vellum-ai 0.1.5__py3-none-any.whl → 0.1.7__py3-none-any.whl

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/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/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/resources/deployments/client.py

@@ -1,17 +1,24 @@
 # 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):
@@ -38,6 +45,52 @@ class DeploymentsClient:
             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):
@@ -63,3 +116,49 @@ class AsyncDeploymentsClient:
         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/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/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/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/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]
 

vellum/types/error_execute_prompt_response.py

@@ -13,8 +13,8 @@ except ImportError:
 
 
 class ErrorExecutePromptResponse(pydantic.BaseModel):
-    value: VellumError
     execution_id: str
+    value: VellumError
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

vellum/types/execute_prompt_request.py

@@ -0,0 +1,39 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from .prompt_deployment_input_request import PromptDeploymentInputRequest
+
+try:
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class ExecutePromptRequest(pydantic.BaseModel):
+    inputs: typing.List[PromptDeploymentInputRequest]
+    prompt_deployment_id: typing.Optional[str] = pydantic.Field(
+        description="The ID of the Prompt Deployment. Must provide either this or prompt_deployment_name."
+    )
+    prompt_deployment_name: typing.Optional[str] = pydantic.Field(
+        description="The name of the Prompt Deployment. Must provide either this or prompt_deployment_id."
+    )
+    release_tag: typing.Optional[str] = pydantic.Field(
+        description="Optionally specify a release tag if you want to pin to a specific release of the Prompt Deployment"
+    )
+    external_id: typing.Optional[str]
+
+    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/types/execute_prompt_streaming_response.py

@@ -0,0 +1,56 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from __future__ import annotations
+
+import typing
+
+import typing_extensions
+
+from .fulfilled_execute_prompt_streaming_response import FulfilledExecutePromptStreamingResponse
+from .initiated_execute_prompt_streaming_response import InitiatedExecutePromptStreamingResponse
+from .rejected_execute_prompt_streaming_response import RejectedExecutePromptStreamingResponse
+from .streaming_execute_prompt_streaming_response import StreamingExecutePromptStreamingResponse
+
+
+class ExecutePromptStreamingResponse_Initiated(InitiatedExecutePromptStreamingResponse):
+    state: typing_extensions.Literal["INITIATED"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class ExecutePromptStreamingResponse_Streaming(StreamingExecutePromptStreamingResponse):
+    state: typing_extensions.Literal["STREAMING"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class ExecutePromptStreamingResponse_Fulfilled(FulfilledExecutePromptStreamingResponse):
+    state: typing_extensions.Literal["FULFILLED"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+class ExecutePromptStreamingResponse_Rejected(RejectedExecutePromptStreamingResponse):
+    state: typing_extensions.Literal["REJECTED"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
+ExecutePromptStreamingResponse = typing.Union[
+    ExecutePromptStreamingResponse_Initiated,
+    ExecutePromptStreamingResponse_Streaming,
+    ExecutePromptStreamingResponse_Fulfilled,
+    ExecutePromptStreamingResponse_Rejected,
+]

vellum/types/fulfilled_execute_prompt_streaming_response.py

@@ -0,0 +1,29 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from .execute_prompt_response import ExecutePromptResponse
+
+try:
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class FulfilledExecutePromptStreamingResponse(pydantic.BaseModel):
+    data: ExecutePromptResponse
+
+    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/types/initiated_execute_prompt_response.py

@@ -0,0 +1,30 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from .vellum_variable_type import VellumVariableType
+
+try:
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class InitiatedExecutePromptResponse(pydantic.BaseModel):
+    type: VellumVariableType
+    execution_id: str
+
+    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/types/initiated_execute_prompt_streaming_response.py

@@ -0,0 +1,29 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from .initiated_execute_prompt_response import InitiatedExecutePromptResponse
+
+try:
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class InitiatedExecutePromptStreamingResponse(pydantic.BaseModel):
+    data: InitiatedExecutePromptResponse
+
+    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/types/json_execute_prompt_response.py

@@ -12,8 +12,8 @@ except ImportError:
 
 
 class JsonExecutePromptResponse(pydantic.BaseModel):
-    value: typing.Dict[str, typing.Any]
     execution_id: str
+    value: typing.Dict[str, typing.Any]
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

vellum/types/rejected_execute_prompt_response.py

@@ -0,0 +1,31 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from .vellum_error import VellumError
+
+try:
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class RejectedExecutePromptResponse(pydantic.BaseModel):
+    type: str
+    value: VellumError
+    execution_id: str
+
+    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/types/rejected_execute_prompt_streaming_response.py

@@ -0,0 +1,29 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from .rejected_execute_prompt_response import RejectedExecutePromptResponse
+
+try:
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class RejectedExecutePromptStreamingResponse(pydantic.BaseModel):
+    data: RejectedExecutePromptResponse
+
+    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/types/streaming_execute_prompt_streaming_response.py

@@ -0,0 +1,29 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from .execute_prompt_response import ExecutePromptResponse
+
+try:
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class StreamingExecutePromptStreamingResponse(pydantic.BaseModel):
+    data: ExecutePromptResponse
+
+    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/types/string_execute_prompt_response.py

@@ -12,8 +12,8 @@ except ImportError:
 
 
 class StringExecutePromptResponse(pydantic.BaseModel):
-    value: str
     execution_id: str
+    value: str
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

{vellum_ai-0.1.5.dist-info → vellum_ai-0.1.7.dist-info}/METADATA

@@ -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.dist-info → vellum_ai-0.1.7.dist-info}/RECORD

@@ -1,8 +1,8 @@
-vellum/__init__.py,sha256=G549OSXyIsjzL4hNZ1xFsFSA19Qznr5CzviTS1TRT_o,15911
-vellum/client.py,sha256=VyCnmohtSxlZBzzR-Tpg9ApsFLh6xlcVCnKyLaQT_q4,43212
+vellum/__init__.py,sha256=D6e2X48Z1TiPjYlFSzaTwFJt3otkyI3gQgi7WdQKGiI,17005
+vellum/client.py,sha256=yIYh69Gfqw9tvq6leZcIj9-dU0jUOV2VPOWZgZ83a-U,43945
 vellum/core/__init__.py,sha256=QJS3CJ2TYP2E1Tge0CS6Z7r8LTNzJHQVX1hD3558eP0,519
 vellum/core/api_error.py,sha256=RE8LELok2QCjABadECTvtDp7qejA1VmINCh6TbqPwSE,426
-vellum/core/client_wrapper.py,sha256=_edGK6g1DZbPsbUeNrzqmKJdj6IgcwSqadtDD5JVKWI,1213
+vellum/core/client_wrapper.py,sha256=JPcuDSpeK70W1OPKqReF9TukOWwvfSbckYsQtbeFQBE,1212
 vellum/core/datetime_utils.py,sha256=nBys2IsYrhPdszxGKCNRPSOCwa-5DWOHG95FB8G9PKo,1047
 vellum/core/jsonable_encoder.py,sha256=MTYkDov2EryHgee4QM46uZiBOuOXK9KTHlBdBwU-CpU,3799
 vellum/core/remove_none_from_dict.py,sha256=8m91FC3YuVem0Gm9_sXhJ2tGvP33owJJdrqCLEdowGw,330
@@ -16,20 +16,20 @@ vellum/errors/not_found_error.py,sha256=P65k-Lm2RuefAVSNLER5hH-4P99SGohKy2cOPSrI
 vellum/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 vellum/resources/__init__.py,sha256=ceVGZa6cItlSHYeXoDUeCJuYVs73cUxghmL6MTL3Vp4,339
 vellum/resources/deployments/__init__.py,sha256=FTtvy8EDg9nNNg9WCatVgKTRYV8-_v1roeGPAKoa_pw,65
-vellum/resources/deployments/client.py,sha256=YWHkoV7MBCtxjLLw-7as_60pxNakgZ7PKh9cJSJOsWI,2498
+vellum/resources/deployments/client.py,sha256=abtSfd_9XCrpOhxQ0kUWyDab9FRzGLTL-DZPWQP9Fr4,6625
 vellum/resources/document_indexes/__init__.py,sha256=FTtvy8EDg9nNNg9WCatVgKTRYV8-_v1roeGPAKoa_pw,65
 vellum/resources/document_indexes/client.py,sha256=O3kun7NPMNFhpEBovL0wryJUxlIf2qbVzkOvg6gCvdI,8231
 vellum/resources/documents/__init__.py,sha256=FTtvy8EDg9nNNg9WCatVgKTRYV8-_v1roeGPAKoa_pw,65
 vellum/resources/documents/client.py,sha256=lK41TE_cpTex8H-HT2WnXLPb7jSw3YA1DmanJIVs8xA,15550
 vellum/resources/model_versions/__init__.py,sha256=FTtvy8EDg9nNNg9WCatVgKTRYV8-_v1roeGPAKoa_pw,65
-vellum/resources/model_versions/client.py,sha256=thI78CxGhoi_IIxBAdJgXaa2M0xFV42PKFn0zRJA76w,2511
+vellum/resources/model_versions/client.py,sha256=S7nsjdWVK61gpB0Lp1Dbmst5SIb3IVJ7WdkNlHEVKSQ,2645
 vellum/resources/registered_prompts/__init__.py,sha256=FTtvy8EDg9nNNg9WCatVgKTRYV8-_v1roeGPAKoa_pw,65
 vellum/resources/registered_prompts/client.py,sha256=2yzgJmV5SL_QgQFhVEMG5ykAMZS-qizKXYZEADaXXlk,9227
 vellum/resources/sandboxes/__init__.py,sha256=FTtvy8EDg9nNNg9WCatVgKTRYV8-_v1roeGPAKoa_pw,65
 vellum/resources/sandboxes/client.py,sha256=RkMHXuNGblYEMDdbUeFHzJDGEIxJd9HGiThXUbR1MNg,8201
 vellum/resources/test_suites/__init__.py,sha256=FTtvy8EDg9nNNg9WCatVgKTRYV8-_v1roeGPAKoa_pw,65
 vellum/resources/test_suites/client.py,sha256=TW8piGrmeEqYmMeWtuOyj2lH5_erQ1WVMmDcCOuGdG8,8586
-vellum/types/__init__.py,sha256=BdaLv4JlnA9fVetO8ZgcwFqC1GZW2jfbdhjNxno-NRY,21535
+vellum/types/__init__.py,sha256=62Nm3XMpxJFSxEE-DhhF00K8ThjoDPZ0I7893M5woCk,23046
 vellum/types/api_node_result.py,sha256=1zAcNznjyVkTQM2V--UE1lYFzRWbYEogoChZBGcsliE,936
 vellum/types/api_node_result_data.py,sha256=HvpZaAKYXsoBOnobACIYCmIdxbRc7Zp-ibIohiz_Nzc,1125
 vellum/types/block_type_enum.py,sha256=BQ8ZN1OKhOdmHeQ3-bhMfkLLohirsNhHPljBJX8Bbmo,1051
@@ -39,7 +39,8 @@ vellum/types/chat_message_request.py,sha256=9wgnG0Q36jUNTr7vS0FASRFrsXzgIccrjNiC
 vellum/types/chat_message_role.py,sha256=VscYXloHNYjiThf7g6OsMxO0S8p0ZUa0G6sakaWhc1g,914
 vellum/types/conditional_node_result.py,sha256=u2Rx3LOY0rNwdSb6vZnOmMRcDvl83uKXccVQv2kzS7g,968
 vellum/types/conditional_node_result_data.py,sha256=IT6PnM2N4q8JJ4srk9ushri4GnCvxMz9VuEcbhmo_rs,911
-vellum/types/deployment_read.py,sha256=rnGqiO_IqtlW3G8_cQqTx4vWBta1B3urlehBuES1lwk,1964
+vellum/types/deployment_provider_payload_response.py,sha256=R8X-oE1hydzE4qgLO0HS6NwlW157if4ecCPJPCLyPHY,918
+vellum/types/deployment_read.py,sha256=FQmnDqpdKxCrKGCaMyIfCZyUXfpG62HFOWRgpBgQeGs,2110
 vellum/types/deployment_status.py,sha256=rtsRFv9cx0kEwNYkgscGzo62bvaNME-rU8ZxFlcY0M8,761
 vellum/types/document_document_to_document_index.py,sha256=So0eaa9uQd_vrbnpQD_wV7YJS0YQY3AH_91asYpYv_g,1634
 vellum/types/document_index_read.py,sha256=PuGRQTrzpQjs4d-ObBe5glzKNlgpJR3Hr5OGEannHak,1889
@@ -48,13 +49,16 @@ vellum/types/document_read.py,sha256=aeAwY8-Si0nT2Ifh1J9ChLaNFJaker1jlfbJkuoA-xc
 vellum/types/document_status.py,sha256=dkotle2rykOxF1QxqcM8af2ORzmFjZR5a7pHXP6SjDQ,144
 vellum/types/enriched_normalized_completion.py,sha256=z3MzEF7T-JcyTQRNlZlnB9GpFcLFo0gy-hF3LYW7Pfg,2135
 vellum/types/environment_enum.py,sha256=16gr0xkzNIO5dhrOnJNjcQ34z9Xk1oE-egW17P0RWDs,799
-vellum/types/error_execute_prompt_response.py,sha256=EJpJ5llClytDgVx5BaAKuoMySHwQ_YNQrSN3jR-A3xs,952
+vellum/types/error_execute_prompt_response.py,sha256=WKGFWwYe-3voDJ201StQg_znLR5LV0Vreg1Iml2sUig,952
 vellum/types/evaluation_params.py,sha256=Ey-RgV4uKVv8G4Dj6lmX_qiBsLcPo1NmoY2xcFW_qDQ,1048
 vellum/types/evaluation_params_request.py,sha256=izDbrQHT7QFYjxXX9bkeZnoCle3teShaodbnV_11sJo,1055
 vellum/types/execute_prompt_api_error_response.py,sha256=f0peA0yIyF1dqh2PclsVEaiCCoLK73KEwYq32cj82Nw,958
+vellum/types/execute_prompt_request.py,sha256=q50zgx3KB_eb1biQhHgEpKyCGDszBMRhJWNkF04xrBE,1570
 vellum/types/execute_prompt_response.py,sha256=XjY80wf3-_zZQp4BeEP4OzedkEPzhLCr3pSJZ3vv-qo,1156
+vellum/types/execute_prompt_streaming_response.py,sha256=a8jAsI0rBhqlvDpDhzShMvtsK-fNK3oJ7LY3bk3Edgo,1779
 vellum/types/execute_workflow_stream_error_response.py,sha256=WHSu333maVV2Nbxs43QCxlW6wjbkPdm-97DP1tzglAA,963
 vellum/types/finish_reason_enum.py,sha256=JawC1tsGIUCwfGoIjrnD2c4wmbsO5Dx39WPAbwYIWm0,726
+vellum/types/fulfilled_execute_prompt_streaming_response.py,sha256=OjN_FNpm1ygCAormfD54SuVGh4WPpzY-PWLFn1T8BbM,973
 vellum/types/generate_error_response.py,sha256=auz4NPbyceabCe0eN89lavEwotWbqsTSbkJtI_lgXJs,950
 vellum/types/generate_options_request.py,sha256=9W8wAC79BB1lu9bJjWm0Wwco7FiB6wZYvRDYWZbV_Tg,1117
 vellum/types/generate_request.py,sha256=Wf5j8TIhLqPwwJJz63TiMNty2cvnJI9xVmUKtWlJIpQ,1581
@@ -66,7 +70,9 @@ vellum/types/generate_stream_response.py,sha256=mbaw11ScmPmSgih02qE2pLDN0fjILc3L
 vellum/types/generate_stream_result.py,sha256=NevSf70_mbODDRPnauYobl41PNbPVcNKyWTe2gg-lxI,1107
 vellum/types/generate_stream_result_data.py,sha256=lyAvxY714Zo5W1i4WkuIbKjyP3rLGJAQ_pL2jkDL7Pg,1011
 vellum/types/indexing_state_enum.py,sha256=7eEvjuZi3dy6XJIYhHgca4XfRDqntaoYTFOOl9AXe78,1181
-vellum/types/json_execute_prompt_response.py,sha256=ESvK2oJfNop3VWotbW7LHR2djcJjoIan70X-11Ivnoo,930
+vellum/types/initiated_execute_prompt_response.py,sha256=aODjQByWjOgOEWcffzHGdUxWAQZEMqbQvbn7isI032A,977
+vellum/types/initiated_execute_prompt_streaming_response.py,sha256=tNezi3r94E19wg4LJp2OYAaScIN0XjjnIuwYvHyBVgU,1001
+vellum/types/json_execute_prompt_response.py,sha256=JN_lyuNWaQP9aHV_SkSzEt-cRbuRb7KganXkiw3lkbI,930
 vellum/types/json_input_request.py,sha256=x3aGIGpjqG8aPxRWfneeWalR2mOdQJKlviF72URrnMg,996
 vellum/types/logical_operator.py,sha256=4AVyWKNKyL8NxaqUKdS8hV7nfRpUlItKDNdC_hkJU9E,4282
 vellum/types/logprobs_enum.py,sha256=v3VTlzw1bpuU0hBhcWJTN7JMBS2nWqwertJlaCgxmuY,490
@@ -111,6 +117,8 @@ vellum/types/registered_prompt_input_variable_request.py,sha256=rbqQnjUtP2_J3axz
 vellum/types/registered_prompt_model_version.py,sha256=g1HQfGIucvXJ0E0xAZiE5rnvkFp8DMpe3MPCYbxHTSo,1057
 vellum/types/registered_prompt_sandbox.py,sha256=TMVbdnTEoSBvabGQ9ZZqMSDNxjK4iXLaQrZciytWazc,1040
 vellum/types/registered_prompt_sandbox_snapshot.py,sha256=Dv4sY70rvdLtyKi8oN2mWwHmHZIHEcdN0v32ULxD67A,960
+vellum/types/rejected_execute_prompt_response.py,sha256=_SdbOPXsPiQMRYAGQgBIdP6fmKYSxhtb56LmjLPEAaI,969
+vellum/types/rejected_execute_prompt_streaming_response.py,sha256=hm48IfCMHandLwfiugItBLHuNVeD4LU-UaTF2ELkM3c,997
 vellum/types/sandbox_metric_input_params.py,sha256=WPrqAWggrSvu9syP2Fk4SGj08YvV55oF9dD6Cb40gjE,961
 vellum/types/sandbox_metric_input_params_request.py,sha256=UbTt4QimyaoYjzhWNggpFL7SlYLgKqZ4i6_skWzAo2I,990
 vellum/types/sandbox_scenario.py,sha256=mGidLY1jAdw7BSMbeXTc-PtiZLSQS4peOiJmxL8YxqQ,1214
@@ -130,7 +138,8 @@ vellum/types/search_result_merging_request.py,sha256=lLgp8q1WwvdUJcR1YWpLRjmZ3Sg
 vellum/types/search_result_request.py,sha256=SMjICHnxr3l8-KCe7ftWMZiKPdlvdMAPZd4zRXNxpQ8,1335
 vellum/types/search_weights_request.py,sha256=guPgN3N0b5Mg0sIpw8ts80iBOT_nUsRNZqjDMKJIphI,1117
 vellum/types/slim_document.py,sha256=-wzURGcLcnoh5vdTlbtkPLKfP3yAShdkkK6AIIi6W48,3074
-vellum/types/string_execute_prompt_response.py,sha256=qsOhsJYzbZ4IjcsrNW8qSF6B0HAkWRJsRKi7xc3k_sk,907
+vellum/types/streaming_execute_prompt_streaming_response.py,sha256=fzXYdZeMSzhAcxigXOSQksrw80ItRibEitKYOrtLnmc,973
+vellum/types/string_execute_prompt_response.py,sha256=yDttrw8xZ7bKQhKKFAAub30orAUmxjPqHDLaHeYPZTI,907
 vellum/types/string_input_request.py,sha256=aUzb_zuLK9G7tHBRHVWCJD4o-UbcVcMVtIrgAoES8dw,973
 vellum/types/submit_completion_actual_request.py,sha256=krKZefK_-0LAEJYIKilUemEwc6v0RELpusQvyj1XUJQ,1787
 vellum/types/submit_completion_actuals_error_response.py,sha256=AJTkBM60F8rxGKXfz0TcjdP5v_OgRnF3zUrDG1CtNDo,895
@@ -199,6 +208,6 @@ vellum/types/workflow_result_event_output_data_number.py,sha256=zWtQor27iaDDHmY5
 vellum/types/workflow_result_event_output_data_search_results.py,sha256=frCaJ5kWrIqCeV-waBNfd7rO4fqWe5aYpSI8PM4-oRw,1323
 vellum/types/workflow_result_event_output_data_string.py,sha256=TByZxyQh9ci4UIdEmoEi_JK1U_JwYCnVZeB_4kGuXKM,1405
 vellum/types/workflow_stream_event.py,sha256=OQUSzwoM-OCfWxNzeOVVLsjCue_WWqin3tGMtwvp_rc,873
-vellum_ai-0.1.5.dist-info/METADATA,sha256=vd81SnK9c0nlCZ6NM7hpZM_lBSXJ8aLXsalahlewW5w,3486
-vellum_ai-0.1.5.dist-info/WHEEL,sha256=Zb28QaM1gQi8f4VCBhsUklF61CTlNYfs9YAZn-TOGFk,88
-vellum_ai-0.1.5.dist-info/RECORD,,
+vellum_ai-0.1.7.dist-info/METADATA,sha256=xJmftveWGDpOAuA4fzAH2woeebCq8AkOHEC0gfL32U0,3486
+vellum_ai-0.1.7.dist-info/WHEEL,sha256=Zb28QaM1gQi8f4VCBhsUklF61CTlNYfs9YAZn-TOGFk,88
+vellum_ai-0.1.7.dist-info/RECORD,,