutePromptResponse_Json,
     ExecutePromptResponse_String,
 )
+from .execute_prompt_streaming_response import (
+    ExecutePromptStreamingResponse,
+    ExecutePromptStreamingResponse_Fulfilled,
+    ExecutePromptStreamingResponse_Initiated,
+    ExecutePromptStreamingResponse_Rejected,
+    ExecutePromptStreamingResponse_Streaming,
+)
 from .execute_workflow_stream_error_response import ExecuteWorkflowStreamErrorResponse
 from .finish_reason_enum import FinishReasonEnum
+from .fulfilled_execute_prompt_streaming_response import FulfilledExecutePromptStreamingResponse
 from .generate_error_response import GenerateErrorResponse
 from .generate_options_request import GenerateOptionsRequest
 from .generate_request import GenerateRequest
@@ -41,6 +51,8 @@ from .generate_stream_response import GenerateStreamResponse
 from .generate_stream_result import GenerateStreamResult
 from .generate_stream_result_data import GenerateStreamResultData
 from .indexing_state_enum import IndexingStateEnum
+from .initiated_execute_prompt_response import InitiatedExecutePromptResponse
+from .initiated_execute_prompt_streaming_response import InitiatedExecutePromptStreamingResponse
 from .json_execute_prompt_response import JsonExecutePromptResponse
 from .json_input_request import JsonInputRequest
 from .logical_operator import LogicalOperator
@@ -99,6 +111,8 @@ from .registered_prompt_input_variable_request import RegisteredPromptInputVaria
 from .registered_prompt_model_version import RegisteredPromptModelVersion
 from .registered_prompt_sandbox import RegisteredPromptSandbox
 from .registered_prompt_sandbox_snapshot import RegisteredPromptSandboxSnapshot
+from .rejected_execute_prompt_response import RejectedExecutePromptResponse
+from .rejected_execute_prompt_streaming_response import RejectedExecutePromptStreamingResponse
 from .sandbox_metric_input_params import SandboxMetricInputParams
 from .sandbox_metric_input_params_request import SandboxMetricInputParamsRequest
 from .sandbox_scenario import SandboxScenario
@@ -118,6 +132,7 @@ from .search_result_merging_request import SearchResultMergingRequest
 from .search_result_request import SearchResultRequest
 from .search_weights_request import SearchWeightsRequest
 from .slim_document import SlimDocument
+from .streaming_execute_prompt_streaming_response import StreamingExecutePromptStreamingResponse
 from .string_execute_prompt_response import StringExecutePromptResponse
 from .string_input_request import StringInputRequest
 from .submit_completion_actual_request import SubmitCompletionActualRequest
@@ -256,6 +271,7 @@ __all__ = [
     "ChatMessageRole",
     "ConditionalNodeResult",
     "ConditionalNodeResultData",
+    "DeploymentProviderPayloadResponse",
     "DeploymentRead",
     "DeploymentStatus",
     "DocumentDocumentToDocumentIndex",
@@ -269,12 +285,19 @@ __all__ = [
     "EvaluationParams",
     "EvaluationParamsRequest",
     "ExecutePromptApiErrorResponse",
+    "ExecutePromptRequest",
     "ExecutePromptResponse",
     "ExecutePromptResponse_Error",
     "ExecutePromptResponse_Json",
     "ExecutePromptResponse_String",
+    "ExecutePromptStreamingResponse",
+    "ExecutePromptStreamingResponse_Fulfilled",
+    "ExecutePromptStreamingResponse_Initiated",
+    "ExecutePromptStreamingResponse_Rejected",
+    "ExecutePromptStreamingResponse_Streaming",
     "ExecuteWorkflowStreamErrorResponse",
     "FinishReasonEnum",
+    "FulfilledExecutePromptStreamingResponse",
     "GenerateErrorResponse",
     "GenerateOptionsRequest",
     "GenerateRequest",
@@ -286,6 +309,8 @@ __all__ = [
     "GenerateStreamResult",
     "GenerateStreamResultData",
     "IndexingStateEnum",
+    "InitiatedExecutePromptResponse",
+    "InitiatedExecutePromptStreamingResponse",
     "JsonExecutePromptResponse",
     "JsonInputRequest",
     "LogicalOperator",
@@ -340,6 +365,8 @@ __all__ = [
     "RegisteredPromptModelVersion",
     "RegisteredPromptSandbox",
     "RegisteredPromptSandboxSnapshot",
+    "RejectedExecutePromptResponse",
+    "RejectedExecutePromptStreamingResponse",
     "SandboxMetricInputParams",
     "SandboxMetricInputParamsRequest",
     "SandboxScenario",
@@ -359,6 +386,7 @@ __all__ = [
     "SearchResultRequest",
     "SearchWeightsRequest",
     "SlimDocument",
+    "StreamingExecutePromptStreamingResponse",
     "StringExecutePromptResponse",
     "StringInputRequest",
     "SubmitCompletionActualRequest",

vellum_ai-0.1.7/src/vellum/types/deployment_provider_payload_response.py

@@ -0,0 +1,28 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+
+try:
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class DeploymentProviderPayloadResponse(pydantic.BaseModel):
+    payload: typing.Dict[str, typing.Any]
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        json_encoders = {dt.datetime: serialize_datetime}

{vellum_ai-0.1.5 → vellum_ai-0.1.7}/src/vellum/types/deployment_read.py

@@ -37,7 +37,9 @@ class DeploymentRead(pydantic.BaseModel):
             "* `PRODUCTION` - Production\n"
         )
     )
-    active_model_version_ids: typing.List[str]
+    active_model_version_ids: typing.List[str] = pydantic.Field(
+        description="Deprecated. The Prompt execution endpoints return a `prompt_version_id` that could be used instead."
+    )
     last_deployed_on: dt.datetime
     input_variables: typing.List[VellumVariable]