vellum-ai 0.10.4__py3-none-any.whl → 0.10.7__py3-none-any.whl

vellum/__init__.py

@@ -186,6 +186,7 @@ from .types import (
     MetadataFilterRuleRequest,
     MetadataFiltersRequest,
     MetricDefinitionExecution,
+    MetricDefinitionHistoryItem,
     MetricDefinitionInput,
     MetricNodeResult,
     MlModelRead,
@@ -708,6 +709,7 @@ __all__ = [
     "MetadataFilterRuleRequest",
     "MetadataFiltersRequest",
     "MetricDefinitionExecution",
+    "MetricDefinitionHistoryItem",
     "MetricDefinitionInput",
     "MetricNodeResult",
     "MlModelRead",

vellum/client/README.md

@@ -91,82 +91,37 @@ The SDK supports streaming responses, as well, the response will be a generator
 
 ```python
 from vellum import (
-    AdHocExpandMeta,
-    EphemeralPromptCacheConfig,
-    FunctionDefinition,
     JinjaPromptBlock,
     PromptParameters,
     PromptRequestStringInput,
-    PromptSettings,
-    StringVellumValue,
     Vellum,
     VellumVariable,
-    VellumVariableExtensions,
 )
 
 client = Vellum(
     api_key="YOUR_API_KEY",
 )
 response = client.ad_hoc.adhoc_execute_prompt_stream(
-    ml_model="string",
+    ml_model="ml_model",
     input_values=[
         PromptRequestStringInput(
-            key="string",
-            value="string",
+            key="key",
+            value="value",
         )
     ],
     input_variables=[
         VellumVariable(
-            id="string",
-            key="string",
+            id="id",
+            key="key",
             type="STRING",
-            required=True,
-            default=StringVellumValue(
-                value="string",
-            ),
-            extensions=VellumVariableExtensions(
-                color={"key": "value"},
-            ),
         )
     ],
-    parameters=PromptParameters(
-        stop=["string"],
-        temperature=1.1,
-        max_tokens=1,
-        top_p=1.1,
-        top_k=1,
-        frequency_penalty=1.1,
-        presence_penalty=1.1,
-        logit_bias={"string": {"key": "value"}},
-        custom_parameters={"string": {"key": "value"}},
-    ),
-    settings=PromptSettings(
-        timeout=1.1,
-    ),
+    parameters=PromptParameters(),
     blocks=[
         JinjaPromptBlock(
-            state="ENABLED",
-            cache_config=EphemeralPromptCacheConfig(),
-            template="string",
+            template="template",
         )
     ],
-    functions=[
-        FunctionDefinition(
-            state="ENABLED",
-            cache_config=EphemeralPromptCacheConfig(),
-            name="string",
-            description="string",
-            parameters={"string": {"key": "value"}},
-            forced=True,
-            strict=True,
-        )
-    ],
-    expand_meta=AdHocExpandMeta(
-        cost=True,
-        model_name=True,
-        usage=True,
-        finish_reason=True,
-    ),
 )
 for chunk in response:
     yield chunk

vellum/client/__init__.py

@@ -447,12 +447,7 @@ class Vellum:
 
         Examples
         --------
-        from vellum import (
-            PromptDeploymentExpandMetaRequest,
-            RawPromptExecutionOverridesRequest,
-            StringInputRequest,
-            Vellum,
-        )
+        from vellum import StringInputRequest, Vellum
 
         client = Vellum(
             api_key="YOUR_API_KEY",
@@ -460,30 +455,10 @@ class Vellum:
         response = client.execute_prompt_stream(
             inputs=[
                 StringInputRequest(
-                    name="string",
-                    value="string",
+                    name="name",
+                    value="value",
                 )
             ],
-            prompt_deployment_id="string",
-            prompt_deployment_name="string",
-            release_tag="string",
-            external_id="string",
-            expand_meta=PromptDeploymentExpandMetaRequest(
-                model_name=True,
-                usage=True,
-                cost=True,
-                finish_reason=True,
-                latency=True,
-                deployment_release_tag=True,
-                prompt_version_id=True,
-            ),
-            raw_overrides=RawPromptExecutionOverridesRequest(
-                body={"string": {"key": "value"}},
-                headers={"string": {"key": "value"}},
-                url="string",
-            ),
-            expand_raw=["string"],
-            metadata={"string": {"key": "value"}},
         )
         for chunk in response:
             yield chunk
@@ -752,11 +727,7 @@ class Vellum:
 
         Examples
         --------
-        from vellum import (
-            Vellum,
-            WorkflowExpandMetaRequest,
-            WorkflowRequestStringInputRequest,
-        )
+        from vellum import Vellum, WorkflowRequestStringInputRequest
 
         client = Vellum(
             api_key="YOUR_API_KEY",
@@ -764,19 +735,10 @@ class Vellum:
         response = client.execute_workflow_stream(
             inputs=[
                 WorkflowRequestStringInputRequest(
-                    name="string",
-                    value="string",
+                    name="name",
+                    value="value",
                 )
             ],
-            expand_meta=WorkflowExpandMetaRequest(
-                usage=True,
-            ),
-            workflow_deployment_id="string",
-            workflow_deployment_name="string",
-            release_tag="string",
-            external_id="string",
-            event_types=["NODE"],
-            metadata={"string": {"key": "value"}},
         )
         for chunk in response:
             yield chunk
@@ -1016,39 +978,17 @@ class Vellum:
 
         Examples
         --------
-        from vellum import (
-            ChatMessageRequest,
-            GenerateOptionsRequest,
-            GenerateRequest,
-            StringChatMessageContentRequest,
-            Vellum,
-        )
+        from vellum import GenerateRequest, Vellum
 
         client = Vellum(
             api_key="YOUR_API_KEY",
         )
         response = client.generate_stream(
-            deployment_id="string",
-            deployment_name="string",
             requests=[
                 GenerateRequest(
-                    input_values={"string": {"key": "value"}},
-                    chat_history=[
-                        ChatMessageRequest(
-                            text="string",
-                            role="SYSTEM",
-                            content=StringChatMessageContentRequest(
-                                value="string",
-                            ),
-                            source="string",
-                        )
-                    ],
-                    external_ids=["string"],
+                    input_values={"key": "value"},
                 )
             ],
-            options=GenerateOptionsRequest(
-                logprobs="ALL",
-            ),
         )
         for chunk in response:
             yield chunk
@@ -1785,12 +1725,7 @@ class AsyncVellum:
         --------
         import asyncio
 
-        from vellum import (
-            AsyncVellum,
-            PromptDeploymentExpandMetaRequest,
-            RawPromptExecutionOverridesRequest,
-            StringInputRequest,
-        )
+        from vellum import AsyncVellum, StringInputRequest
 
         client = AsyncVellum(
             api_key="YOUR_API_KEY",
@@ -1801,30 +1736,10 @@ class AsyncVellum:
             response = await client.execute_prompt_stream(
                 inputs=[
                     StringInputRequest(
-                        name="string",
-                        value="string",
+                        name="name",
+                        value="value",
                     )
                 ],
-                prompt_deployment_id="string",
-                prompt_deployment_name="string",
-                release_tag="string",
-                external_id="string",
-                expand_meta=PromptDeploymentExpandMetaRequest(
-                    model_name=True,
-                    usage=True,
-                    cost=True,
-                    finish_reason=True,
-                    latency=True,
-                    deployment_release_tag=True,
-                    prompt_version_id=True,
-                ),
-                raw_overrides=RawPromptExecutionOverridesRequest(
-                    body={"string": {"key": "value"}},
-                    headers={"string": {"key": "value"}},
-                    url="string",
-                ),
-                expand_raw=["string"],
-                metadata={"string": {"key": "value"}},
             )
             async for chunk in response:
                 yield chunk
@@ -2106,11 +2021,7 @@ class AsyncVellum:
         --------
         import asyncio
 
-        from vellum import (
-            AsyncVellum,
-            WorkflowExpandMetaRequest,
-            WorkflowRequestStringInputRequest,
-        )
+        from vellum import AsyncVellum, WorkflowRequestStringInputRequest
 
         client = AsyncVellum(
             api_key="YOUR_API_KEY",
@@ -2121,19 +2032,10 @@ class AsyncVellum:
             response = await client.execute_workflow_stream(
                 inputs=[
                     WorkflowRequestStringInputRequest(
-                        name="string",
-                        value="string",
+                        name="name",
+                        value="value",
                     )
                 ],
-                expand_meta=WorkflowExpandMetaRequest(
-                    usage=True,
-                ),
-                workflow_deployment_id="string",
-                workflow_deployment_name="string",
-                release_tag="string",
-                external_id="string",
-                event_types=["NODE"],
-                metadata={"string": {"key": "value"}},
             )
             async for chunk in response:
                 yield chunk
@@ -2386,13 +2288,7 @@ class AsyncVellum:
         --------
         import asyncio
 
-        from vellum import (
-            AsyncVellum,
-            ChatMessageRequest,
-            GenerateOptionsRequest,
-            GenerateRequest,
-            StringChatMessageContentRequest,
-        )
+        from vellum import AsyncVellum, GenerateRequest
 
         client = AsyncVellum(
             api_key="YOUR_API_KEY",
@@ -2401,27 +2297,11 @@ class AsyncVellum:
 
         async def main() -> None:
             response = await client.generate_stream(
-                deployment_id="string",
-                deployment_name="string",
                 requests=[
                     GenerateRequest(
-                        input_values={"string": {"key": "value"}},
-                        chat_history=[
-                            ChatMessageRequest(
-                                text="string",
-                                role="SYSTEM",
-                                content=StringChatMessageContentRequest(
-                                    value="string",
-                                ),
-                                source="string",
-                            )
-                        ],
-                        external_ids=["string"],
+                        input_values={"key": "value"},
                     )
                 ],
-                options=GenerateOptionsRequest(
-                    logprobs="ALL",
-                ),
             )
             async for chunk in response:
                 yield chunk

vellum/client/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": "0.10.4",
+            "X-Fern-SDK-Version": "0.10.7",
         }
         headers["X_API_KEY"] = self.api_key
         return headers

vellum/client/resources/ad_hoc/client.py

@@ -74,82 +74,37 @@ class AdHocClient:
         Examples
         --------
         from vellum import (
-            AdHocExpandMeta,
-            EphemeralPromptCacheConfig,
-            FunctionDefinition,
             JinjaPromptBlock,
             PromptParameters,
             PromptRequestStringInput,
-            PromptSettings,
-            StringVellumValue,
             Vellum,
             VellumVariable,
-            VellumVariableExtensions,
         )
 
         client = Vellum(
             api_key="YOUR_API_KEY",
         )
         response = client.ad_hoc.adhoc_execute_prompt_stream(
-            ml_model="string",
+            ml_model="ml_model",
             input_values=[
                 PromptRequestStringInput(
-                    key="string",
-                    value="string",
+                    key="key",
+                    value="value",
                 )
             ],
             input_variables=[
                 VellumVariable(
-                    id="string",
-                    key="string",
+                    id="id",
+                    key="key",
                     type="STRING",
-                    required=True,
-                    default=StringVellumValue(
-                        value="string",
-                    ),
-                    extensions=VellumVariableExtensions(
-                        color={"key": "value"},
-                    ),
                 )
             ],
-            parameters=PromptParameters(
-                stop=["string"],
-                temperature=1.1,
-                max_tokens=1,
-                top_p=1.1,
-                top_k=1,
-                frequency_penalty=1.1,
-                presence_penalty=1.1,
-                logit_bias={"string": {"key": "value"}},
-                custom_parameters={"string": {"key": "value"}},
-            ),
-            settings=PromptSettings(
-                timeout=1.1,
-            ),
+            parameters=PromptParameters(),
             blocks=[
                 JinjaPromptBlock(
-                    state="ENABLED",
-                    cache_config=EphemeralPromptCacheConfig(),
-                    template="string",
+                    template="template",
                 )
             ],
-            functions=[
-                FunctionDefinition(
-                    state="ENABLED",
-                    cache_config=EphemeralPromptCacheConfig(),
-                    name="string",
-                    description="string",
-                    parameters={"string": {"key": "value"}},
-                    forced=True,
-                    strict=True,
-                )
-            ],
-            expand_meta=AdHocExpandMeta(
-                cost=True,
-                model_name=True,
-                usage=True,
-                finish_reason=True,
-            ),
         )
         for chunk in response:
             yield chunk
@@ -289,17 +244,11 @@ class AsyncAdHocClient:
         import asyncio
 
         from vellum import (
-            AdHocExpandMeta,
             AsyncVellum,
-            EphemeralPromptCacheConfig,
-            FunctionDefinition,
             JinjaPromptBlock,
             PromptParameters,
             PromptRequestStringInput,
-            PromptSettings,
-            StringVellumValue,
             VellumVariable,
-            VellumVariableExtensions,
         )
 
         client = AsyncVellum(
@@ -309,65 +258,26 @@ class AsyncAdHocClient:
 
         async def main() -> None:
             response = await client.ad_hoc.adhoc_execute_prompt_stream(
-                ml_model="string",
+                ml_model="ml_model",
                 input_values=[
                     PromptRequestStringInput(
-                        key="string",
-                        value="string",
+                        key="key",
+                        value="value",
                     )
                 ],
                 input_variables=[
                     VellumVariable(
-                        id="string",
-                        key="string",
+                        id="id",
+                        key="key",
                         type="STRING",
-                        required=True,
-                        default=StringVellumValue(
-                            value="string",
-                        ),
-                        extensions=VellumVariableExtensions(
-                            color={"key": "value"},
-                        ),
                     )
                 ],
-                parameters=PromptParameters(
-                    stop=["string"],
-                    temperature=1.1,
-                    max_tokens=1,
-                    top_p=1.1,
-                    top_k=1,
-                    frequency_penalty=1.1,
-                    presence_penalty=1.1,
-                    logit_bias={"string": {"key": "value"}},
-                    custom_parameters={"string": {"key": "value"}},
-                ),
-                settings=PromptSettings(
-                    timeout=1.1,
-                ),
+                parameters=PromptParameters(),
                 blocks=[
                     JinjaPromptBlock(
-                        state="ENABLED",
-                        cache_config=EphemeralPromptCacheConfig(),
-                        template="string",
+                        template="template",
                     )
                 ],
-                functions=[
-                    FunctionDefinition(
-                        state="ENABLED",
-                        cache_config=EphemeralPromptCacheConfig(),
-                        name="string",
-                        description="string",
-                        parameters={"string": {"key": "value"}},
-                        forced=True,
-                        strict=True,
-                    )
-                ],
-                expand_meta=AdHocExpandMeta(
-                    cost=True,
-                    model_name=True,
-                    usage=True,
-                    finish_reason=True,
-                ),
             )
             async for chunk in response:
                 yield chunk

vellum/client/resources/metric_definitions/client.py

@@ -10,6 +10,7 @@ from ...core.serialization import convert_and_respect_annotation_metadata
 from ...core.pydantic_utilities import parse_obj_as
 from json.decoder import JSONDecodeError
 from ...core.api_error import ApiError
+from ...types.metric_definition_history_item import MetricDefinitionHistoryItem
 from ...core.client_wrapper import AsyncClientWrapper
 
 # this is used as the default value for optional parameters
@@ -92,6 +93,58 @@ class MetricDefinitionsClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    def metric_definition_history_item_retrieve(
+        self, history_id_or_release_tag: str, id: str, *, request_options: typing.Optional[RequestOptions] = None
+    ) -> MetricDefinitionHistoryItem:
+        """
+        Parameters
+        ----------
+        history_id_or_release_tag : str
+            Either the UUID of Metric Definition History Item you'd like to retrieve, or the name of a Release Tag that's pointing to the Metric Definition History Item you'd like to retrieve.
+
+        id : str
+            A UUID string identifying this metric definition.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        MetricDefinitionHistoryItem
+
+
+        Examples
+        --------
+        from vellum import Vellum
+
+        client = Vellum(
+            api_key="YOUR_API_KEY",
+        )
+        client.metric_definitions.metric_definition_history_item_retrieve(
+            history_id_or_release_tag="history_id_or_release_tag",
+            id="id",
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            f"v1/metric-definitions/{jsonable_encoder(id)}/history/{jsonable_encoder(history_id_or_release_tag)}",
+            base_url=self._client_wrapper.get_environment().default,
+            method="GET",
+            request_options=request_options,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    MetricDefinitionHistoryItem,
+                    parse_obj_as(
+                        type_=MetricDefinitionHistoryItem,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
 
 class AsyncMetricDefinitionsClient:
     def __init__(self, *, client_wrapper: AsyncClientWrapper):
@@ -176,3 +229,63 @@ class AsyncMetricDefinitionsClient:
         except JSONDecodeError:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    async def metric_definition_history_item_retrieve(
+        self, history_id_or_release_tag: str, id: str, *, request_options: typing.Optional[RequestOptions] = None
+    ) -> MetricDefinitionHistoryItem:
+        """
+        Parameters
+        ----------
+        history_id_or_release_tag : str
+            Either the UUID of Metric Definition History Item you'd like to retrieve, or the name of a Release Tag that's pointing to the Metric Definition History Item you'd like to retrieve.
+
+        id : str
+            A UUID string identifying this metric definition.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        MetricDefinitionHistoryItem
+
+
+        Examples
+        --------
+        import asyncio
+
+        from vellum import AsyncVellum
+
+        client = AsyncVellum(
+            api_key="YOUR_API_KEY",
+        )
+
+
+        async def main() -> None:
+            await client.metric_definitions.metric_definition_history_item_retrieve(
+                history_id_or_release_tag="history_id_or_release_tag",
+                id="id",
+            )
+
+
+        asyncio.run(main())
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            f"v1/metric-definitions/{jsonable_encoder(id)}/history/{jsonable_encoder(history_id_or_release_tag)}",
+            base_url=self._client_wrapper.get_environment().default,
+            method="GET",
+            request_options=request_options,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    MetricDefinitionHistoryItem,
+                    parse_obj_as(
+                        type_=MetricDefinitionHistoryItem,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            _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)