scale-gp-beta 0.1.0a2__py3-none-any.whl → 0.1.0a4__py3-none-any.whl

{scale_gp → scale_gp_beta}/__init__.py

@@ -85,12 +85,12 @@ _setup_logging()
 # Update the __module__ attribute for exported symbols so that
 # error messages point to this module instead of the module
 # it was originally defined in, e.g.
-# scale_gp._exceptions.NotFoundError -> scale_gp.NotFoundError
+# scale_gp_beta._exceptions.NotFoundError -> scale_gp_beta.NotFoundError
 __locals = locals()
 for __name in __all__:
     if not __name.startswith("__"):
         try:
-            __locals[__name].__module__ = "scale_gp"
+            __locals[__name].__module__ = "scale_gp_beta"
         except (TypeError, AttributeError):
             # Some of our exported symbols are builtins which we can't set attributes for.
             pass

{scale_gp → scale_gp_beta}/_base_client.py

@@ -9,7 +9,6 @@ import asyncio
 import inspect
 import logging
 import platform
-import warnings
 import email.utils
 from types import TracebackType
 from random import random
@@ -36,7 +35,7 @@ import anyio
 import httpx
 import distro
 import pydantic
-from httpx import URL, Limits
+from httpx import URL
 from pydantic import PrivateAttr
 
 from . import _exceptions
@@ -51,19 +50,16 @@ from ._types import (
     Timeout,
     NotGiven,
     ResponseT,
-    Transport,
     AnyMapping,
     PostParser,
-    ProxiesTypes,
     RequestFiles,
     HttpxSendArgs,
-    AsyncTransport,
     RequestOptions,
     HttpxRequestFiles,
     ModelBuilderProtocol,
 )
 from ._utils import is_dict, is_list, asyncify, is_given, lru_cache, is_mapping
-from ._compat import model_copy, model_dump
+from ._compat import PYDANTIC_V2, model_copy, model_dump
 from ._models import GenericModel, FinalRequestOptions, validate_type, construct_type
 from ._response import (
     APIResponse,
@@ -207,6 +203,9 @@ class BaseSyncPage(BasePage[_T], Generic[_T]):
         model: Type[_T],
         options: FinalRequestOptions,
     ) -> None:
+        if PYDANTIC_V2 and getattr(self, "__pydantic_private__", None) is None:
+            self.__pydantic_private__ = {}
+
         self._model = model
         self._client = client
         self._options = options
@@ -292,6 +291,9 @@ class BaseAsyncPage(BasePage[_T], Generic[_T]):
         client: AsyncAPIClient,
         options: FinalRequestOptions,
     ) -> None:
+        if PYDANTIC_V2 and getattr(self, "__pydantic_private__", None) is None:
+            self.__pydantic_private__ = {}
+
         self._model = model
         self._client = client
         self._options = options
@@ -331,9 +333,6 @@ class BaseClient(Generic[_HttpxClientT, _DefaultStreamT]):
     _base_url: URL
     max_retries: int
     timeout: Union[float, Timeout, None]
-    _limits: httpx.Limits
-    _proxies: ProxiesTypes | None
-    _transport: Transport | AsyncTransport | None
     _strict_response_validation: bool
     _idempotency_header: str | None
     _default_stream_cls: type[_DefaultStreamT] | None = None
@@ -346,9 +345,6 @@ class BaseClient(Generic[_HttpxClientT, _DefaultStreamT]):
         _strict_response_validation: bool,
         max_retries: int = DEFAULT_MAX_RETRIES,
         timeout: float | Timeout | None = DEFAULT_TIMEOUT,
-        limits: httpx.Limits,
-        transport: Transport | AsyncTransport | None,
-        proxies: ProxiesTypes | None,
         custom_headers: Mapping[str, str] | None = None,
         custom_query: Mapping[str, object] | None = None,
     ) -> None:
@@ -356,9 +352,6 @@ class BaseClient(Generic[_HttpxClientT, _DefaultStreamT]):
         self._base_url = self._enforce_trailing_slash(URL(base_url))
         self.max_retries = max_retries
         self.timeout = timeout
-        self._limits = limits
-        self._proxies = proxies
-        self._transport = transport
         self._custom_headers = custom_headers or {}
         self._custom_query = custom_query or {}
         self._strict_response_validation = _strict_response_validation
@@ -367,7 +360,7 @@ class BaseClient(Generic[_HttpxClientT, _DefaultStreamT]):
 
         if max_retries is None:  # pyright: ignore[reportUnnecessaryComparison]
             raise TypeError(
-                "max_retries cannot be None. If you want to disable retries, pass `0`; if you want unlimited retries, pass `math.inf` or a very high number; if you want the default behavior, pass `scale_gp.DEFAULT_MAX_RETRIES`"
+                "max_retries cannot be None. If you want to disable retries, pass `0`; if you want unlimited retries, pass `math.inf` or a very high number; if you want the default behavior, pass `scale_gp_beta.DEFAULT_MAX_RETRIES`"
             )
 
     def _enforce_trailing_slash(self, url: URL) -> URL:
@@ -518,7 +511,7 @@ class BaseClient(Generic[_HttpxClientT, _DefaultStreamT]):
             # so that passing a `TypedDict` doesn't cause an error.
             # https://github.com/microsoft/pyright/issues/3526#event-6715453066
             params=self.qs.stringify(cast(Mapping[str, Any], params)) if params else None,
-            json=json_data,
+            json=json_data if is_given(json_data) else None,
             files=files,
             **kwargs,
         )
@@ -794,46 +787,11 @@ class SyncAPIClient(BaseClient[httpx.Client, Stream[Any]]):
         base_url: str | URL,
         max_retries: int = DEFAULT_MAX_RETRIES,
         timeout: float | Timeout | None | NotGiven = NOT_GIVEN,
-        transport: Transport | None = None,
-        proxies: ProxiesTypes | None = None,
-        limits: Limits | None = None,
         http_client: httpx.Client | None = None,
         custom_headers: Mapping[str, str] | None = None,
         custom_query: Mapping[str, object] | None = None,
         _strict_response_validation: bool,
     ) -> None:
-        kwargs: dict[str, Any] = {}
-        if limits is not None:
-            warnings.warn(
-                "The `connection_pool_limits` argument is deprecated. The `http_client` argument should be passed instead",
-                category=DeprecationWarning,
-                stacklevel=3,
-            )
-            if http_client is not None:
-                raise ValueError("The `http_client` argument is mutually exclusive with `connection_pool_limits`")
-        else:
-            limits = DEFAULT_CONNECTION_LIMITS
-
-        if transport is not None:
-            kwargs["transport"] = transport
-            warnings.warn(
-                "The `transport` argument is deprecated. The `http_client` argument should be passed instead",
-                category=DeprecationWarning,
-                stacklevel=3,
-            )
-            if http_client is not None:
-                raise ValueError("The `http_client` argument is mutually exclusive with `transport`")
-
-        if proxies is not None:
-            kwargs["proxies"] = proxies
-            warnings.warn(
-                "The `proxies` argument is deprecated. The `http_client` argument should be passed instead",
-                category=DeprecationWarning,
-                stacklevel=3,
-            )
-            if http_client is not None:
-                raise ValueError("The `http_client` argument is mutually exclusive with `proxies`")
-
         if not is_given(timeout):
             # if the user passed in a custom http client with a non-default
             # timeout set then we use that timeout.
@@ -854,12 +812,9 @@ class SyncAPIClient(BaseClient[httpx.Client, Stream[Any]]):
 
         super().__init__(
             version=version,
-            limits=limits,
             # cast to a valid type because mypy doesn't understand our type narrowing
             timeout=cast(Timeout, timeout),
-            proxies=proxies,
             base_url=base_url,
-            transport=transport,
             max_retries=max_retries,
             custom_query=custom_query,
             custom_headers=custom_headers,
@@ -869,9 +824,6 @@ class SyncAPIClient(BaseClient[httpx.Client, Stream[Any]]):
             base_url=base_url,
             # cast to a valid type because mypy doesn't understand our type narrowing
             timeout=cast(Timeout, timeout),
-            limits=limits,
-            follow_redirects=True,
-            **kwargs,  # type: ignore
         )
 
     def is_closed(self) -> bool:
@@ -1366,45 +1318,10 @@ class AsyncAPIClient(BaseClient[httpx.AsyncClient, AsyncStream[Any]]):
         _strict_response_validation: bool,
         max_retries: int = DEFAULT_MAX_RETRIES,
         timeout: float | Timeout | None | NotGiven = NOT_GIVEN,
-        transport: AsyncTransport | None = None,
-        proxies: ProxiesTypes | None = None,
-        limits: Limits | None = None,
         http_client: httpx.AsyncClient | None = None,
         custom_headers: Mapping[str, str] | None = None,
         custom_query: Mapping[str, object] | None = None,
     ) -> None:
-        kwargs: dict[str, Any] = {}
-        if limits is not None:
-            warnings.warn(
-                "The `connection_pool_limits` argument is deprecated. The `http_client` argument should be passed instead",
-                category=DeprecationWarning,
-                stacklevel=3,
-            )
-            if http_client is not None:
-                raise ValueError("The `http_client` argument is mutually exclusive with `connection_pool_limits`")
-        else:
-            limits = DEFAULT_CONNECTION_LIMITS
-
-        if transport is not None:
-            kwargs["transport"] = transport
-            warnings.warn(
-                "The `transport` argument is deprecated. The `http_client` argument should be passed instead",
-                category=DeprecationWarning,
-                stacklevel=3,
-            )
-            if http_client is not None:
-                raise ValueError("The `http_client` argument is mutually exclusive with `transport`")
-
-        if proxies is not None:
-            kwargs["proxies"] = proxies
-            warnings.warn(
-                "The `proxies` argument is deprecated. The `http_client` argument should be passed instead",
-                category=DeprecationWarning,
-                stacklevel=3,
-            )
-            if http_client is not None:
-                raise ValueError("The `http_client` argument is mutually exclusive with `proxies`")
-
         if not is_given(timeout):
             # if the user passed in a custom http client with a non-default
             # timeout set then we use that timeout.
@@ -1426,11 +1343,8 @@ class AsyncAPIClient(BaseClient[httpx.AsyncClient, AsyncStream[Any]]):
         super().__init__(
             version=version,
             base_url=base_url,
-            limits=limits,
             # cast to a valid type because mypy doesn't understand our type narrowing
             timeout=cast(Timeout, timeout),
-            proxies=proxies,
-            transport=transport,
             max_retries=max_retries,
             custom_query=custom_query,
             custom_headers=custom_headers,
@@ -1440,9 +1354,6 @@ class AsyncAPIClient(BaseClient[httpx.AsyncClient, AsyncStream[Any]]):
             base_url=base_url,
             # cast to a valid type because mypy doesn't understand our type narrowing
             timeout=cast(Timeout, timeout),
-            limits=limits,
-            follow_redirects=True,
-            **kwargs,  # type: ignore
         )
 
     def is_closed(self) -> bool:

{scale_gp → scale_gp_beta}/_client.py

@@ -316,7 +316,7 @@ class AsyncSGPClient(AsyncAPIClient):
         # part of our public interface in the future.
         _strict_response_validation: bool = False,
     ) -> None:
-        """Construct a new async SGPClient client instance.
+        """Construct a new async AsyncSGPClient client instance.
 
         This automatically infers the following arguments from their corresponding environment variables if they are not provided:
         - `api_key` from `SGP_API_KEY`

{scale_gp → scale_gp_beta}/_files.py

@@ -34,7 +34,7 @@ def assert_is_file_content(obj: object, *, key: str | None = None) -> None:
     if not is_file_content(obj):
         prefix = f"Expected entry at `{key}`" if key is not None else f"Expected file input `{obj!r}`"
         raise RuntimeError(
-            f"{prefix} to be bytes, an io.IOBase instance, PathLike or a tuple but received {type(obj)} instead."
+            f"{prefix} to be bytes, an io.IOBase instance, PathLike or a tuple but received {type(obj)} instead. See https://github.com/scaleapi/sgp-python-beta/tree/main#file-uploads"
         ) from None
 
 

{scale_gp → scale_gp_beta}/_models.py

@@ -65,7 +65,7 @@ from ._compat import (
 from ._constants import RAW_RESPONSE_HEADER
 
 if TYPE_CHECKING:
-    from pydantic_core.core_schema import ModelField, LiteralSchema, ModelFieldsSchema
+    from pydantic_core.core_schema import ModelField, ModelSchema, LiteralSchema, ModelFieldsSchema
 
 __all__ = ["BaseModel", "GenericModel"]
 
@@ -646,15 +646,18 @@ def _build_discriminated_union_meta(*, union: type, meta_annotations: tuple[Any,
 
 def _extract_field_schema_pv2(model: type[BaseModel], field_name: str) -> ModelField | None:
     schema = model.__pydantic_core_schema__
+    if schema["type"] == "definitions":
+        schema = schema["schema"]
+
     if schema["type"] != "model":
         return None
 
+    schema = cast("ModelSchema", schema)
     fields_schema = schema["schema"]
     if fields_schema["type"] != "model-fields":
         return None
 
     fields_schema = cast("ModelFieldsSchema", fields_schema)
-
     field = fields_schema["fields"].get(field_name)
     if not field:
         return None

{scale_gp → scale_gp_beta}/_response.py

@@ -217,7 +217,9 @@ class BaseAPIResponse(Generic[R]):
             and not issubclass(origin, BaseModel)
             and issubclass(origin, pydantic.BaseModel)
         ):
-            raise TypeError("Pydantic models must subclass our base model type, e.g. `from scale_gp import BaseModel`")
+            raise TypeError(
+                "Pydantic models must subclass our base model type, e.g. `from scale_gp_beta import BaseModel`"
+            )
 
         if (
             cast_to is not object
@@ -283,7 +285,7 @@ class APIResponse(BaseAPIResponse[R]):
         the `to` argument, e.g.
 
         ```py
-        from scale_gp import BaseModel
+        from scale_gp_beta import BaseModel
 
 
         class MyModel(BaseModel):
@@ -385,7 +387,7 @@ class AsyncAPIResponse(BaseAPIResponse[R]):
         the `to` argument, e.g.
 
         ```py
-        from scale_gp import BaseModel
+        from scale_gp_beta import BaseModel
 
 
         class MyModel(BaseModel):
@@ -556,7 +558,7 @@ class AsyncStreamedBinaryAPIResponse(AsyncAPIResponse[bytes]):
 class MissingStreamClassError(TypeError):
     def __init__(self) -> None:
         super().__init__(
-            "The `stream` argument was set to `True` but the `stream_cls` argument was not given. See `scale_gp._streaming` for reference",
+            "The `stream` argument was set to `True` but the `stream_cls` argument was not given. See `scale_gp_beta._streaming` for reference",
         )
 
 

{scale_gp → scale_gp_beta}/_types.py

@@ -81,7 +81,7 @@ HttpxRequestFiles = Union[Mapping[str, HttpxFileTypes], Sequence[Tuple[str, Http
 # This unfortunately means that you will either have
 # to import this type and pass it explicitly:
 #
-# from scale_gp import NoneType
+# from scale_gp_beta import NoneType
 # client.get('/foo', cast_to=NoneType)
 #
 # or build it yourself:

{scale_gp → scale_gp_beta}/_utils/_logs.py

@@ -1,12 +1,12 @@
 import os
 import logging
 
-logger: logging.Logger = logging.getLogger("scale_gp")
+logger: logging.Logger = logging.getLogger("scale_gp_beta")
 httpx_logger: logging.Logger = logging.getLogger("httpx")
 
 
 def _basic_config() -> None:
-    # e.g. [2023-10-05 14:12:26 - scale_gp._base_client:818 - DEBUG] HTTP Request: POST http://127.0.0.1:4010/foo/bar "200 OK"
+    # e.g. [2023-10-05 14:12:26 - scale_gp_beta._base_client:818 - DEBUG] HTTP Request: POST http://127.0.0.1:4010/foo/bar "200 OK"
     logging.basicConfig(
         format="[%(asctime)s - %(name)s:%(lineno)d - %(levelname)s] %(message)s",
         datefmt="%Y-%m-%d %H:%M:%S",

{scale_gp → scale_gp_beta}/_version.py

@@ -1,4 +1,4 @@
 # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
-__title__ = "scale_gp"
-__version__ = "0.1.0-alpha.2"  # x-release-please-version
+__title__ = "scale_gp_beta"
+__version__ = "0.1.0-alpha.4"  # x-release-please-version

{scale_gp → scale_gp_beta}/resources/chat/completions.py

@@ -474,53 +474,50 @@ class CompletionsResource(SyncAPIResource):
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
     ) -> CompletionCreateResponse | Stream[ChatCompletionChunk]:
-        return cast(
-            CompletionCreateResponse,
-            self._post(
-                "/v5/chat/completions",
-                body=maybe_transform(
-                    {
-                        "messages": messages,
-                        "model": model,
-                        "audio": audio,
-                        "frequency_penalty": frequency_penalty,
-                        "function_call": function_call,
-                        "functions": functions,
-                        "logit_bias": logit_bias,
-                        "logprobs": logprobs,
-                        "max_completion_tokens": max_completion_tokens,
-                        "max_tokens": max_tokens,
-                        "metadata": metadata,
-                        "modalities": modalities,
-                        "n": n,
-                        "parallel_tool_calls": parallel_tool_calls,
-                        "prediction": prediction,
-                        "presence_penalty": presence_penalty,
-                        "reasoning_effort": reasoning_effort,
-                        "response_format": response_format,
-                        "seed": seed,
-                        "stop": stop,
-                        "store": store,
-                        "stream": stream,
-                        "stream_options": stream_options,
-                        "temperature": temperature,
-                        "tool_choice": tool_choice,
-                        "tools": tools,
-                        "top_k": top_k,
-                        "top_logprobs": top_logprobs,
-                        "top_p": top_p,
-                    },
-                    completion_create_params.CompletionCreateParams,
-                ),
-                options=make_request_options(
-                    extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
-                ),
-                cast_to=cast(
-                    Any, CompletionCreateResponse
-                ),  # Union types cannot be passed in as arguments in the type system
-                stream=stream or False,
-                stream_cls=Stream[ChatCompletionChunk],
+        return self._post(
+            "/v5/chat/completions",
+            body=maybe_transform(
+                {
+                    "messages": messages,
+                    "model": model,
+                    "audio": audio,
+                    "frequency_penalty": frequency_penalty,
+                    "function_call": function_call,
+                    "functions": functions,
+                    "logit_bias": logit_bias,
+                    "logprobs": logprobs,
+                    "max_completion_tokens": max_completion_tokens,
+                    "max_tokens": max_tokens,
+                    "metadata": metadata,
+                    "modalities": modalities,
+                    "n": n,
+                    "parallel_tool_calls": parallel_tool_calls,
+                    "prediction": prediction,
+                    "presence_penalty": presence_penalty,
+                    "reasoning_effort": reasoning_effort,
+                    "response_format": response_format,
+                    "seed": seed,
+                    "stop": stop,
+                    "store": store,
+                    "stream": stream,
+                    "stream_options": stream_options,
+                    "temperature": temperature,
+                    "tool_choice": tool_choice,
+                    "tools": tools,
+                    "top_k": top_k,
+                    "top_logprobs": top_logprobs,
+                    "top_p": top_p,
+                },
+                completion_create_params.CompletionCreateParams,
             ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=cast(
+                Any, CompletionCreateResponse
+            ),  # Union types cannot be passed in as arguments in the type system
+            stream=stream or False,
+            stream_cls=Stream[ChatCompletionChunk],
         )
 
 
@@ -968,53 +965,50 @@ class AsyncCompletionsResource(AsyncAPIResource):
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
     ) -> CompletionCreateResponse | AsyncStream[ChatCompletionChunk]:
-        return cast(
-            CompletionCreateResponse,
-            await self._post(
-                "/v5/chat/completions",
-                body=await async_maybe_transform(
-                    {
-                        "messages": messages,
-                        "model": model,
-                        "audio": audio,
-                        "frequency_penalty": frequency_penalty,
-                        "function_call": function_call,
-                        "functions": functions,
-                        "logit_bias": logit_bias,
-                        "logprobs": logprobs,
-                        "max_completion_tokens": max_completion_tokens,
-                        "max_tokens": max_tokens,
-                        "metadata": metadata,
-                        "modalities": modalities,
-                        "n": n,
-                        "parallel_tool_calls": parallel_tool_calls,
-                        "prediction": prediction,
-                        "presence_penalty": presence_penalty,
-                        "reasoning_effort": reasoning_effort,
-                        "response_format": response_format,
-                        "seed": seed,
-                        "stop": stop,
-                        "store": store,
-                        "stream": stream,
-                        "stream_options": stream_options,
-                        "temperature": temperature,
-                        "tool_choice": tool_choice,
-                        "tools": tools,
-                        "top_k": top_k,
-                        "top_logprobs": top_logprobs,
-                        "top_p": top_p,
-                    },
-                    completion_create_params.CompletionCreateParams,
-                ),
-                options=make_request_options(
-                    extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
-                ),
-                cast_to=cast(
-                    Any, CompletionCreateResponse
-                ),  # Union types cannot be passed in as arguments in the type system
-                stream=stream or False,
-                stream_cls=AsyncStream[ChatCompletionChunk],
+        return await self._post(
+            "/v5/chat/completions",
+            body=await async_maybe_transform(
+                {
+                    "messages": messages,
+                    "model": model,
+                    "audio": audio,
+                    "frequency_penalty": frequency_penalty,
+                    "function_call": function_call,
+                    "functions": functions,
+                    "logit_bias": logit_bias,
+                    "logprobs": logprobs,
+                    "max_completion_tokens": max_completion_tokens,
+                    "max_tokens": max_tokens,
+                    "metadata": metadata,
+                    "modalities": modalities,
+                    "n": n,
+                    "parallel_tool_calls": parallel_tool_calls,
+                    "prediction": prediction,
+                    "presence_penalty": presence_penalty,
+                    "reasoning_effort": reasoning_effort,
+                    "response_format": response_format,
+                    "seed": seed,
+                    "stop": stop,
+                    "store": store,
+                    "stream": stream,
+                    "stream_options": stream_options,
+                    "temperature": temperature,
+                    "tool_choice": tool_choice,
+                    "tools": tools,
+                    "top_k": top_k,
+                    "top_logprobs": top_logprobs,
+                    "top_p": top_p,
+                },
+                completion_create_params.CompletionCreateParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
             ),
+            cast_to=cast(
+                Any, CompletionCreateResponse
+            ),  # Union types cannot be passed in as arguments in the type system
+            stream=stream or False,
+            stream_cls=AsyncStream[ChatCompletionChunk],
         )
 
 

{scale_gp → scale_gp_beta}/resources/models.py

@@ -310,7 +310,19 @@ class ModelsResource(SyncAPIResource):
         ending_before: Optional[str] | NotGiven = NOT_GIVEN,
         limit: int | NotGiven = NOT_GIVEN,
         model_vendor: Optional[
-            Literal["openai", "cohere", "vertex_ai", "anthropic", "launch", "llmengine", "model_zoo"]
+            Literal[
+                "openai",
+                "cohere",
+                "vertex_ai",
+                "anthropic",
+                "azure",
+                "gemini",
+                "launch",
+                "llmengine",
+                "model_zoo",
+                "bedrock",
+                "xai",
+            ]
         ]
         | NotGiven = NOT_GIVEN,
         name: Optional[str] | NotGiven = NOT_GIVEN,
@@ -670,7 +682,19 @@ class AsyncModelsResource(AsyncAPIResource):
         ending_before: Optional[str] | NotGiven = NOT_GIVEN,
         limit: int | NotGiven = NOT_GIVEN,
         model_vendor: Optional[
-            Literal["openai", "cohere", "vertex_ai", "anthropic", "launch", "llmengine", "model_zoo"]
+            Literal[
+                "openai",
+                "cohere",
+                "vertex_ai",
+                "anthropic",
+                "azure",
+                "gemini",
+                "launch",
+                "llmengine",
+                "model_zoo",
+                "bedrock",
+                "xai",
+            ]
         ]
         | NotGiven = NOT_GIVEN,
         name: Optional[str] | NotGiven = NOT_GIVEN,

{scale_gp → scale_gp_beta}/types/inference_model.py

@@ -152,16 +152,30 @@ class InferenceModel(BaseModel):
 
     api_model_type: Literal["generic", "completion", "chat_completion"] = FieldInfo(alias="model_type")
 
-    api_model_vendor: Literal["openai", "cohere", "vertex_ai", "anthropic", "launch", "llmengine", "model_zoo"] = (
-        FieldInfo(alias="model_vendor")
-    )
+    api_model_vendor: Literal[
+        "openai",
+        "cohere",
+        "vertex_ai",
+        "anthropic",
+        "azure",
+        "gemini",
+        "launch",
+        "llmengine",
+        "model_zoo",
+        "bedrock",
+        "xai",
+    ] = FieldInfo(alias="model_vendor")
 
     name: str
 
     status: Literal["failed", "ready", "deploying"]
 
-    vendor_configuration: VendorConfiguration
+    description: Optional[str] = None
+
+    display_name: Optional[str] = None
 
     api_model_metadata: Optional[Dict[str, object]] = FieldInfo(alias="model_metadata", default=None)
 
     object: Optional[Literal["model"]] = None
+
+    vendor_configuration: Optional[VendorConfiguration] = None