vellum-ai 0.6.3__tar.gz → 0.6.5__tar.gz

vellum_ai-0.6.5/PKG-INFO

@@ -0,0 +1,126 @@
+Metadata-Version: 2.1
+Name: vellum-ai
+Version: 0.6.5
+Summary: 
+Requires-Python: >=3.8,<4.0
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Requires-Dist: cdktf (>=0.20.5,<0.21.0)
+Requires-Dist: httpx (>=0.21.2)
+Requires-Dist: publication (==0.0.3)
+Requires-Dist: pydantic (>=1.9.2)
+Requires-Dist: typing_extensions (>=4.0.0)
+Description-Content-Type: text/markdown
+
+# Vellum Python Library
+
+[![pypi](https://img.shields.io/pypi/v/vellum-ai.svg)](https://pypi.python.org/pypi/vellum-ai)
+![license badge](https://img.shields.io/github/license/vellum-ai/vellum-client-python)
+[![fern shield](https://img.shields.io/badge/%F0%9F%8C%BF-SDK%20generated%20by%20Fern-brightgreen)](https://buildwithfern.com/?utm_source=vellum-ai/vellum-client-python/readme)
+
+The Vellum Python SDK provides access to the Vellum API from python.
+
+
+## API Docs
+You can find Vellum's complete API docs at [docs.vellum.ai](https://docs.vellum.ai/api-reference/introduction/getting-started).
+
+## Installation
+
+```sh
+pip install --upgrade vellum-ai
+```
+
+## Usage
+Below is how you would invoke a deployed Prompt from the Vellum API. For a complete list of all APIs
+that Vellum supports, check out our [API Reference](https://docs.vellum.ai/api-reference/introduction/getting-started).
+
+```python
+from vellum import (
+    PromptDeploymentInputRequest_String,
+)
+from vellum.client import Vellum
+
+client = Vellum(
+    api_key="YOUR_API_KEY",
+)
+
+def execute() -> str:
+    result = client.execute_prompt(
+        prompt_deployment_name="<example-deployment-name>>",
+        release_tag="LATEST",
+        inputs=[
+            PromptDeploymentInputRequest_String(
+                name="input_a",
+                type="STRING",
+                value="Hello, world!",
+            )
+        ],
+    )
+    
+    if result.state == "REJECTED":
+        raise Exception(result.error.message)
+
+    return result.outputs[0].value
+
+if __name__ == "__main__":
+    print(execute())
+```
+
+> [!TIP]
+> You can set a system environment variable `VELLUM_API_KEY` to avoid writing your api key within your code. To do so, add `export VELLUM_API_KEY=<your-api-token>`
+> to your ~/.zshrc or ~/.bashrc, open a new terminal, and then any code calling `vellum.Vellum()` will read this key.
+
+## Async Client
+This SDK has an async version. Here's how to use it:
+
+
+
+```python
+import asyncio
+
+import vellum
+from vellum.client import AsyncVellum
+
+client = AsyncVellum(api_key="YOUR_API_KEY")
+
+async def execute() -> str:
+    result = await client.execute_prompt(
+        prompt_deployment_name="<example-deployment-name>>",
+        release_tag="LATEST",
+        inputs=[
+            vellum.PromptDeploymentInputRequest_String(
+                name="input_a",
+                value="Hello, world!",
+            )
+        ],
+    )
+
+    if result.state == "REJECTED":
+        raise Exception(result.error.message)
+    
+    return result.outputs[0].value
+
+if __name__ == "__main__":
+    print(asyncio.run(execute()))
+```
+
+## Contributing
+
+While we value open-source contributions to this SDK, most of this library is generated programmatically.
+
+Please feel free to make contributions to any of the directories or files below:
+```plaintext
+examples/*
+src/vellum/lib/*
+tests/*
+README.md
+```
+
+Any additions made to files beyond those directories and files above would have to be moved over to our generation code
+(found in the separate [vellum-client-generator](https://github.com/vellum-ai/vellum-client-generator) repo),
+otherwise they would be overwritten upon the next generated release. Feel free to open a PR as a proof of concept,
+but know that we will not be able to merge it as-is. We suggest opening an issue first to discuss with us!
+

vellum_ai-0.6.5/README.md

@@ -0,0 +1,108 @@
+# Vellum Python Library
+
+[![pypi](https://img.shields.io/pypi/v/vellum-ai.svg)](https://pypi.python.org/pypi/vellum-ai)
+![license badge](https://img.shields.io/github/license/vellum-ai/vellum-client-python)
+[![fern shield](https://img.shields.io/badge/%F0%9F%8C%BF-SDK%20generated%20by%20Fern-brightgreen)](https://buildwithfern.com/?utm_source=vellum-ai/vellum-client-python/readme)
+
+The Vellum Python SDK provides access to the Vellum API from python.
+
+
+## API Docs
+You can find Vellum's complete API docs at [docs.vellum.ai](https://docs.vellum.ai/api-reference/introduction/getting-started).
+
+## Installation
+
+```sh
+pip install --upgrade vellum-ai
+```
+
+## Usage
+Below is how you would invoke a deployed Prompt from the Vellum API. For a complete list of all APIs
+that Vellum supports, check out our [API Reference](https://docs.vellum.ai/api-reference/introduction/getting-started).
+
+```python
+from vellum import (
+    PromptDeploymentInputRequest_String,
+)
+from vellum.client import Vellum
+
+client = Vellum(
+    api_key="YOUR_API_KEY",
+)
+
+def execute() -> str:
+    result = client.execute_prompt(
+        prompt_deployment_name="<example-deployment-name>>",
+        release_tag="LATEST",
+        inputs=[
+            PromptDeploymentInputRequest_String(
+                name="input_a",
+                type="STRING",
+                value="Hello, world!",
+            )
+        ],
+    )
+    
+    if result.state == "REJECTED":
+        raise Exception(result.error.message)
+
+    return result.outputs[0].value
+
+if __name__ == "__main__":
+    print(execute())
+```
+
+> [!TIP]
+> You can set a system environment variable `VELLUM_API_KEY` to avoid writing your api key within your code. To do so, add `export VELLUM_API_KEY=<your-api-token>`
+> to your ~/.zshrc or ~/.bashrc, open a new terminal, and then any code calling `vellum.Vellum()` will read this key.
+
+## Async Client
+This SDK has an async version. Here's how to use it:
+
+
+
+```python
+import asyncio
+
+import vellum
+from vellum.client import AsyncVellum
+
+client = AsyncVellum(api_key="YOUR_API_KEY")
+
+async def execute() -> str:
+    result = await client.execute_prompt(
+        prompt_deployment_name="<example-deployment-name>>",
+        release_tag="LATEST",
+        inputs=[
+            vellum.PromptDeploymentInputRequest_String(
+                name="input_a",
+                value="Hello, world!",
+            )
+        ],
+    )
+
+    if result.state == "REJECTED":
+        raise Exception(result.error.message)
+    
+    return result.outputs[0].value
+
+if __name__ == "__main__":
+    print(asyncio.run(execute()))
+```
+
+## Contributing
+
+While we value open-source contributions to this SDK, most of this library is generated programmatically.
+
+Please feel free to make contributions to any of the directories or files below:
+```plaintext
+examples/*
+src/vellum/lib/*
+tests/*
+README.md
+```
+
+Any additions made to files beyond those directories and files above would have to be moved over to our generation code
+(found in the separate [vellum-client-generator](https://github.com/vellum-ai/vellum-client-generator) repo),
+otherwise they would be overwritten upon the next generated release. Feel free to open a PR as a proof of concept,
+but know that we will not be able to merge it as-is. We suggest opening an issue first to discuss with us!

{vellum_ai-0.6.3 → vellum_ai-0.6.5}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "vellum-ai"
-version = "0.6.3"
+version = "0.6.5"
 description = ""
 readme = "README.md"
 authors = []

{vellum_ai-0.6.3 → vellum_ai-0.6.5}/src/vellum/__init__.py

@@ -35,6 +35,8 @@ from .types import (
     BasicVectorizerSentenceTransformersMultiQaMpnetBaseCosV1Request,
     BasicVectorizerSentenceTransformersMultiQaMpnetBaseDotV1,
     BasicVectorizerSentenceTransformersMultiQaMpnetBaseDotV1Request,
+    BulkCreateTestSuiteTestCaseDataRequest,
+    BulkReplaceTestSuiteTestCaseDataRequest,
     ChatHistoryEnum,
     ChatHistoryInputRequest,
     ChatMessage,
@@ -71,6 +73,10 @@ from .types import (
     CodeExecutionNodeStringResult,
     ConditionalNodeResult,
     ConditionalNodeResultData,
+    CreateEnum,
+    CreatedEnum,
+    DeleteEnum,
+    DeletedEnum,
     DeploymentProviderPayloadResponse,
     DeploymentRead,
     DeploymentReleaseTagDeploymentHistoryItem,
@@ -317,6 +323,8 @@ from .types import (
     RejectedPromptExecutionMeta,
     RejectedWorkflowNodeResultEvent,
     ReleaseTagSource,
+    ReplaceEnum,
+    ReplacedEnum,
     SandboxScenario,
     ScenarioInput,
     ScenarioInputChatHistoryVariableValue,
@@ -473,6 +481,26 @@ from .types import (
     TestSuiteRunWorkflowReleaseTagExecConfigRequest,
     TestSuiteRunWorkflowReleaseTagExecConfigTypeEnum,
     TestSuiteTestCase,
+    TestSuiteTestCaseBulkOperationRequest,
+    TestSuiteTestCaseBulkOperationRequest_Create,
+    TestSuiteTestCaseBulkOperationRequest_Delete,
+    TestSuiteTestCaseBulkOperationRequest_Replace,
+    TestSuiteTestCaseBulkResult,
+    TestSuiteTestCaseBulkResult_Created,
+    TestSuiteTestCaseBulkResult_Deleted,
+    TestSuiteTestCaseBulkResult_Rejected,
+    TestSuiteTestCaseBulkResult_Replaced,
+    TestSuiteTestCaseCreateBulkOperationRequest,
+    TestSuiteTestCaseCreatedBulkResult,
+    TestSuiteTestCaseCreatedBulkResultData,
+    TestSuiteTestCaseDeleteBulkOperationDataRequest,
+    TestSuiteTestCaseDeleteBulkOperationRequest,
+    TestSuiteTestCaseDeletedBulkResult,
+    TestSuiteTestCaseDeletedBulkResultData,
+    TestSuiteTestCaseRejectedBulkResult,
+    TestSuiteTestCaseReplaceBulkOperationRequest,
+    TestSuiteTestCaseReplacedBulkResult,
+    TestSuiteTestCaseReplacedBulkResultData,
     TextEmbedding3LargeEnum,
     TextEmbedding3SmallEnum,
     TextEmbeddingAda002Enum,
@@ -622,6 +650,8 @@ __all__ = [
     "BasicVectorizerSentenceTransformersMultiQaMpnetBaseCosV1Request",
     "BasicVectorizerSentenceTransformersMultiQaMpnetBaseDotV1",
     "BasicVectorizerSentenceTransformersMultiQaMpnetBaseDotV1Request",
+    "BulkCreateTestSuiteTestCaseDataRequest",
+    "BulkReplaceTestSuiteTestCaseDataRequest",
     "ChatHistoryEnum",
     "ChatHistoryInputRequest",
     "ChatMessage",
@@ -658,6 +688,10 @@ __all__ = [
     "CodeExecutionNodeStringResult",
     "ConditionalNodeResult",
     "ConditionalNodeResultData",
+    "CreateEnum",
+    "CreatedEnum",
+    "DeleteEnum",
+    "DeletedEnum",
     "DeploymentProviderPayloadResponse",
     "DeploymentRead",
     "DeploymentReleaseTagDeploymentHistoryItem",
@@ -909,6 +943,8 @@ __all__ = [
     "RejectedPromptExecutionMeta",
     "RejectedWorkflowNodeResultEvent",
     "ReleaseTagSource",
+    "ReplaceEnum",
+    "ReplacedEnum",
     "SandboxScenario",
     "ScenarioInput",
     "ScenarioInputChatHistoryVariableValue",
@@ -1065,6 +1101,26 @@ __all__ = [
     "TestSuiteRunWorkflowReleaseTagExecConfigRequest",
     "TestSuiteRunWorkflowReleaseTagExecConfigTypeEnum",
     "TestSuiteTestCase",
+    "TestSuiteTestCaseBulkOperationRequest",
+    "TestSuiteTestCaseBulkOperationRequest_Create",
+    "TestSuiteTestCaseBulkOperationRequest_Delete",
+    "TestSuiteTestCaseBulkOperationRequest_Replace",
+    "TestSuiteTestCaseBulkResult",
+    "TestSuiteTestCaseBulkResult_Created",
+    "TestSuiteTestCaseBulkResult_Deleted",
+    "TestSuiteTestCaseBulkResult_Rejected",
+    "TestSuiteTestCaseBulkResult_Replaced",
+    "TestSuiteTestCaseCreateBulkOperationRequest",
+    "TestSuiteTestCaseCreatedBulkResult",
+    "TestSuiteTestCaseCreatedBulkResultData",
+    "TestSuiteTestCaseDeleteBulkOperationDataRequest",
+    "TestSuiteTestCaseDeleteBulkOperationRequest",
+    "TestSuiteTestCaseDeletedBulkResult",
+    "TestSuiteTestCaseDeletedBulkResultData",
+    "TestSuiteTestCaseRejectedBulkResult",
+    "TestSuiteTestCaseReplaceBulkOperationRequest",
+    "TestSuiteTestCaseReplacedBulkResult",
+    "TestSuiteTestCaseReplacedBulkResultData",
     "TextEmbedding3LargeEnum",
     "TextEmbedding3SmallEnum",
     "TextEmbeddingAda002Enum",

{vellum_ai-0.6.3 → vellum_ai-0.6.5}/src/vellum/client.py

@@ -591,7 +591,8 @@ class Vellum:
         """
         Generate a completion using a previously defined deployment.
 
-        **Note:** Uses a base url of `https://predict.vellum.ai`.
+        Important: This endpoint is DEPRECATED and has been superseded by
+        [execute-prompt](/api-reference/api-reference/execute-prompt).
 
         Parameters:
             - deployment_id: typing.Optional[str]. The ID of the deployment. Must provide either this or deployment_name.
@@ -679,7 +680,8 @@ class Vellum:
         """
         Generate a stream of completions using a previously defined deployment.
 
-        **Note:** Uses a base url of `https://predict.vellum.ai`.
+        Important: This endpoint is DEPRECATED and has been superseded by
+        [execute-prompt-stream](/api-reference/api-reference/execute-prompt-stream).
 
         Parameters:
             - deployment_id: typing.Optional[str]. The ID of the deployment. Must provide either this or deployment_name.
@@ -791,8 +793,6 @@ class Vellum:
         """
         Perform a search against a document index.
 
-        **Note:** Uses a base url of `https://predict.vellum.ai`.
-
         Parameters:
             - index_id: typing.Optional[str]. The ID of the index to search against. Must provide either this or index_name.
 
@@ -871,8 +871,6 @@ class Vellum:
         """
         Used to submit feedback regarding the quality of previously generated completions.
 
-        **Note:** Uses a base url of `https://predict.vellum.ai`.
-
         Parameters:
             - deployment_id: typing.Optional[str]. The ID of the deployment. Must provide either this or deployment_name.
 
@@ -1554,7 +1552,8 @@ class AsyncVellum:
         """
         Generate a completion using a previously defined deployment.
 
-        **Note:** Uses a base url of `https://predict.vellum.ai`.
+        Important: This endpoint is DEPRECATED and has been superseded by
+        [execute-prompt](/api-reference/api-reference/execute-prompt).
 
         Parameters:
             - deployment_id: typing.Optional[str]. The ID of the deployment. Must provide either this or deployment_name.
@@ -1642,7 +1641,8 @@ class AsyncVellum:
         """
         Generate a stream of completions using a previously defined deployment.
 
-        **Note:** Uses a base url of `https://predict.vellum.ai`.
+        Important: This endpoint is DEPRECATED and has been superseded by
+        [execute-prompt-stream](/api-reference/api-reference/execute-prompt-stream).
 
         Parameters:
             - deployment_id: typing.Optional[str]. The ID of the deployment. Must provide either this or deployment_name.
@@ -1754,8 +1754,6 @@ class AsyncVellum:
         """
         Perform a search against a document index.
 
-        **Note:** Uses a base url of `https://predict.vellum.ai`.
-
         Parameters:
             - index_id: typing.Optional[str]. The ID of the index to search against. Must provide either this or index_name.
 
@@ -1834,8 +1832,6 @@ class AsyncVellum:
         """
         Used to submit feedback regarding the quality of previously generated completions.
 
-        **Note:** Uses a base url of `https://predict.vellum.ai`.
-
         Parameters:
             - deployment_id: typing.Optional[str]. The ID of the deployment. Must provide either this or deployment_name.
 

{vellum_ai-0.6.3 → vellum_ai-0.6.5}/src/vellum/core/client_wrapper.py

@@ -18,7 +18,7 @@ class BaseClientWrapper:
         headers: typing.Dict[str, str] = {
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "vellum-ai",
-            "X-Fern-SDK-Version": "0.6.3",
+            "X-Fern-SDK-Version": "0.6.5",
         }
         headers["X_API_KEY"] = self.api_key
         return headers

{vellum_ai-0.6.3 → vellum_ai-0.6.5}/src/vellum/resources/test_suites/client.py

@@ -1,5 +1,6 @@
 # This file was auto-generated by Fern from our API Definition.
 
+import json
 import typing
 import urllib.parse
 from json.decoder import JSONDecodeError
@@ -13,6 +14,8 @@ from ...core.request_options import RequestOptions
 from ...types.named_test_case_variable_value_request import NamedTestCaseVariableValueRequest
 from ...types.paginated_test_suite_test_case_list import PaginatedTestSuiteTestCaseList
 from ...types.test_suite_test_case import TestSuiteTestCase
+from ...types.test_suite_test_case_bulk_operation_request import TestSuiteTestCaseBulkOperationRequest
+from ...types.test_suite_test_case_bulk_result import TestSuiteTestCaseBulkResult
 
 # this is used as the default value for optional parameters
 OMIT = typing.cast(typing.Any, ...)
@@ -114,13 +117,13 @@ class TestSuitesClient:
         Parameters:
             - id: str. A UUID string identifying this test suite.
 
-            - upsert_test_suite_test_case_request_id: typing.Optional[str].
+            - upsert_test_suite_test_case_request_id: typing.Optional[str]. The ID of the Test Case to upsert. If specified and a match is found, the existing Test Case will be updated. If specified and no match is found, a Test Case will be created with the provided ID. If not provided, a new Test Case will be created with an auto-generated ID.
 
             - label: typing.Optional[str].
 
-            - input_values: typing.Sequence[NamedTestCaseVariableValueRequest].
+            - input_values: typing.Sequence[NamedTestCaseVariableValueRequest]. Values for each of the Test Case's input variables
 
-            - evaluation_values: typing.Sequence[NamedTestCaseVariableValueRequest].
+            - evaluation_values: typing.Sequence[NamedTestCaseVariableValueRequest]. Values for each of the Test Case's evaluation variables
 
             - request_options: typing.Optional[RequestOptions]. Request-specific configuration.
         ---
@@ -177,6 +180,89 @@ class TestSuitesClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    def test_suite_test_cases_bulk(
+        self,
+        id: str,
+        *,
+        request: typing.Sequence[TestSuiteTestCaseBulkOperationRequest],
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> typing.Iterator[typing.List[TestSuiteTestCaseBulkResult]]:
+        """
+        Created, replace, and delete Test Cases within the specified Test Suite in bulk
+
+        Parameters:
+            - id: str. A UUID string identifying this test suite.
+
+            - request: typing.Sequence[TestSuiteTestCaseBulkOperationRequest].
+
+            - request_options: typing.Optional[RequestOptions]. Request-specific configuration.
+        ---
+        from vellum import (
+            BulkCreateTestSuiteTestCaseDataRequest,
+            NamedTestCaseVariableValueRequest_String,
+            TestSuiteTestCaseBulkOperationRequest_Create,
+        )
+        from vellum.client import Vellum
+
+        client = Vellum(
+            api_key="YOUR_API_KEY",
+        )
+        client.test_suites.test_suite_test_cases_bulk(
+            id="string",
+            request=[
+                TestSuiteTestCaseBulkOperationRequest_Create(
+                    id="string",
+                    data=BulkCreateTestSuiteTestCaseDataRequest(
+                        label="string",
+                        input_values=[NamedTestCaseVariableValueRequest_String()],
+                        evaluation_values=[NamedTestCaseVariableValueRequest_String()],
+                    ),
+                )
+            ],
+        )
+        """
+        with self._client_wrapper.httpx_client.stream(
+            method="POST",
+            url=urllib.parse.urljoin(
+                f"{self._client_wrapper.get_environment().default}/",
+                f"v1/test-suites/{jsonable_encoder(id)}/test-cases-bulk",
+            ),
+            params=jsonable_encoder(
+                request_options.get("additional_query_parameters") if request_options is not None else None
+            ),
+            json=jsonable_encoder(request)
+            if request_options is None or request_options.get("additional_body_parameters") is None
+            else {
+                **jsonable_encoder(request),
+                **(jsonable_encoder(remove_none_from_dict(request_options.get("additional_body_parameters", {})))),
+            },
+            headers=jsonable_encoder(
+                remove_none_from_dict(
+                    {
+                        **self._client_wrapper.get_headers(),
+                        **(request_options.get("additional_headers", {}) if request_options is not None else {}),
+                    }
+                )
+            ),
+            timeout=request_options.get("timeout_in_seconds")
+            if request_options is not None and request_options.get("timeout_in_seconds") is not None
+            else self._client_wrapper.get_timeout(),
+            retries=0,
+            max_retries=request_options.get("max_retries") if request_options is not None else 0,  # type: ignore
+        ) as _response:
+            if 200 <= _response.status_code < 300:
+                for _text in _response.iter_lines():
+                    if len(_text) == 0:
+                        continue
+                    yield pydantic_v1.parse_obj_as(typing.List[TestSuiteTestCaseBulkResult], json.loads(_text))  # type: ignore
+                return
+            _response.read()
+            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 delete_test_suite_test_case(
         self, id: str, test_case_id: str, *, request_options: typing.Optional[RequestOptions] = None
     ) -> None:
@@ -328,13 +414,13 @@ class AsyncTestSuitesClient:
         Parameters:
             - id: str. A UUID string identifying this test suite.
 
-            - upsert_test_suite_test_case_request_id: typing.Optional[str].
+            - upsert_test_suite_test_case_request_id: typing.Optional[str]. The ID of the Test Case to upsert. If specified and a match is found, the existing Test Case will be updated. If specified and no match is found, a Test Case will be created with the provided ID. If not provided, a new Test Case will be created with an auto-generated ID.
 
             - label: typing.Optional[str].
 
-            - input_values: typing.Sequence[NamedTestCaseVariableValueRequest].
+            - input_values: typing.Sequence[NamedTestCaseVariableValueRequest]. Values for each of the Test Case's input variables
 
-            - evaluation_values: typing.Sequence[NamedTestCaseVariableValueRequest].
+            - evaluation_values: typing.Sequence[NamedTestCaseVariableValueRequest]. Values for each of the Test Case's evaluation variables
 
             - request_options: typing.Optional[RequestOptions]. Request-specific configuration.
         ---
@@ -391,6 +477,89 @@ class AsyncTestSuitesClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    async def test_suite_test_cases_bulk(
+        self,
+        id: str,
+        *,
+        request: typing.Sequence[TestSuiteTestCaseBulkOperationRequest],
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> typing.AsyncIterator[typing.List[TestSuiteTestCaseBulkResult]]:
+        """
+        Created, replace, and delete Test Cases within the specified Test Suite in bulk
+
+        Parameters:
+            - id: str. A UUID string identifying this test suite.
+
+            - request: typing.Sequence[TestSuiteTestCaseBulkOperationRequest].
+
+            - request_options: typing.Optional[RequestOptions]. Request-specific configuration.
+        ---
+        from vellum import (
+            BulkCreateTestSuiteTestCaseDataRequest,
+            NamedTestCaseVariableValueRequest_String,
+            TestSuiteTestCaseBulkOperationRequest_Create,
+        )
+        from vellum.client import AsyncVellum
+
+        client = AsyncVellum(
+            api_key="YOUR_API_KEY",
+        )
+        await client.test_suites.test_suite_test_cases_bulk(
+            id="string",
+            request=[
+                TestSuiteTestCaseBulkOperationRequest_Create(
+                    id="string",
+                    data=BulkCreateTestSuiteTestCaseDataRequest(
+                        label="string",
+                        input_values=[NamedTestCaseVariableValueRequest_String()],
+                        evaluation_values=[NamedTestCaseVariableValueRequest_String()],
+                    ),
+                )
+            ],
+        )
+        """
+        async with self._client_wrapper.httpx_client.stream(
+            method="POST",
+            url=urllib.parse.urljoin(
+                f"{self._client_wrapper.get_environment().default}/",
+                f"v1/test-suites/{jsonable_encoder(id)}/test-cases-bulk",
+            ),
+            params=jsonable_encoder(
+                request_options.get("additional_query_parameters") if request_options is not None else None
+            ),
+            json=jsonable_encoder(request)
+            if request_options is None or request_options.get("additional_body_parameters") is None
+            else {
+                **jsonable_encoder(request),
+                **(jsonable_encoder(remove_none_from_dict(request_options.get("additional_body_parameters", {})))),
+            },
+            headers=jsonable_encoder(
+                remove_none_from_dict(
+                    {
+                        **self._client_wrapper.get_headers(),
+                        **(request_options.get("additional_headers", {}) if request_options is not None else {}),
+                    }
+                )
+            ),
+            timeout=request_options.get("timeout_in_seconds")
+            if request_options is not None and request_options.get("timeout_in_seconds") is not None
+            else self._client_wrapper.get_timeout(),
+            retries=0,
+            max_retries=request_options.get("max_retries") if request_options is not None else 0,  # type: ignore
+        ) as _response:
+            if 200 <= _response.status_code < 300:
+                async for _text in _response.aiter_lines():
+                    if len(_text) == 0:
+                        continue
+                    yield pydantic_v1.parse_obj_as(typing.List[TestSuiteTestCaseBulkResult], json.loads(_text))  # type: ignore
+                return
+            await _response.aread()
+            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 delete_test_suite_test_case(
         self, id: str, test_case_id: str, *, request_options: typing.Optional[RequestOptions] = None
     ) -> None: