vellum-ai 0.1.3__py3-none-any.whl → 0.1.5__py3-none-any.whl

vellum/__init__.py

@@ -4,6 +4,7 @@ from .types import (
     ApiNodeResult,
     ApiNodeResultData,
     BlockTypeEnum,
+    ChatHistoryInputRequest,
     ChatMessage,
     ChatMessageRequest,
     ChatMessageRole,
@@ -18,8 +19,14 @@ from .types import (
     DocumentStatus,
     EnrichedNormalizedCompletion,
     EnvironmentEnum,
+    ErrorExecutePromptResponse,
     EvaluationParams,
     EvaluationParamsRequest,
+    ExecutePromptApiErrorResponse,
+    ExecutePromptResponse,
+    ExecutePromptResponse_Error,
+    ExecutePromptResponse_Json,
+    ExecutePromptResponse_String,
     ExecuteWorkflowStreamErrorResponse,
     FinishReasonEnum,
     GenerateErrorResponse,
@@ -33,6 +40,8 @@ from .types import (
     GenerateStreamResult,
     GenerateStreamResultData,
     IndexingStateEnum,
+    JsonExecutePromptResponse,
+    JsonInputRequest,
     LogicalOperator,
     LogprobsEnum,
     MetadataFilterConfigRequest,
@@ -62,6 +71,10 @@ from .types import (
     PaginatedSlimDocumentList,
     ProcessingFailureReasonEnum,
     ProcessingStateEnum,
+    PromptDeploymentInputRequest,
+    PromptDeploymentInputRequest_ChatHistory,
+    PromptDeploymentInputRequest_Json,
+    PromptDeploymentInputRequest_String,
     PromptNodeResult,
     PromptNodeResultData,
     PromptTemplateBlock,
@@ -95,9 +108,13 @@ from .types import (
     SearchResponse,
     SearchResult,
     SearchResultDocument,
+    SearchResultDocumentRequest,
     SearchResultMergingRequest,
+    SearchResultRequest,
     SearchWeightsRequest,
     SlimDocument,
+    StringExecutePromptResponse,
+    StringInputRequest,
     SubmitCompletionActualRequest,
     SubmitCompletionActualsErrorResponse,
     SubmitWorkflowExecutionActualRequest,
@@ -134,11 +151,38 @@ from .types import (
     TerminalNodeResultOutput_String,
     TerminalNodeSearchResultsResult,
     TerminalNodeStringResult,
+    TestCaseChatHistoryVariableValue,
+    TestCaseChatHistoryVariableValueRequest,
+    TestCaseErrorVariableValue,
+    TestCaseErrorVariableValueRequest,
+    TestCaseJsonVariableValue,
+    TestCaseJsonVariableValueRequest,
+    TestCaseNumberVariableValue,
+    TestCaseNumberVariableValueRequest,
+    TestCaseSearchResultsVariableValue,
+    TestCaseSearchResultsVariableValueRequest,
+    TestCaseStringVariableValue,
+    TestCaseStringVariableValueRequest,
+    TestCaseVariableValue,
+    TestCaseVariableValueRequest,
+    TestCaseVariableValueRequest_ChatHistory,
+    TestCaseVariableValueRequest_Error,
+    TestCaseVariableValueRequest_Json,
+    TestCaseVariableValueRequest_Number,
+    TestCaseVariableValueRequest_SearchResults,
+    TestCaseVariableValueRequest_String,
+    TestCaseVariableValue_ChatHistory,
+    TestCaseVariableValue_Error,
+    TestCaseVariableValue_Json,
+    TestCaseVariableValue_Number,
+    TestCaseVariableValue_SearchResults,
+    TestCaseVariableValue_String,
     TestSuiteTestCase,
     UploadDocumentErrorResponse,
     UploadDocumentResponse,
     VellumError,
     VellumErrorCodeEnum,
+    VellumErrorRequest,
     VellumVariable,
     VellumVariableType,
     WorkflowEventError,
@@ -200,6 +244,7 @@ __all__ = [
     "ApiNodeResultData",
     "BadRequestError",
     "BlockTypeEnum",
+    "ChatHistoryInputRequest",
     "ChatMessage",
     "ChatMessageRequest",
     "ChatMessageRole",
@@ -215,8 +260,14 @@ __all__ = [
     "DocumentStatus",
     "EnrichedNormalizedCompletion",
     "EnvironmentEnum",
+    "ErrorExecutePromptResponse",
     "EvaluationParams",
     "EvaluationParamsRequest",
+    "ExecutePromptApiErrorResponse",
+    "ExecutePromptResponse",
+    "ExecutePromptResponse_Error",
+    "ExecutePromptResponse_Json",
+    "ExecutePromptResponse_String",
     "ExecuteWorkflowStreamErrorResponse",
     "FinishReasonEnum",
     "ForbiddenError",
@@ -232,6 +283,8 @@ __all__ = [
     "GenerateStreamResultData",
     "IndexingStateEnum",
     "InternalServerError",
+    "JsonExecutePromptResponse",
+    "JsonInputRequest",
     "LogicalOperator",
     "LogprobsEnum",
     "MetadataFilterConfigRequest",
@@ -262,6 +315,10 @@ __all__ = [
     "PaginatedSlimDocumentList",
     "ProcessingFailureReasonEnum",
     "ProcessingStateEnum",
+    "PromptDeploymentInputRequest",
+    "PromptDeploymentInputRequest_ChatHistory",
+    "PromptDeploymentInputRequest_Json",
+    "PromptDeploymentInputRequest_String",
     "PromptNodeResult",
     "PromptNodeResultData",
     "PromptTemplateBlock",
@@ -295,9 +352,13 @@ __all__ = [
     "SearchResponse",
     "SearchResult",
     "SearchResultDocument",
+    "SearchResultDocumentRequest",
     "SearchResultMergingRequest",
+    "SearchResultRequest",
     "SearchWeightsRequest",
     "SlimDocument",
+    "StringExecutePromptResponse",
+    "StringInputRequest",
     "SubmitCompletionActualRequest",
     "SubmitCompletionActualsErrorResponse",
     "SubmitWorkflowExecutionActualRequest",
@@ -334,12 +395,39 @@ __all__ = [
     "TerminalNodeResultOutput_String",
     "TerminalNodeSearchResultsResult",
     "TerminalNodeStringResult",
+    "TestCaseChatHistoryVariableValue",
+    "TestCaseChatHistoryVariableValueRequest",
+    "TestCaseErrorVariableValue",
+    "TestCaseErrorVariableValueRequest",
+    "TestCaseJsonVariableValue",
+    "TestCaseJsonVariableValueRequest",
+    "TestCaseNumberVariableValue",
+    "TestCaseNumberVariableValueRequest",
+    "TestCaseSearchResultsVariableValue",
+    "TestCaseSearchResultsVariableValueRequest",
+    "TestCaseStringVariableValue",
+    "TestCaseStringVariableValueRequest",
+    "TestCaseVariableValue",
+    "TestCaseVariableValueRequest",
+    "TestCaseVariableValueRequest_ChatHistory",
+    "TestCaseVariableValueRequest_Error",
+    "TestCaseVariableValueRequest_Json",
+    "TestCaseVariableValueRequest_Number",
+    "TestCaseVariableValueRequest_SearchResults",
+    "TestCaseVariableValueRequest_String",
+    "TestCaseVariableValue_ChatHistory",
+    "TestCaseVariableValue_Error",
+    "TestCaseVariableValue_Json",
+    "TestCaseVariableValue_Number",
+    "TestCaseVariableValue_SearchResults",
+    "TestCaseVariableValue_String",
     "TestSuiteTestCase",
     "UploadDocumentErrorResponse",
     "UploadDocumentResponse",
     "VellumEnvironment",
     "VellumError",
     "VellumErrorCodeEnum",
+    "VellumErrorRequest",
     "VellumVariable",
     "VellumVariableType",
     "WorkflowEventError",

vellum/client.py

@@ -22,11 +22,12 @@ 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.generate_error_response import GenerateErrorResponse
+from .types.execute_prompt_response import ExecutePromptResponse
 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
@@ -66,6 +67,61 @@ 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:
+        """
+        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: 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),
+            headers=self._client_wrapper.get_headers(),
+            timeout=None,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ExecutePromptResponse, _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,
         *,
@@ -86,7 +142,7 @@ class Vellum:
 
             - release_tag: typing.Optional[str]. Optionally specify a release tag if you want to pin to a specific release of the Workflow Deployment
 
-            - inputs: typing.List[WorkflowRequestInputRequest].
+            - inputs: typing.List[WorkflowRequestInputRequest]. The list of inputs defined in the Workflow's deployment with their corresponding values.
 
             - external_id: typing.Optional[str]. Optionally include a unique identifier for tracking purposes.
 
@@ -187,7 +243,7 @@ class Vellum:
         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(GenerateErrorResponse, _response.json()))  # type: ignore
+            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:
@@ -244,7 +300,7 @@ class Vellum:
             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(GenerateErrorResponse, _response.json()))  # type: ignore
+                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:
@@ -432,6 +488,61 @@ 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:
+        """
+        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: 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),
+            headers=self._client_wrapper.get_headers(),
+            timeout=None,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ExecutePromptResponse, _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,
         *,
@@ -452,7 +563,7 @@ class AsyncVellum:
 
             - release_tag: typing.Optional[str]. Optionally specify a release tag if you want to pin to a specific release of the Workflow Deployment
 
-            - inputs: typing.List[WorkflowRequestInputRequest].
+            - inputs: typing.List[WorkflowRequestInputRequest]. The list of inputs defined in the Workflow's deployment with their corresponding values.
 
             - external_id: typing.Optional[str]. Optionally include a unique identifier for tracking purposes.
 
@@ -553,7 +664,7 @@ class AsyncVellum:
         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(GenerateErrorResponse, _response.json()))  # type: ignore
+            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:
@@ -610,7 +721,7 @@ class AsyncVellum:
             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(GenerateErrorResponse, _response.json()))  # type: ignore
+                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:

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": "v0.1.3",
+            "X-Fern-SDK-Version": "v0.1.5",
         }
         headers["X_API_KEY"] = self.api_key
         return headers

vellum/errors/forbidden_error.py

@@ -1,9 +1,10 @@
 # This file was auto-generated by Fern from our API Definition.
 
+import typing
+
 from ..core.api_error import ApiError
-from ..types.generate_error_response import GenerateErrorResponse
 
 
 class ForbiddenError(ApiError):
-    def __init__(self, body: GenerateErrorResponse):
+    def __init__(self, body: typing.Any):
         super().__init__(status_code=403, body=body)

vellum/resources/test_suites/client.py

@@ -7,7 +7,7 @@ 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.evaluation_params_request import EvaluationParamsRequest
+from ...types.test_case_variable_value_request import TestCaseVariableValueRequest
 from ...types.test_suite_test_case import TestSuiteTestCase
 
 try:
@@ -27,10 +27,10 @@ class TestSuitesClient:
         self,
         id: str,
         *,
-        test_case_id: typing.Optional[str] = OMIT,
+        test_suite_test_case_request_id: typing.Optional[str] = OMIT,
         label: typing.Optional[str] = OMIT,
-        input_values: typing.Dict[str, typing.Any],
-        evaluation_params: EvaluationParamsRequest,
+        input_values: typing.List[TestCaseVariableValueRequest],
+        evaluation_values: typing.List[TestCaseVariableValueRequest],
     ) -> TestSuiteTestCase:
         """
         Upserts a new test case for a test suite, keying off of the optionally provided test case id.
@@ -44,15 +44,14 @@ class TestSuitesClient:
         Parameters:
             - id: str. A UUID string identifying this test suite.
 
-            - test_case_id: typing.Optional[str]. The id of the test case to update. If none is provided, an id will be generated and a new test case will be appended.
+            - test_suite_test_case_request_id: typing.Optional[str].
 
-            - label: typing.Optional[str]. A human-friendly label for the test case.
+            - label: typing.Optional[str].
 
-            - input_values: typing.Dict[str, typing.Any]. Key/value pairs for each input variable that the Test Suite expects.
+            - input_values: typing.List[TestCaseVariableValueRequest].
 
-            - evaluation_params: EvaluationParamsRequest. Parameters to use when evaluating the test case, specific to the test suite's evaluation metric.
+            - evaluation_values: typing.List[TestCaseVariableValueRequest].
         ---
-        from vellum import EvaluationParamsRequest
         from vellum.client import Vellum
 
         client = Vellum(
@@ -60,13 +59,13 @@ class TestSuitesClient:
         )
         client.test_suites.upsert_test_suite_test_case(
             id="id",
-            input_values={},
-            evaluation_params=EvaluationParamsRequest(),
+            input_values=[],
+            evaluation_values=[],
         )
         """
-        _request: typing.Dict[str, typing.Any] = {"input_values": input_values, "evaluation_params": evaluation_params}
-        if test_case_id is not OMIT:
-            _request["test_case_id"] = test_case_id
+        _request: typing.Dict[str, typing.Any] = {"input_values": input_values, "evaluation_values": evaluation_values}
+        if test_suite_test_case_request_id is not OMIT:
+            _request["id"] = test_suite_test_case_request_id
         if label is not OMIT:
             _request["label"] = label
         _response = self._client_wrapper.httpx_client.request(
@@ -130,10 +129,10 @@ class AsyncTestSuitesClient:
         self,
         id: str,
         *,
-        test_case_id: typing.Optional[str] = OMIT,
+        test_suite_test_case_request_id: typing.Optional[str] = OMIT,
         label: typing.Optional[str] = OMIT,
-        input_values: typing.Dict[str, typing.Any],
-        evaluation_params: EvaluationParamsRequest,
+        input_values: typing.List[TestCaseVariableValueRequest],
+        evaluation_values: typing.List[TestCaseVariableValueRequest],
     ) -> TestSuiteTestCase:
         """
         Upserts a new test case for a test suite, keying off of the optionally provided test case id.
@@ -147,15 +146,14 @@ class AsyncTestSuitesClient:
         Parameters:
             - id: str. A UUID string identifying this test suite.
 
-            - test_case_id: typing.Optional[str]. The id of the test case to update. If none is provided, an id will be generated and a new test case will be appended.
+            - test_suite_test_case_request_id: typing.Optional[str].
 
-            - label: typing.Optional[str]. A human-friendly label for the test case.
+            - label: typing.Optional[str].
 
-            - input_values: typing.Dict[str, typing.Any]. Key/value pairs for each input variable that the Test Suite expects.
+            - input_values: typing.List[TestCaseVariableValueRequest].
 
-            - evaluation_params: EvaluationParamsRequest. Parameters to use when evaluating the test case, specific to the test suite's evaluation metric.
+            - evaluation_values: typing.List[TestCaseVariableValueRequest].
         ---
-        from vellum import EvaluationParamsRequest
         from vellum.client import AsyncVellum
 
         client = AsyncVellum(
@@ -163,13 +161,13 @@ class AsyncTestSuitesClient:
         )
         await client.test_suites.upsert_test_suite_test_case(
             id="id",
-            input_values={},
-            evaluation_params=EvaluationParamsRequest(),
+            input_values=[],
+            evaluation_values=[],
         )
         """
-        _request: typing.Dict[str, typing.Any] = {"input_values": input_values, "evaluation_params": evaluation_params}
-        if test_case_id is not OMIT:
-            _request["test_case_id"] = test_case_id
+        _request: typing.Dict[str, typing.Any] = {"input_values": input_values, "evaluation_values": evaluation_values}
+        if test_suite_test_case_request_id is not OMIT:
+            _request["id"] = test_suite_test_case_request_id
         if label is not OMIT:
             _request["label"] = label
         _response = await self._client_wrapper.httpx_client.request(