vellum-ai 0.8.4__py3-none-any.whl → 0.8.6__py3-none-any.whl

vellum/__init__.py

@@ -1,6 +1,12 @@
 # This file was auto-generated by Fern from our API Definition.
 
 from .types import (
+    AdHocExecutePromptEvent,
+    AdHocExpandMetaRequest,
+    AdHocFulfilledPromptExecutionMeta,
+    AdHocInitiatedPromptExecutionMeta,
+    AdHocRejectedPromptExecutionMeta,
+    AdHocStreamingPromptExecutionMeta,
     AddOpenaiApiKeyEnum,
     ApiNodeResult,
     ApiNodeResultData,
@@ -21,6 +27,8 @@ from .types import (
     ChatMessage,
     ChatMessageContent,
     ChatMessageContentRequest,
+    ChatMessagePromptBlockPropertiesRequest,
+    ChatMessagePromptBlockRequest,
     ChatMessageRequest,
     ChatMessageRole,
     CodeExecutionNodeArrayResult,
@@ -57,6 +65,8 @@ from .types import (
     EnrichedNormalizedCompletion,
     EntityStatus,
     EnvironmentEnum,
+    EphemeralPromptCacheConfigRequest,
+    EphemeralPromptCacheConfigTypeEnum,
     ErrorVariableValue,
     ErrorVellumValue,
     ErrorVellumValueRequest,
@@ -76,6 +86,7 @@ from .types import (
     ExternalTestCaseExecution,
     ExternalTestCaseExecutionRequest,
     FinishReasonEnum,
+    FulfilledAdHocExecutePromptEvent,
     FulfilledEnum,
     FulfilledExecutePromptEvent,
     FulfilledExecutePromptResponse,
@@ -91,6 +102,8 @@ from .types import (
     FunctionCallVariableValue,
     FunctionCallVellumValue,
     FunctionCallVellumValueRequest,
+    FunctionDefinitionPromptBlockPropertiesRequest,
+    FunctionDefinitionPromptBlockRequest,
     GenerateOptionsRequest,
     GenerateRequest,
     GenerateResponse,
@@ -102,9 +115,6 @@ from .types import (
     GenerateStreamResultData,
     HkunlpInstructorXlVectorizer,
     HkunlpInstructorXlVectorizerRequest,
-    HostedByEnum,
-    HuggingFaceTokenizerConfig,
-    HuggingFaceTokenizerConfigRequest,
     ImageChatMessageContent,
     ImageChatMessageContentRequest,
     ImageVariableValue,
@@ -113,12 +123,15 @@ from .types import (
     IndexingConfigVectorizer,
     IndexingConfigVectorizerRequest,
     IndexingStateEnum,
+    InitiatedAdHocExecutePromptEvent,
     InitiatedExecutePromptEvent,
     InitiatedPromptExecutionMeta,
     InitiatedWorkflowNodeResultEvent,
     InstructorVectorizerConfig,
     InstructorVectorizerConfigRequest,
     IterationStateEnum,
+    JinjaPromptBlockPropertiesRequest,
+    JinjaPromptBlockRequest,
     JsonInputRequest,
     JsonVariableValue,
     JsonVellumValue,
@@ -133,29 +146,6 @@ from .types import (
     MetadataFilterRuleCombinator,
     MetadataFilterRuleRequest,
     MetricNodeResult,
-    MlModelDeveloper,
-    MlModelDeveloperEnumValueLabel,
-    MlModelDisplayConfigLabelled,
-    MlModelDisplayConfigRequest,
-    MlModelDisplayTag,
-    MlModelDisplayTagEnumValueLabel,
-    MlModelExecConfig,
-    MlModelExecConfigRequest,
-    MlModelFamily,
-    MlModelFamilyEnumValueLabel,
-    MlModelFeature,
-    MlModelParameterConfig,
-    MlModelParameterConfigRequest,
-    MlModelRead,
-    MlModelRequestAuthorizationConfig,
-    MlModelRequestAuthorizationConfigRequest,
-    MlModelRequestAuthorizationConfigTypeEnum,
-    MlModelRequestConfig,
-    MlModelRequestConfigRequest,
-    MlModelResponseConfig,
-    MlModelResponseConfigRequest,
-    MlModelTokenizerConfig,
-    MlModelTokenizerConfigRequest,
     MlModelUsage,
     NamedScenarioInputChatHistoryVariableValueRequest,
     NamedScenarioInputJsonVariableValueRequest,
@@ -210,28 +200,7 @@ from .types import (
     OpenAiVectorizerTextEmbedding3SmallRequest,
     OpenAiVectorizerTextEmbeddingAda002,
     OpenAiVectorizerTextEmbeddingAda002Request,
-    OpenApiArrayProperty,
-    OpenApiArrayPropertyRequest,
-    OpenApiBooleanProperty,
-    OpenApiBooleanPropertyRequest,
-    OpenApiConstProperty,
-    OpenApiConstPropertyRequest,
-    OpenApiIntegerProperty,
-    OpenApiIntegerPropertyRequest,
-    OpenApiNumberProperty,
-    OpenApiNumberPropertyRequest,
-    OpenApiObjectProperty,
-    OpenApiObjectPropertyRequest,
-    OpenApiOneOfProperty,
-    OpenApiOneOfPropertyRequest,
-    OpenApiProperty,
-    OpenApiPropertyRequest,
-    OpenApiRefProperty,
-    OpenApiRefPropertyRequest,
-    OpenApiStringProperty,
-    OpenApiStringPropertyRequest,
     PaginatedDocumentIndexReadList,
-    PaginatedMlModelReadList,
     PaginatedSlimDeploymentReadList,
     PaginatedSlimDocumentList,
     PaginatedSlimWorkflowDeploymentList,
@@ -239,20 +208,29 @@ from .types import (
     PaginatedTestSuiteTestCaseList,
     PdfSearchResultMetaSource,
     PdfSearchResultMetaSourceRequest,
+    PlainTextPromptBlockRequest,
     ProcessingFailureReasonEnum,
     ProcessingStateEnum,
-    PromptDeploymentExpandMetaRequestRequest,
+    PromptBlockRequest,
+    PromptBlockState,
+    PromptDeploymentExpandMetaRequest,
     PromptDeploymentInputRequest,
     PromptExecutionMeta,
     PromptNodeExecutionMeta,
     PromptNodeResult,
     PromptNodeResultData,
     PromptOutput,
+    PromptParametersRequest,
+    PromptRequestChatHistoryInputRequest,
+    PromptRequestInputRequest,
+    PromptRequestJsonInputRequest,
+    PromptRequestStringInputRequest,
     RawPromptExecutionOverridesRequest,
     ReductoChunkerConfig,
     ReductoChunkerConfigRequest,
     ReductoChunking,
     ReductoChunkingRequest,
+    RejectedAdHocExecutePromptEvent,
     RejectedExecutePromptEvent,
     RejectedExecutePromptResponse,
     RejectedExecuteWorkflowWorkflowResultEvent,
@@ -260,6 +238,8 @@ from .types import (
     RejectedWorkflowNodeResultEvent,
     ReleaseTagSource,
     ReplaceTestSuiteTestCaseRequest,
+    RichTextChildBlockRequest,
+    RichTextPromptBlockRequest,
     SandboxScenario,
     ScenarioInput,
     ScenarioInputChatHistoryVariableValue,
@@ -285,6 +265,7 @@ from .types import (
     SlimDeploymentRead,
     SlimDocument,
     SlimWorkflowDeployment,
+    StreamingAdHocExecutePromptEvent,
     StreamingExecutePromptEvent,
     StreamingPromptExecutionMeta,
     StreamingWorkflowNodeResultEvent,
@@ -377,22 +358,21 @@ from .types import (
     TestSuiteTestCaseReplacedBulkResult,
     TestSuiteTestCaseReplacedBulkResultData,
     TestSuiteTestCaseUpsertBulkOperationRequest,
-    TikTokenTokenizerConfig,
-    TikTokenTokenizerConfigRequest,
     TokenOverlappingWindowChunkerConfig,
     TokenOverlappingWindowChunkerConfigRequest,
     TokenOverlappingWindowChunking,
     TokenOverlappingWindowChunkingRequest,
     UploadDocumentResponse,
     UpsertTestSuiteTestCaseRequest,
+    VariablePromptBlockRequest,
     VellumError,
     VellumErrorCodeEnum,
     VellumErrorRequest,
     VellumImage,
     VellumImageRequest,
     VellumVariable,
+    VellumVariableRequest,
     VellumVariableType,
-    VisibilityEnum,
     WorkflowDeploymentRead,
     WorkflowEventError,
     WorkflowExecutionActualChatHistoryRequest,
@@ -440,11 +420,11 @@ from .resources import (
     DeploymentsListRequestStatus,
     DocumentIndexesListRequestStatus,
     WorkflowDeploymentsListRequestStatus,
+    ad_hoc,
     deployments,
     document_indexes,
     documents,
     folder_entities,
-    ml_models,
     sandboxes,
     test_suite_runs,
     test_suites,
@@ -456,6 +436,12 @@ from .environment import VellumEnvironment
 from .version import __version__
 
 __all__ = [
+    "AdHocExecutePromptEvent",
+    "AdHocExpandMetaRequest",
+    "AdHocFulfilledPromptExecutionMeta",
+    "AdHocInitiatedPromptExecutionMeta",
+    "AdHocRejectedPromptExecutionMeta",
+    "AdHocStreamingPromptExecutionMeta",
     "AddOpenaiApiKeyEnum",
     "ApiNodeResult",
     "ApiNodeResultData",
@@ -478,6 +464,8 @@ __all__ = [
     "ChatMessage",
     "ChatMessageContent",
     "ChatMessageContentRequest",
+    "ChatMessagePromptBlockPropertiesRequest",
+    "ChatMessagePromptBlockRequest",
     "ChatMessageRequest",
     "ChatMessageRole",
     "CodeExecutionNodeArrayResult",
@@ -516,6 +504,8 @@ __all__ = [
     "EnrichedNormalizedCompletion",
     "EntityStatus",
     "EnvironmentEnum",
+    "EphemeralPromptCacheConfigRequest",
+    "EphemeralPromptCacheConfigTypeEnum",
     "ErrorVariableValue",
     "ErrorVellumValue",
     "ErrorVellumValueRequest",
@@ -536,6 +526,7 @@ __all__ = [
     "ExternalTestCaseExecutionRequest",
     "FinishReasonEnum",
     "ForbiddenError",
+    "FulfilledAdHocExecutePromptEvent",
     "FulfilledEnum",
     "FulfilledExecutePromptEvent",
     "FulfilledExecutePromptResponse",
@@ -551,6 +542,8 @@ __all__ = [
     "FunctionCallVariableValue",
     "FunctionCallVellumValue",
     "FunctionCallVellumValueRequest",
+    "FunctionDefinitionPromptBlockPropertiesRequest",
+    "FunctionDefinitionPromptBlockRequest",
     "GenerateOptionsRequest",
     "GenerateRequest",
     "GenerateResponse",
@@ -562,9 +555,6 @@ __all__ = [
     "GenerateStreamResultData",
     "HkunlpInstructorXlVectorizer",
     "HkunlpInstructorXlVectorizerRequest",
-    "HostedByEnum",
-    "HuggingFaceTokenizerConfig",
-    "HuggingFaceTokenizerConfigRequest",
     "ImageChatMessageContent",
     "ImageChatMessageContentRequest",
     "ImageVariableValue",
@@ -573,6 +563,7 @@ __all__ = [
     "IndexingConfigVectorizer",
     "IndexingConfigVectorizerRequest",
     "IndexingStateEnum",
+    "InitiatedAdHocExecutePromptEvent",
     "InitiatedExecutePromptEvent",
     "InitiatedPromptExecutionMeta",
     "InitiatedWorkflowNodeResultEvent",
@@ -580,6 +571,8 @@ __all__ = [
     "InstructorVectorizerConfigRequest",
     "InternalServerError",
     "IterationStateEnum",
+    "JinjaPromptBlockPropertiesRequest",
+    "JinjaPromptBlockRequest",
     "JsonInputRequest",
     "JsonVariableValue",
     "JsonVellumValue",
@@ -594,29 +587,6 @@ __all__ = [
     "MetadataFilterRuleCombinator",
     "MetadataFilterRuleRequest",
     "MetricNodeResult",
-    "MlModelDeveloper",
-    "MlModelDeveloperEnumValueLabel",
-    "MlModelDisplayConfigLabelled",
-    "MlModelDisplayConfigRequest",
-    "MlModelDisplayTag",
-    "MlModelDisplayTagEnumValueLabel",
-    "MlModelExecConfig",
-    "MlModelExecConfigRequest",
-    "MlModelFamily",
-    "MlModelFamilyEnumValueLabel",
-    "MlModelFeature",
-    "MlModelParameterConfig",
-    "MlModelParameterConfigRequest",
-    "MlModelRead",
-    "MlModelRequestAuthorizationConfig",
-    "MlModelRequestAuthorizationConfigRequest",
-    "MlModelRequestAuthorizationConfigTypeEnum",
-    "MlModelRequestConfig",
-    "MlModelRequestConfigRequest",
-    "MlModelResponseConfig",
-    "MlModelResponseConfigRequest",
-    "MlModelTokenizerConfig",
-    "MlModelTokenizerConfigRequest",
     "MlModelUsage",
     "NamedScenarioInputChatHistoryVariableValueRequest",
     "NamedScenarioInputJsonVariableValueRequest",
@@ -672,28 +642,7 @@ __all__ = [
     "OpenAiVectorizerTextEmbedding3SmallRequest",
     "OpenAiVectorizerTextEmbeddingAda002",
     "OpenAiVectorizerTextEmbeddingAda002Request",
-    "OpenApiArrayProperty",
-    "OpenApiArrayPropertyRequest",
-    "OpenApiBooleanProperty",
-    "OpenApiBooleanPropertyRequest",
-    "OpenApiConstProperty",
-    "OpenApiConstPropertyRequest",
-    "OpenApiIntegerProperty",
-    "OpenApiIntegerPropertyRequest",
-    "OpenApiNumberProperty",
-    "OpenApiNumberPropertyRequest",
-    "OpenApiObjectProperty",
-    "OpenApiObjectPropertyRequest",
-    "OpenApiOneOfProperty",
-    "OpenApiOneOfPropertyRequest",
-    "OpenApiProperty",
-    "OpenApiPropertyRequest",
-    "OpenApiRefProperty",
-    "OpenApiRefPropertyRequest",
-    "OpenApiStringProperty",
-    "OpenApiStringPropertyRequest",
     "PaginatedDocumentIndexReadList",
-    "PaginatedMlModelReadList",
     "PaginatedSlimDeploymentReadList",
     "PaginatedSlimDocumentList",
     "PaginatedSlimWorkflowDeploymentList",
@@ -701,20 +650,29 @@ __all__ = [
     "PaginatedTestSuiteTestCaseList",
     "PdfSearchResultMetaSource",
     "PdfSearchResultMetaSourceRequest",
+    "PlainTextPromptBlockRequest",
     "ProcessingFailureReasonEnum",
     "ProcessingStateEnum",
-    "PromptDeploymentExpandMetaRequestRequest",
+    "PromptBlockRequest",
+    "PromptBlockState",
+    "PromptDeploymentExpandMetaRequest",
     "PromptDeploymentInputRequest",
     "PromptExecutionMeta",
     "PromptNodeExecutionMeta",
     "PromptNodeResult",
     "PromptNodeResultData",
     "PromptOutput",
+    "PromptParametersRequest",
+    "PromptRequestChatHistoryInputRequest",
+    "PromptRequestInputRequest",
+    "PromptRequestJsonInputRequest",
+    "PromptRequestStringInputRequest",
     "RawPromptExecutionOverridesRequest",
     "ReductoChunkerConfig",
     "ReductoChunkerConfigRequest",
     "ReductoChunking",
     "ReductoChunkingRequest",
+    "RejectedAdHocExecutePromptEvent",
     "RejectedExecutePromptEvent",
     "RejectedExecutePromptResponse",
     "RejectedExecuteWorkflowWorkflowResultEvent",
@@ -722,6 +680,8 @@ __all__ = [
     "RejectedWorkflowNodeResultEvent",
     "ReleaseTagSource",
     "ReplaceTestSuiteTestCaseRequest",
+    "RichTextChildBlockRequest",
+    "RichTextPromptBlockRequest",
     "SandboxScenario",
     "ScenarioInput",
     "ScenarioInputChatHistoryVariableValue",
@@ -747,6 +707,7 @@ __all__ = [
     "SlimDeploymentRead",
     "SlimDocument",
     "SlimWorkflowDeployment",
+    "StreamingAdHocExecutePromptEvent",
     "StreamingExecutePromptEvent",
     "StreamingPromptExecutionMeta",
     "StreamingWorkflowNodeResultEvent",
@@ -839,14 +800,13 @@ __all__ = [
     "TestSuiteTestCaseReplacedBulkResult",
     "TestSuiteTestCaseReplacedBulkResultData",
     "TestSuiteTestCaseUpsertBulkOperationRequest",
-    "TikTokenTokenizerConfig",
-    "TikTokenTokenizerConfigRequest",
     "TokenOverlappingWindowChunkerConfig",
     "TokenOverlappingWindowChunkerConfigRequest",
     "TokenOverlappingWindowChunking",
     "TokenOverlappingWindowChunkingRequest",
     "UploadDocumentResponse",
     "UpsertTestSuiteTestCaseRequest",
+    "VariablePromptBlockRequest",
     "Vellum",
     "VellumEnvironment",
     "VellumError",
@@ -855,8 +815,8 @@ __all__ = [
     "VellumImage",
     "VellumImageRequest",
     "VellumVariable",
+    "VellumVariableRequest",
     "VellumVariableType",
-    "VisibilityEnum",
     "WorkflowDeploymentRead",
     "WorkflowDeploymentsListRequestStatus",
     "WorkflowEventError",
@@ -900,11 +860,11 @@ __all__ = [
     "WorkflowResultEventOutputDataString",
     "WorkflowStreamEvent",
     "__version__",
+    "ad_hoc",
     "deployments",
     "document_indexes",
     "documents",
     "folder_entities",
-    "ml_models",
     "sandboxes",
     "test_suite_runs",
     "test_suites",

vellum/client.py

@@ -4,18 +4,18 @@ import typing
 from .environment import VellumEnvironment
 import httpx
 from .core.client_wrapper import SyncClientWrapper
+from .resources.ad_hoc.client import AdHocClient
 from .resources.deployments.client import DeploymentsClient
 from .resources.document_indexes.client import DocumentIndexesClient
 from .resources.documents.client import DocumentsClient
 from .resources.folder_entities.client import FolderEntitiesClient
-from .resources.ml_models.client import MlModelsClient
 from .resources.sandboxes.client import SandboxesClient
 from .resources.test_suite_runs.client import TestSuiteRunsClient
 from .resources.test_suites.client import TestSuitesClient
 from .resources.workflow_deployments.client import WorkflowDeploymentsClient
 from .resources.workflow_sandboxes.client import WorkflowSandboxesClient
 from .types.prompt_deployment_input_request import PromptDeploymentInputRequest
-from .types.prompt_deployment_expand_meta_request_request import PromptDeploymentExpandMetaRequestRequest
+from .types.prompt_deployment_expand_meta_request import PromptDeploymentExpandMetaRequest
 from .types.raw_prompt_execution_overrides_request import RawPromptExecutionOverridesRequest
 from .core.request_options import RequestOptions
 from .types.execute_prompt_response import ExecutePromptResponse
@@ -42,11 +42,11 @@ from .types.search_response import SearchResponse
 from .types.submit_completion_actual_request import SubmitCompletionActualRequest
 from .types.submit_workflow_execution_actual_request import SubmitWorkflowExecutionActualRequest
 from .core.client_wrapper import AsyncClientWrapper
+from .resources.ad_hoc.client import AsyncAdHocClient
 from .resources.deployments.client import AsyncDeploymentsClient
 from .resources.document_indexes.client import AsyncDocumentIndexesClient
 from .resources.documents.client import AsyncDocumentsClient
 from .resources.folder_entities.client import AsyncFolderEntitiesClient
-from .resources.ml_models.client import AsyncMlModelsClient
 from .resources.sandboxes.client import AsyncSandboxesClient
 from .resources.test_suite_runs.client import AsyncTestSuiteRunsClient
 from .resources.test_suites.client import AsyncTestSuitesClient
@@ -111,11 +111,11 @@ class Vellum:
             else httpx.Client(timeout=_defaulted_timeout),
             timeout=_defaulted_timeout,
         )
+        self.ad_hoc = AdHocClient(client_wrapper=self._client_wrapper)
         self.deployments = DeploymentsClient(client_wrapper=self._client_wrapper)
         self.document_indexes = DocumentIndexesClient(client_wrapper=self._client_wrapper)
         self.documents = DocumentsClient(client_wrapper=self._client_wrapper)
         self.folder_entities = FolderEntitiesClient(client_wrapper=self._client_wrapper)
-        self.ml_models = MlModelsClient(client_wrapper=self._client_wrapper)
         self.sandboxes = SandboxesClient(client_wrapper=self._client_wrapper)
         self.test_suite_runs = TestSuiteRunsClient(client_wrapper=self._client_wrapper)
         self.test_suites = TestSuitesClient(client_wrapper=self._client_wrapper)
@@ -130,7 +130,7 @@ class Vellum:
         prompt_deployment_name: typing.Optional[str] = OMIT,
         release_tag: typing.Optional[str] = OMIT,
         external_id: typing.Optional[str] = OMIT,
-        expand_meta: typing.Optional[PromptDeploymentExpandMetaRequestRequest] = OMIT,
+        expand_meta: typing.Optional[PromptDeploymentExpandMetaRequest] = OMIT,
         raw_overrides: typing.Optional[RawPromptExecutionOverridesRequest] = OMIT,
         expand_raw: typing.Optional[typing.Sequence[str]] = OMIT,
         metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
@@ -156,7 +156,7 @@ class Vellum:
         external_id : typing.Optional[str]
             Optionally include a unique identifier for tracking purposes. Must be unique within a given Prompt Deployment.
 
-        expand_meta : typing.Optional[PromptDeploymentExpandMetaRequestRequest]
+        expand_meta : typing.Optional[PromptDeploymentExpandMetaRequest]
             An optionally specified configuration used to opt in to including additional metadata about this prompt execution in the API response. Corresponding values will be returned under the `meta` key of the API response.
 
         raw_overrides : typing.Optional[RawPromptExecutionOverridesRequest]
@@ -272,7 +272,7 @@ class Vellum:
         prompt_deployment_name: typing.Optional[str] = OMIT,
         release_tag: typing.Optional[str] = OMIT,
         external_id: typing.Optional[str] = OMIT,
-        expand_meta: typing.Optional[PromptDeploymentExpandMetaRequestRequest] = OMIT,
+        expand_meta: typing.Optional[PromptDeploymentExpandMetaRequest] = OMIT,
         raw_overrides: typing.Optional[RawPromptExecutionOverridesRequest] = OMIT,
         expand_raw: typing.Optional[typing.Sequence[str]] = OMIT,
         metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
@@ -298,7 +298,7 @@ class Vellum:
         external_id : typing.Optional[str]
             Optionally include a unique identifier for tracking purposes. Must be unique within a given Prompt Deployment.
 
-        expand_meta : typing.Optional[PromptDeploymentExpandMetaRequestRequest]
+        expand_meta : typing.Optional[PromptDeploymentExpandMetaRequest]
             An optionally specified configuration used to opt in to including additional metadata about this prompt execution in the API response. Corresponding values will be returned under the `meta` key of the API response.
 
         raw_overrides : typing.Optional[RawPromptExecutionOverridesRequest]
@@ -321,7 +321,7 @@ class Vellum:
         Examples
         --------
         from vellum import (
-            PromptDeploymentExpandMetaRequestRequest,
+            PromptDeploymentExpandMetaRequest,
             RawPromptExecutionOverridesRequest,
             StringInputRequest,
             Vellum,
@@ -341,7 +341,7 @@ class Vellum:
             prompt_deployment_name="string",
             release_tag="string",
             external_id="string",
-            expand_meta=PromptDeploymentExpandMetaRequestRequest(
+            expand_meta=PromptDeploymentExpandMetaRequest(
                 model_name=True,
                 usage=True,
                 finish_reason=True,
@@ -1278,11 +1278,11 @@ class AsyncVellum:
             else httpx.AsyncClient(timeout=_defaulted_timeout),
             timeout=_defaulted_timeout,
         )
+        self.ad_hoc = AsyncAdHocClient(client_wrapper=self._client_wrapper)
         self.deployments = AsyncDeploymentsClient(client_wrapper=self._client_wrapper)
         self.document_indexes = AsyncDocumentIndexesClient(client_wrapper=self._client_wrapper)
         self.documents = AsyncDocumentsClient(client_wrapper=self._client_wrapper)
         self.folder_entities = AsyncFolderEntitiesClient(client_wrapper=self._client_wrapper)
-        self.ml_models = AsyncMlModelsClient(client_wrapper=self._client_wrapper)
         self.sandboxes = AsyncSandboxesClient(client_wrapper=self._client_wrapper)
         self.test_suite_runs = AsyncTestSuiteRunsClient(client_wrapper=self._client_wrapper)
         self.test_suites = AsyncTestSuitesClient(client_wrapper=self._client_wrapper)
@@ -1297,7 +1297,7 @@ class AsyncVellum:
         prompt_deployment_name: typing.Optional[str] = OMIT,
         release_tag: typing.Optional[str] = OMIT,
         external_id: typing.Optional[str] = OMIT,
-        expand_meta: typing.Optional[PromptDeploymentExpandMetaRequestRequest] = OMIT,
+        expand_meta: typing.Optional[PromptDeploymentExpandMetaRequest] = OMIT,
         raw_overrides: typing.Optional[RawPromptExecutionOverridesRequest] = OMIT,
         expand_raw: typing.Optional[typing.Sequence[str]] = OMIT,
         metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
@@ -1323,7 +1323,7 @@ class AsyncVellum:
         external_id : typing.Optional[str]
             Optionally include a unique identifier for tracking purposes. Must be unique within a given Prompt Deployment.
 
-        expand_meta : typing.Optional[PromptDeploymentExpandMetaRequestRequest]
+        expand_meta : typing.Optional[PromptDeploymentExpandMetaRequest]
             An optionally specified configuration used to opt in to including additional metadata about this prompt execution in the API response. Corresponding values will be returned under the `meta` key of the API response.
 
         raw_overrides : typing.Optional[RawPromptExecutionOverridesRequest]
@@ -1447,7 +1447,7 @@ class AsyncVellum:
         prompt_deployment_name: typing.Optional[str] = OMIT,
         release_tag: typing.Optional[str] = OMIT,
         external_id: typing.Optional[str] = OMIT,
-        expand_meta: typing.Optional[PromptDeploymentExpandMetaRequestRequest] = OMIT,
+        expand_meta: typing.Optional[PromptDeploymentExpandMetaRequest] = OMIT,
         raw_overrides: typing.Optional[RawPromptExecutionOverridesRequest] = OMIT,
         expand_raw: typing.Optional[typing.Sequence[str]] = OMIT,
         metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
@@ -1473,7 +1473,7 @@ class AsyncVellum:
         external_id : typing.Optional[str]
             Optionally include a unique identifier for tracking purposes. Must be unique within a given Prompt Deployment.
 
-        expand_meta : typing.Optional[PromptDeploymentExpandMetaRequestRequest]
+        expand_meta : typing.Optional[PromptDeploymentExpandMetaRequest]
             An optionally specified configuration used to opt in to including additional metadata about this prompt execution in the API response. Corresponding values will be returned under the `meta` key of the API response.
 
         raw_overrides : typing.Optional[RawPromptExecutionOverridesRequest]
@@ -1499,7 +1499,7 @@ class AsyncVellum:
 
         from vellum import (
             AsyncVellum,
-            PromptDeploymentExpandMetaRequestRequest,
+            PromptDeploymentExpandMetaRequest,
             RawPromptExecutionOverridesRequest,
             StringInputRequest,
         )
@@ -1521,7 +1521,7 @@ class AsyncVellum:
                 prompt_deployment_name="string",
                 release_tag="string",
                 external_id="string",
-                expand_meta=PromptDeploymentExpandMetaRequestRequest(
+                expand_meta=PromptDeploymentExpandMetaRequest(
                     model_name=True,
                     usage=True,
                     finish_reason=True,

vellum/core/client_wrapper.py

@@ -17,7 +17,7 @@ class BaseClientWrapper:
         headers: typing.Dict[str, str] = {
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "vellum-ai",
-            "X-Fern-SDK-Version": "0.8.4",
+            "X-Fern-SDK-Version": "0.8.6",
         }
         headers["X_API_KEY"] = self.api_key
         return headers

vellum/resources/__init__.py

@@ -1,11 +1,11 @@
 # This file was auto-generated by Fern from our API Definition.
 
 from . import (
+    ad_hoc,
     deployments,
     document_indexes,
     documents,
     folder_entities,
-    ml_models,
     sandboxes,
     test_suite_runs,
     test_suites,
@@ -20,11 +20,11 @@ __all__ = [
     "DeploymentsListRequestStatus",
     "DocumentIndexesListRequestStatus",
     "WorkflowDeploymentsListRequestStatus",
+    "ad_hoc",
     "deployments",
     "document_indexes",
     "documents",
     "folder_entities",
-    "ml_models",
     "sandboxes",
     "test_suite_runs",
     "test_suites",