vellum-ai 0.8.6__tar.gz → 0.8.9__tar.gz

{vellum_ai-0.8.6 → vellum_ai-0.8.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vellum-ai
-Version: 0.8.6
+Version: 0.8.9
 Summary: 
 License: MIT
 Requires-Python: >=3.8,<4.0

{vellum_ai-0.8.6 → vellum_ai-0.8.9}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "vellum-ai"
-version = "0.8.6"
+version = "0.8.9"
 description = ""
 readme = "README.md"
 authors = []

{vellum_ai-0.8.6 → vellum_ai-0.8.9}/src/vellum/__init__.py

@@ -209,6 +209,7 @@ from .types import (
     PdfSearchResultMetaSource,
     PdfSearchResultMetaSourceRequest,
     PlainTextPromptBlockRequest,
+    Price,
     ProcessingFailureReasonEnum,
     ProcessingStateEnum,
     PromptBlockRequest,
@@ -333,6 +334,7 @@ from .types import (
     TestSuiteRunExternalExecConfigDataRequest,
     TestSuiteRunExternalExecConfigRequest,
     TestSuiteRunMetricErrorOutput,
+    TestSuiteRunMetricJsonOutput,
     TestSuiteRunMetricNumberOutput,
     TestSuiteRunMetricOutput,
     TestSuiteRunMetricStringOutput,
@@ -362,6 +364,7 @@ from .types import (
     TokenOverlappingWindowChunkerConfigRequest,
     TokenOverlappingWindowChunking,
     TokenOverlappingWindowChunkingRequest,
+    UnitEnum,
     UploadDocumentResponse,
     UpsertTestSuiteTestCaseRequest,
     VariablePromptBlockRequest,
@@ -651,6 +654,7 @@ __all__ = [
     "PdfSearchResultMetaSource",
     "PdfSearchResultMetaSourceRequest",
     "PlainTextPromptBlockRequest",
+    "Price",
     "ProcessingFailureReasonEnum",
     "ProcessingStateEnum",
     "PromptBlockRequest",
@@ -775,6 +779,7 @@ __all__ = [
     "TestSuiteRunExternalExecConfigDataRequest",
     "TestSuiteRunExternalExecConfigRequest",
     "TestSuiteRunMetricErrorOutput",
+    "TestSuiteRunMetricJsonOutput",
     "TestSuiteRunMetricNumberOutput",
     "TestSuiteRunMetricOutput",
     "TestSuiteRunMetricStringOutput",
@@ -804,6 +809,7 @@ __all__ = [
     "TokenOverlappingWindowChunkerConfigRequest",
     "TokenOverlappingWindowChunking",
     "TokenOverlappingWindowChunkingRequest",
+    "UnitEnum",
     "UploadDocumentResponse",
     "UpsertTestSuiteTestCaseRequest",
     "VariablePromptBlockRequest",

{vellum_ai-0.8.6 → vellum_ai-0.8.9}/src/vellum/client.py

@@ -344,6 +344,7 @@ class Vellum:
             expand_meta=PromptDeploymentExpandMetaRequest(
                 model_name=True,
                 usage=True,
+                cost=True,
                 finish_reason=True,
                 latency=True,
                 deployment_release_tag=True,
@@ -449,6 +450,7 @@ class Vellum:
         workflow_deployment_name: typing.Optional[str] = OMIT,
         release_tag: typing.Optional[str] = OMIT,
         external_id: typing.Optional[str] = OMIT,
+        metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> ExecuteWorkflowResponse:
         """
@@ -474,6 +476,9 @@ class Vellum:
         external_id : typing.Optional[str]
             Optionally include a unique identifier for tracking purposes. Must be unique for a given workflow deployment.
 
+        metadata : typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]]
+            Arbitrary JSON metadata associated with this request. Can be used to capture additional monitoring data such as user id, session id, etc. for future analysis.
+
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
@@ -509,6 +514,7 @@ class Vellum:
                 "workflow_deployment_name": workflow_deployment_name,
                 "release_tag": release_tag,
                 "external_id": external_id,
+                "metadata": metadata,
             },
             request_options=request_options,
             omit=OMIT,
@@ -567,6 +573,7 @@ class Vellum:
         release_tag: typing.Optional[str] = OMIT,
         external_id: typing.Optional[str] = OMIT,
         event_types: typing.Optional[typing.Sequence[WorkflowExecutionEventType]] = OMIT,
+        metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> typing.Iterator[WorkflowStreamEvent]:
         """
@@ -595,6 +602,9 @@ class Vellum:
         event_types : typing.Optional[typing.Sequence[WorkflowExecutionEventType]]
             Optionally specify which events you want to receive. Defaults to only WORKFLOW events. Note that the schema of non-WORKFLOW events is unstable and should be used with caution.
 
+        metadata : typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]]
+            Arbitrary JSON metadata associated with this request. Can be used to capture additional monitoring data such as user id, session id, etc. for future analysis.
+
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
@@ -629,6 +639,7 @@ class Vellum:
             release_tag="string",
             external_id="string",
             event_types=["NODE"],
+            metadata={"string": {"key": "value"}},
         )
         for chunk in response:
             yield chunk
@@ -645,6 +656,7 @@ class Vellum:
                 "release_tag": release_tag,
                 "external_id": external_id,
                 "event_types": event_types,
+                "metadata": metadata,
             },
             request_options=request_options,
             omit=OMIT,
@@ -1524,6 +1536,7 @@ class AsyncVellum:
                 expand_meta=PromptDeploymentExpandMetaRequest(
                     model_name=True,
                     usage=True,
+                    cost=True,
                     finish_reason=True,
                     latency=True,
                     deployment_release_tag=True,
@@ -1632,6 +1645,7 @@ class AsyncVellum:
         workflow_deployment_name: typing.Optional[str] = OMIT,
         release_tag: typing.Optional[str] = OMIT,
         external_id: typing.Optional[str] = OMIT,
+        metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> ExecuteWorkflowResponse:
         """
@@ -1657,6 +1671,9 @@ class AsyncVellum:
         external_id : typing.Optional[str]
             Optionally include a unique identifier for tracking purposes. Must be unique for a given workflow deployment.
 
+        metadata : typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]]
+            Arbitrary JSON metadata associated with this request. Can be used to capture additional monitoring data such as user id, session id, etc. for future analysis.
+
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
@@ -1700,6 +1717,7 @@ class AsyncVellum:
                 "workflow_deployment_name": workflow_deployment_name,
                 "release_tag": release_tag,
                 "external_id": external_id,
+                "metadata": metadata,
             },
             request_options=request_options,
             omit=OMIT,
@@ -1758,6 +1776,7 @@ class AsyncVellum:
         release_tag: typing.Optional[str] = OMIT,
         external_id: typing.Optional[str] = OMIT,
         event_types: typing.Optional[typing.Sequence[WorkflowExecutionEventType]] = OMIT,
+        metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> typing.AsyncIterator[WorkflowStreamEvent]:
         """
@@ -1786,6 +1805,9 @@ class AsyncVellum:
         event_types : typing.Optional[typing.Sequence[WorkflowExecutionEventType]]
             Optionally specify which events you want to receive. Defaults to only WORKFLOW events. Note that the schema of non-WORKFLOW events is unstable and should be used with caution.
 
+        metadata : typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]]
+            Arbitrary JSON metadata associated with this request. Can be used to capture additional monitoring data such as user id, session id, etc. for future analysis.
+
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
@@ -1825,6 +1847,7 @@ class AsyncVellum:
                 release_tag="string",
                 external_id="string",
                 event_types=["NODE"],
+                metadata={"string": {"key": "value"}},
             )
             async for chunk in response:
                 yield chunk
@@ -1844,6 +1867,7 @@ class AsyncVellum:
                 "release_tag": release_tag,
                 "external_id": external_id,
                 "event_types": event_types,
+                "metadata": metadata,
             },
             request_options=request_options,
             omit=OMIT,

{vellum_ai-0.8.6 → vellum_ai-0.8.9}/src/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": "0.8.6",
+            "X-Fern-SDK-Version": "0.8.9",
         }
         headers["X_API_KEY"] = self.api_key
         return headers

{vellum_ai-0.8.6 → vellum_ai-0.8.9}/src/vellum/types/__init__.py

@@ -216,6 +216,7 @@ from .paginated_test_suite_test_case_list import PaginatedTestSuiteTestCaseList
 from .pdf_search_result_meta_source import PdfSearchResultMetaSource
 from .pdf_search_result_meta_source_request import PdfSearchResultMetaSourceRequest
 from .plain_text_prompt_block_request import PlainTextPromptBlockRequest
+from .price import Price
 from .processing_failure_reason_enum import ProcessingFailureReasonEnum
 from .processing_state_enum import ProcessingStateEnum
 from .prompt_block_request import PromptBlockRequest
@@ -342,6 +343,7 @@ from .test_suite_run_external_exec_config_data import TestSuiteRunExternalExecCo
 from .test_suite_run_external_exec_config_data_request import TestSuiteRunExternalExecConfigDataRequest
 from .test_suite_run_external_exec_config_request import TestSuiteRunExternalExecConfigRequest
 from .test_suite_run_metric_error_output import TestSuiteRunMetricErrorOutput
+from .test_suite_run_metric_json_output import TestSuiteRunMetricJsonOutput
 from .test_suite_run_metric_number_output import TestSuiteRunMetricNumberOutput
 from .test_suite_run_metric_output import TestSuiteRunMetricOutput
 from .test_suite_run_metric_string_output import TestSuiteRunMetricStringOutput
@@ -373,6 +375,7 @@ from .token_overlapping_window_chunker_config import TokenOverlappingWindowChunk
 from .token_overlapping_window_chunker_config_request import TokenOverlappingWindowChunkerConfigRequest
 from .token_overlapping_window_chunking import TokenOverlappingWindowChunking
 from .token_overlapping_window_chunking_request import TokenOverlappingWindowChunkingRequest
+from .unit_enum import UnitEnum
 from .upload_document_response import UploadDocumentResponse
 from .upsert_test_suite_test_case_request import UpsertTestSuiteTestCaseRequest
 from .variable_prompt_block_request import VariablePromptBlockRequest
@@ -635,6 +638,7 @@ __all__ = [
     "PdfSearchResultMetaSource",
     "PdfSearchResultMetaSourceRequest",
     "PlainTextPromptBlockRequest",
+    "Price",
     "ProcessingFailureReasonEnum",
     "ProcessingStateEnum",
     "PromptBlockRequest",
@@ -759,6 +763,7 @@ __all__ = [
     "TestSuiteRunExternalExecConfigDataRequest",
     "TestSuiteRunExternalExecConfigRequest",
     "TestSuiteRunMetricErrorOutput",
+    "TestSuiteRunMetricJsonOutput",
     "TestSuiteRunMetricNumberOutput",
     "TestSuiteRunMetricOutput",
     "TestSuiteRunMetricStringOutput",
@@ -788,6 +793,7 @@ __all__ = [
     "TokenOverlappingWindowChunkerConfigRequest",
     "TokenOverlappingWindowChunking",
     "TokenOverlappingWindowChunkingRequest",
+    "UnitEnum",
     "UploadDocumentResponse",
     "UpsertTestSuiteTestCaseRequest",
     "VariablePromptBlockRequest",

{vellum_ai-0.8.6 → vellum_ai-0.8.9}/src/vellum/types/ad_hoc_expand_meta_request.py

@@ -7,7 +7,11 @@ from ..core.pydantic_utilities import IS_PYDANTIC_V2
 
 
 class AdHocExpandMetaRequest(UniversalBaseModel):
-    cost: typing.Optional[bool] = None
+    cost: typing.Optional[bool] = pydantic.Field(default=None)
+    """
+    If enabled, the response will include model host cost tracking. This may increase latency for some model hosts.
+    """
+
     model_name: typing.Optional[bool] = pydantic.Field(default=None)
     """
     If enabled, the response will include the model identifier representing the ML Model invoked by the Prompt.

vellum_ai-0.8.9/src/vellum/types/price.py

@@ -0,0 +1,21 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from ..core.pydantic_utilities import UniversalBaseModel
+from .unit_enum import UnitEnum
+from ..core.pydantic_utilities import IS_PYDANTIC_V2
+import typing
+import pydantic
+
+
+class Price(UniversalBaseModel):
+    value: float
+    unit: UnitEnum = "USD"
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

{vellum_ai-0.8.6 → vellum_ai-0.8.9}/src/vellum/types/prompt_deployment_expand_meta_request.py

@@ -17,6 +17,11 @@ class PromptDeploymentExpandMetaRequest(UniversalBaseModel):
     If enabled, the response will include model host usage tracking. This may increase latency for some model hosts.
     """
 
+    cost: typing.Optional[bool] = pydantic.Field(default=None)
+    """
+    If enabled, the response will include model host cost tracking. This may increase latency for some model hosts.
+    """
+
     finish_reason: typing.Optional[bool] = pydantic.Field(default=None)
     """
     If enabled, the response will include the reason provided by the model for why the execution finished.

{vellum_ai-0.8.6 → vellum_ai-0.8.9}/src/vellum/types/prompt_execution_meta.py

@@ -4,6 +4,7 @@ from ..core.pydantic_utilities import UniversalBaseModel
 import typing
 from .finish_reason_enum import FinishReasonEnum
 from .ml_model_usage import MlModelUsage
+from .price import Price
 from ..core.pydantic_utilities import IS_PYDANTIC_V2
 import pydantic
 
@@ -19,6 +20,7 @@ class PromptExecutionMeta(UniversalBaseModel):
     prompt_version_id: typing.Optional[str] = None
     finish_reason: typing.Optional[FinishReasonEnum] = None
     usage: typing.Optional[MlModelUsage] = None
+    cost: typing.Optional[Price] = None
 
     if IS_PYDANTIC_V2:
         model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2

vellum_ai-0.8.9/src/vellum/types/test_suite_run_metric_json_output.py

@@ -0,0 +1,25 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from ..core.pydantic_utilities import UniversalBaseModel
+import typing
+from ..core.pydantic_utilities import IS_PYDANTIC_V2
+import pydantic
+
+
+class TestSuiteRunMetricJsonOutput(UniversalBaseModel):
+    """
+    Output for a test suite run metric that is of type NUMBER
+    """
+
+    value: typing.Optional[typing.Any] = None
+    type: typing.Literal["JSON"] = "JSON"
+    name: str
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

{vellum_ai-0.8.6 → vellum_ai-0.8.9}/src/vellum/types/test_suite_run_metric_output.py

@@ -3,8 +3,12 @@
 import typing
 from .test_suite_run_metric_string_output import TestSuiteRunMetricStringOutput
 from .test_suite_run_metric_number_output import TestSuiteRunMetricNumberOutput
+from .test_suite_run_metric_json_output import TestSuiteRunMetricJsonOutput
 from .test_suite_run_metric_error_output import TestSuiteRunMetricErrorOutput
 
 TestSuiteRunMetricOutput = typing.Union[
-    TestSuiteRunMetricStringOutput, TestSuiteRunMetricNumberOutput, TestSuiteRunMetricErrorOutput
+    TestSuiteRunMetricStringOutput,
+    TestSuiteRunMetricNumberOutput,
+    TestSuiteRunMetricJsonOutput,
+    TestSuiteRunMetricErrorOutput,
 ]

vellum_ai-0.8.9/src/vellum/types/unit_enum.py

@@ -0,0 +1,5 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+UnitEnum = typing.Literal["USD"]