Initial commit: Email alerts application

venv/lib/python3.11/site-packages/groq/__init__.py

@@ -0,0 +1,90 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+import typing as _t
+
+from . import types
+from ._types import NOT_GIVEN, Omit, NoneType, NotGiven, Transport, ProxiesTypes
+from ._utils import file_from_path
+from ._client import Groq, Client, Stream, Timeout, AsyncGroq, Transport, AsyncClient, AsyncStream, RequestOptions
+from ._models import BaseModel
+from ._version import __title__, __version__
+from ._response import APIResponse as APIResponse, AsyncAPIResponse as AsyncAPIResponse
+from ._constants import DEFAULT_TIMEOUT, DEFAULT_MAX_RETRIES, DEFAULT_CONNECTION_LIMITS
+from ._exceptions import (
+    APIError,
+    GroqError,
+    ConflictError,
+    NotFoundError,
+    APIStatusError,
+    RateLimitError,
+    APITimeoutError,
+    BadRequestError,
+    APIConnectionError,
+    AuthenticationError,
+    InternalServerError,
+    PermissionDeniedError,
+    UnprocessableEntityError,
+    APIResponseValidationError,
+)
+from ._base_client import DefaultHttpxClient, DefaultAioHttpClient, DefaultAsyncHttpxClient
+from ._utils._logs import setup_logging as _setup_logging
+
+__all__ = [
+    "types",
+    "__version__",
+    "__title__",
+    "NoneType",
+    "Transport",
+    "ProxiesTypes",
+    "NotGiven",
+    "NOT_GIVEN",
+    "Omit",
+    "GroqError",
+    "APIError",
+    "APIStatusError",
+    "APITimeoutError",
+    "APIConnectionError",
+    "APIResponseValidationError",
+    "BadRequestError",
+    "AuthenticationError",
+    "PermissionDeniedError",
+    "NotFoundError",
+    "ConflictError",
+    "UnprocessableEntityError",
+    "RateLimitError",
+    "InternalServerError",
+    "Timeout",
+    "RequestOptions",
+    "Client",
+    "AsyncClient",
+    "Stream",
+    "AsyncStream",
+    "Groq",
+    "AsyncGroq",
+    "file_from_path",
+    "BaseModel",
+    "DEFAULT_TIMEOUT",
+    "DEFAULT_MAX_RETRIES",
+    "DEFAULT_CONNECTION_LIMITS",
+    "DefaultHttpxClient",
+    "DefaultAsyncHttpxClient",
+    "DefaultAioHttpClient",
+]
+
+if not _t.TYPE_CHECKING:
+    from ._utils._resources_proxy import resources as resources
+
+_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.
+# groq._exceptions.NotFoundError -> groq.NotFoundError
+__locals = locals()
+for __name in __all__:
+    if not __name.startswith("__"):
+        try:
+            __locals[__name].__module__ = "groq"
+        except (TypeError, AttributeError):
+            # Some of our exported symbols are builtins which we can't set attributes for.
+            pass

venv/lib/python3.11/site-packages/groq/_client.py

@@ -0,0 +1,627 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+import os
+from typing import TYPE_CHECKING, Any, Union, Mapping
+from typing_extensions import Self, override
+
+import httpx
+
+from . import _exceptions
+from ._qs import Querystring
+from ._types import (
+    NOT_GIVEN,
+    Omit,
+    Timeout,
+    NotGiven,
+    Transport,
+    ProxiesTypes,
+    RequestOptions,
+)
+from ._utils import is_given, get_async_library
+from ._compat import cached_property
+from ._version import __version__
+from ._streaming import Stream as Stream, AsyncStream as AsyncStream
+from ._exceptions import GroqError, APIStatusError
+from ._base_client import (
+    DEFAULT_MAX_RETRIES,
+    SyncAPIClient,
+    AsyncAPIClient,
+)
+
+if TYPE_CHECKING:
+    from .resources import chat, audio, files, models, batches, embeddings
+    from .resources.files import Files, AsyncFiles
+    from .resources.models import Models, AsyncModels
+    from .resources.batches import Batches, AsyncBatches
+    from .resources.chat.chat import Chat, AsyncChat
+    from .resources.embeddings import Embeddings, AsyncEmbeddings
+    from .resources.audio.audio import Audio, AsyncAudio
+
+__all__ = ["Timeout", "Transport", "ProxiesTypes", "RequestOptions", "Groq", "AsyncGroq", "Client", "AsyncClient"]
+
+
+class Groq(SyncAPIClient):
+    # client options
+    api_key: str
+
+    def __init__(
+        self,
+        *,
+        api_key: str | None = None,
+        base_url: str | httpx.URL | None = None,
+        timeout: Union[float, Timeout, None, NotGiven] = NOT_GIVEN,
+        max_retries: int = DEFAULT_MAX_RETRIES,
+        default_headers: Mapping[str, str] | None = None,
+        default_query: Mapping[str, object] | None = None,
+        # Configure a custom httpx client.
+        # We provide a `DefaultHttpxClient` class that you can pass to retain the default values we use for `limits`, `timeout` & `follow_redirects`.
+        # See the [httpx documentation](https://www.python-httpx.org/api/#client) for more details.
+        http_client: httpx.Client | None = None,
+        # Enable or disable schema validation for data returned by the API.
+        # When enabled an error APIResponseValidationError is raised
+        # if the API responds with invalid data for the expected schema.
+        #
+        # This parameter may be removed or changed in the future.
+        # If you rely on this feature, please open a GitHub issue
+        # outlining your use-case to help us decide if it should be
+        # part of our public interface in the future.
+        _strict_response_validation: bool = False,
+    ) -> None:
+        """Construct a new synchronous Groq client instance.
+
+        This automatically infers the `api_key` argument from the `GROQ_API_KEY` environment variable if it is not provided.
+        """
+        if api_key is None:
+            api_key = os.environ.get("GROQ_API_KEY")
+        if api_key is None:
+            raise GroqError(
+                "The api_key client option must be set either by passing api_key to the client or by setting the GROQ_API_KEY environment variable"
+            )
+        self.api_key = api_key
+
+        if base_url is None:
+            base_url = os.environ.get("GROQ_BASE_URL")
+        if base_url is None:
+            base_url = f"https://api.groq.com"
+
+        super().__init__(
+            version=__version__,
+            base_url=base_url,
+            max_retries=max_retries,
+            timeout=timeout,
+            http_client=http_client,
+            custom_headers=default_headers,
+            custom_query=default_query,
+            _strict_response_validation=_strict_response_validation,
+        )
+
+    @cached_property
+    def chat(self) -> Chat:
+        from .resources.chat import Chat
+
+        return Chat(self)
+
+    @cached_property
+    def embeddings(self) -> Embeddings:
+        from .resources.embeddings import Embeddings
+
+        return Embeddings(self)
+
+    @cached_property
+    def audio(self) -> Audio:
+        from .resources.audio import Audio
+
+        return Audio(self)
+
+    @cached_property
+    def models(self) -> Models:
+        from .resources.models import Models
+
+        return Models(self)
+
+    @cached_property
+    def batches(self) -> Batches:
+        from .resources.batches import Batches
+
+        return Batches(self)
+
+    @cached_property
+    def files(self) -> Files:
+        from .resources.files import Files
+
+        return Files(self)
+
+    @cached_property
+    def with_raw_response(self) -> GroqWithRawResponse:
+        return GroqWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> GroqWithStreamedResponse:
+        return GroqWithStreamedResponse(self)
+
+    @property
+    @override
+    def qs(self) -> Querystring:
+        return Querystring(array_format="comma")
+
+    @property
+    @override
+    def auth_headers(self) -> dict[str, str]:
+        api_key = self.api_key
+        return {"Authorization": f"Bearer {api_key}"}
+
+    @property
+    @override
+    def default_headers(self) -> dict[str, str | Omit]:
+        return {
+            **super().default_headers,
+            "X-Stainless-Async": "false",
+            **self._custom_headers,
+        }
+
+    def copy(
+        self,
+        *,
+        api_key: str | None = None,
+        base_url: str | httpx.URL | None = None,
+        timeout: float | Timeout | None | NotGiven = NOT_GIVEN,
+        http_client: httpx.Client | None = None,
+        max_retries: int | NotGiven = NOT_GIVEN,
+        default_headers: Mapping[str, str] | None = None,
+        set_default_headers: Mapping[str, str] | None = None,
+        default_query: Mapping[str, object] | None = None,
+        set_default_query: Mapping[str, object] | None = None,
+        _extra_kwargs: Mapping[str, Any] = {},
+    ) -> Self:
+        """
+        Create a new client instance re-using the same options given to the current client with optional overriding.
+        """
+        if default_headers is not None and set_default_headers is not None:
+            raise ValueError("The `default_headers` and `set_default_headers` arguments are mutually exclusive")
+
+        if default_query is not None and set_default_query is not None:
+            raise ValueError("The `default_query` and `set_default_query` arguments are mutually exclusive")
+
+        headers = self._custom_headers
+        if default_headers is not None:
+            headers = {**headers, **default_headers}
+        elif set_default_headers is not None:
+            headers = set_default_headers
+
+        params = self._custom_query
+        if default_query is not None:
+            params = {**params, **default_query}
+        elif set_default_query is not None:
+            params = set_default_query
+
+        http_client = http_client or self._client
+        return self.__class__(
+            api_key=api_key or self.api_key,
+            base_url=base_url or self.base_url,
+            timeout=self.timeout if isinstance(timeout, NotGiven) else timeout,
+            http_client=http_client,
+            max_retries=max_retries if is_given(max_retries) else self.max_retries,
+            default_headers=headers,
+            default_query=params,
+            **_extra_kwargs,
+        )
+
+    # Alias for `copy` for nicer inline usage, e.g.
+    # client.with_options(timeout=10).foo.create(...)
+    with_options = copy
+
+    @override
+    def _make_status_error(
+        self,
+        err_msg: str,
+        *,
+        body: object,
+        response: httpx.Response,
+    ) -> APIStatusError:
+        if response.status_code == 400:
+            return _exceptions.BadRequestError(err_msg, response=response, body=body)
+
+        if response.status_code == 401:
+            return _exceptions.AuthenticationError(err_msg, response=response, body=body)
+
+        if response.status_code == 403:
+            return _exceptions.PermissionDeniedError(err_msg, response=response, body=body)
+
+        if response.status_code == 404:
+            return _exceptions.NotFoundError(err_msg, response=response, body=body)
+
+        if response.status_code == 409:
+            return _exceptions.ConflictError(err_msg, response=response, body=body)
+
+        if response.status_code == 422:
+            return _exceptions.UnprocessableEntityError(err_msg, response=response, body=body)
+
+        if response.status_code == 429:
+            return _exceptions.RateLimitError(err_msg, response=response, body=body)
+
+        if response.status_code >= 500:
+            return _exceptions.InternalServerError(err_msg, response=response, body=body)
+        return APIStatusError(err_msg, response=response, body=body)
+
+
+class AsyncGroq(AsyncAPIClient):
+    # client options
+    api_key: str
+
+    def __init__(
+        self,
+        *,
+        api_key: str | None = None,
+        base_url: str | httpx.URL | None = None,
+        timeout: Union[float, Timeout, None, NotGiven] = NOT_GIVEN,
+        max_retries: int = DEFAULT_MAX_RETRIES,
+        default_headers: Mapping[str, str] | None = None,
+        default_query: Mapping[str, object] | None = None,
+        # Configure a custom httpx client.
+        # We provide a `DefaultAsyncHttpxClient` class that you can pass to retain the default values we use for `limits`, `timeout` & `follow_redirects`.
+        # See the [httpx documentation](https://www.python-httpx.org/api/#asyncclient) for more details.
+        http_client: httpx.AsyncClient | None = None,
+        # Enable or disable schema validation for data returned by the API.
+        # When enabled an error APIResponseValidationError is raised
+        # if the API responds with invalid data for the expected schema.
+        #
+        # This parameter may be removed or changed in the future.
+        # If you rely on this feature, please open a GitHub issue
+        # outlining your use-case to help us decide if it should be
+        # part of our public interface in the future.
+        _strict_response_validation: bool = False,
+    ) -> None:
+        """Construct a new async AsyncGroq client instance.
+
+        This automatically infers the `api_key` argument from the `GROQ_API_KEY` environment variable if it is not provided.
+        """
+        if api_key is None:
+            api_key = os.environ.get("GROQ_API_KEY")
+        if api_key is None:
+            raise GroqError(
+                "The api_key client option must be set either by passing api_key to the client or by setting the GROQ_API_KEY environment variable"
+            )
+        self.api_key = api_key
+
+        if base_url is None:
+            base_url = os.environ.get("GROQ_BASE_URL")
+        if base_url is None:
+            base_url = f"https://api.groq.com"
+
+        super().__init__(
+            version=__version__,
+            base_url=base_url,
+            max_retries=max_retries,
+            timeout=timeout,
+            http_client=http_client,
+            custom_headers=default_headers,
+            custom_query=default_query,
+            _strict_response_validation=_strict_response_validation,
+        )
+
+    @cached_property
+    def chat(self) -> AsyncChat:
+        from .resources.chat import AsyncChat
+
+        return AsyncChat(self)
+
+    @cached_property
+    def embeddings(self) -> AsyncEmbeddings:
+        from .resources.embeddings import AsyncEmbeddings
+
+        return AsyncEmbeddings(self)
+
+    @cached_property
+    def audio(self) -> AsyncAudio:
+        from .resources.audio import AsyncAudio
+
+        return AsyncAudio(self)
+
+    @cached_property
+    def models(self) -> AsyncModels:
+        from .resources.models import AsyncModels
+
+        return AsyncModels(self)
+
+    @cached_property
+    def batches(self) -> AsyncBatches:
+        from .resources.batches import AsyncBatches
+
+        return AsyncBatches(self)
+
+    @cached_property
+    def files(self) -> AsyncFiles:
+        from .resources.files import AsyncFiles
+
+        return AsyncFiles(self)
+
+    @cached_property
+    def with_raw_response(self) -> AsyncGroqWithRawResponse:
+        return AsyncGroqWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AsyncGroqWithStreamedResponse:
+        return AsyncGroqWithStreamedResponse(self)
+
+    @property
+    @override
+    def qs(self) -> Querystring:
+        return Querystring(array_format="comma")
+
+    @property
+    @override
+    def auth_headers(self) -> dict[str, str]:
+        api_key = self.api_key
+        return {"Authorization": f"Bearer {api_key}"}
+
+    @property
+    @override
+    def default_headers(self) -> dict[str, str | Omit]:
+        return {
+            **super().default_headers,
+            "X-Stainless-Async": f"async:{get_async_library()}",
+            **self._custom_headers,
+        }
+
+    def copy(
+        self,
+        *,
+        api_key: str | None = None,
+        base_url: str | httpx.URL | None = None,
+        timeout: float | Timeout | None | NotGiven = NOT_GIVEN,
+        http_client: httpx.AsyncClient | None = None,
+        max_retries: int | NotGiven = NOT_GIVEN,
+        default_headers: Mapping[str, str] | None = None,
+        set_default_headers: Mapping[str, str] | None = None,
+        default_query: Mapping[str, object] | None = None,
+        set_default_query: Mapping[str, object] | None = None,
+        _extra_kwargs: Mapping[str, Any] = {},
+    ) -> Self:
+        """
+        Create a new client instance re-using the same options given to the current client with optional overriding.
+        """
+        if default_headers is not None and set_default_headers is not None:
+            raise ValueError("The `default_headers` and `set_default_headers` arguments are mutually exclusive")
+
+        if default_query is not None and set_default_query is not None:
+            raise ValueError("The `default_query` and `set_default_query` arguments are mutually exclusive")
+
+        headers = self._custom_headers
+        if default_headers is not None:
+            headers = {**headers, **default_headers}
+        elif set_default_headers is not None:
+            headers = set_default_headers
+
+        params = self._custom_query
+        if default_query is not None:
+            params = {**params, **default_query}
+        elif set_default_query is not None:
+            params = set_default_query
+
+        http_client = http_client or self._client
+        return self.__class__(
+            api_key=api_key or self.api_key,
+            base_url=base_url or self.base_url,
+            timeout=self.timeout if isinstance(timeout, NotGiven) else timeout,
+            http_client=http_client,
+            max_retries=max_retries if is_given(max_retries) else self.max_retries,
+            default_headers=headers,
+            default_query=params,
+            **_extra_kwargs,
+        )
+
+    # Alias for `copy` for nicer inline usage, e.g.
+    # client.with_options(timeout=10).foo.create(...)
+    with_options = copy
+
+    @override
+    def _make_status_error(
+        self,
+        err_msg: str,
+        *,
+        body: object,
+        response: httpx.Response,
+    ) -> APIStatusError:
+        if response.status_code == 400:
+            return _exceptions.BadRequestError(err_msg, response=response, body=body)
+
+        if response.status_code == 401:
+            return _exceptions.AuthenticationError(err_msg, response=response, body=body)
+
+        if response.status_code == 403:
+            return _exceptions.PermissionDeniedError(err_msg, response=response, body=body)
+
+        if response.status_code == 404:
+            return _exceptions.NotFoundError(err_msg, response=response, body=body)
+
+        if response.status_code == 409:
+            return _exceptions.ConflictError(err_msg, response=response, body=body)
+
+        if response.status_code == 422:
+            return _exceptions.UnprocessableEntityError(err_msg, response=response, body=body)
+
+        if response.status_code == 429:
+            return _exceptions.RateLimitError(err_msg, response=response, body=body)
+
+        if response.status_code >= 500:
+            return _exceptions.InternalServerError(err_msg, response=response, body=body)
+        return APIStatusError(err_msg, response=response, body=body)
+
+
+class GroqWithRawResponse:
+    _client: Groq
+
+    def __init__(self, client: Groq) -> None:
+        self._client = client
+
+    @cached_property
+    def chat(self) -> chat.ChatWithRawResponse:
+        from .resources.chat import ChatWithRawResponse
+
+        return ChatWithRawResponse(self._client.chat)
+
+    @cached_property
+    def embeddings(self) -> embeddings.EmbeddingsWithRawResponse:
+        from .resources.embeddings import EmbeddingsWithRawResponse
+
+        return EmbeddingsWithRawResponse(self._client.embeddings)
+
+    @cached_property
+    def audio(self) -> audio.AudioWithRawResponse:
+        from .resources.audio import AudioWithRawResponse
+
+        return AudioWithRawResponse(self._client.audio)
+
+    @cached_property
+    def models(self) -> models.ModelsWithRawResponse:
+        from .resources.models import ModelsWithRawResponse
+
+        return ModelsWithRawResponse(self._client.models)
+
+    @cached_property
+    def batches(self) -> batches.BatchesWithRawResponse:
+        from .resources.batches import BatchesWithRawResponse
+
+        return BatchesWithRawResponse(self._client.batches)
+
+    @cached_property
+    def files(self) -> files.FilesWithRawResponse:
+        from .resources.files import FilesWithRawResponse
+
+        return FilesWithRawResponse(self._client.files)
+
+
+class AsyncGroqWithRawResponse:
+    _client: AsyncGroq
+
+    def __init__(self, client: AsyncGroq) -> None:
+        self._client = client
+
+    @cached_property
+    def chat(self) -> chat.AsyncChatWithRawResponse:
+        from .resources.chat import AsyncChatWithRawResponse
+
+        return AsyncChatWithRawResponse(self._client.chat)
+
+    @cached_property
+    def embeddings(self) -> embeddings.AsyncEmbeddingsWithRawResponse:
+        from .resources.embeddings import AsyncEmbeddingsWithRawResponse
+
+        return AsyncEmbeddingsWithRawResponse(self._client.embeddings)
+
+    @cached_property
+    def audio(self) -> audio.AsyncAudioWithRawResponse:
+        from .resources.audio import AsyncAudioWithRawResponse
+
+        return AsyncAudioWithRawResponse(self._client.audio)
+
+    @cached_property
+    def models(self) -> models.AsyncModelsWithRawResponse:
+        from .resources.models import AsyncModelsWithRawResponse
+
+        return AsyncModelsWithRawResponse(self._client.models)
+
+    @cached_property
+    def batches(self) -> batches.AsyncBatchesWithRawResponse:
+        from .resources.batches import AsyncBatchesWithRawResponse
+
+        return AsyncBatchesWithRawResponse(self._client.batches)
+
+    @cached_property
+    def files(self) -> files.AsyncFilesWithRawResponse:
+        from .resources.files import AsyncFilesWithRawResponse
+
+        return AsyncFilesWithRawResponse(self._client.files)
+
+
+class GroqWithStreamedResponse:
+    _client: Groq
+
+    def __init__(self, client: Groq) -> None:
+        self._client = client
+
+    @cached_property
+    def chat(self) -> chat.ChatWithStreamingResponse:
+        from .resources.chat import ChatWithStreamingResponse
+
+        return ChatWithStreamingResponse(self._client.chat)
+
+    @cached_property
+    def embeddings(self) -> embeddings.EmbeddingsWithStreamingResponse:
+        from .resources.embeddings import EmbeddingsWithStreamingResponse
+
+        return EmbeddingsWithStreamingResponse(self._client.embeddings)
+
+    @cached_property
+    def audio(self) -> audio.AudioWithStreamingResponse:
+        from .resources.audio import AudioWithStreamingResponse
+
+        return AudioWithStreamingResponse(self._client.audio)
+
+    @cached_property
+    def models(self) -> models.ModelsWithStreamingResponse:
+        from .resources.models import ModelsWithStreamingResponse
+
+        return ModelsWithStreamingResponse(self._client.models)
+
+    @cached_property
+    def batches(self) -> batches.BatchesWithStreamingResponse:
+        from .resources.batches import BatchesWithStreamingResponse
+
+        return BatchesWithStreamingResponse(self._client.batches)
+
+    @cached_property
+    def files(self) -> files.FilesWithStreamingResponse:
+        from .resources.files import FilesWithStreamingResponse
+
+        return FilesWithStreamingResponse(self._client.files)
+
+
+class AsyncGroqWithStreamedResponse:
+    _client: AsyncGroq
+
+    def __init__(self, client: AsyncGroq) -> None:
+        self._client = client
+
+    @cached_property
+    def chat(self) -> chat.AsyncChatWithStreamingResponse:
+        from .resources.chat import AsyncChatWithStreamingResponse
+
+        return AsyncChatWithStreamingResponse(self._client.chat)
+
+    @cached_property
+    def embeddings(self) -> embeddings.AsyncEmbeddingsWithStreamingResponse:
+        from .resources.embeddings import AsyncEmbeddingsWithStreamingResponse
+
+        return AsyncEmbeddingsWithStreamingResponse(self._client.embeddings)
+
+    @cached_property
+    def audio(self) -> audio.AsyncAudioWithStreamingResponse:
+        from .resources.audio import AsyncAudioWithStreamingResponse
+
+        return AsyncAudioWithStreamingResponse(self._client.audio)
+
+    @cached_property
+    def models(self) -> models.AsyncModelsWithStreamingResponse:
+        from .resources.models import AsyncModelsWithStreamingResponse
+
+        return AsyncModelsWithStreamingResponse(self._client.models)
+
+    @cached_property
+    def batches(self) -> batches.AsyncBatchesWithStreamingResponse:
+        from .resources.batches import AsyncBatchesWithStreamingResponse
+
+        return AsyncBatchesWithStreamingResponse(self._client.batches)
+
+    @cached_property
+    def files(self) -> files.AsyncFilesWithStreamingResponse:
+        from .resources.files import AsyncFilesWithStreamingResponse
+
+        return AsyncFilesWithStreamingResponse(self._client.files)
+
+
+Client = Groq
+
+AsyncClient = AsyncGroq

venv/lib/python3.11/site-packages/groq/_compat.py

@@ -0,0 +1,219 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, Any, Union, Generic, TypeVar, Callable, cast, overload
+from datetime import date, datetime
+from typing_extensions import Self, Literal
+
+import pydantic
+from pydantic.fields import FieldInfo
+
+from ._types import IncEx, StrBytesIntFloat
+
+_T = TypeVar("_T")
+_ModelT = TypeVar("_ModelT", bound=pydantic.BaseModel)
+
+# --------------- Pydantic v2 compatibility ---------------
+
+# Pyright incorrectly reports some of our functions as overriding a method when they don't
+# pyright: reportIncompatibleMethodOverride=false
+
+PYDANTIC_V2 = pydantic.VERSION.startswith("2.")
+
+# v1 re-exports
+if TYPE_CHECKING:
+
+    def parse_date(value: date | StrBytesIntFloat) -> date:  # noqa: ARG001
+        ...
+
+    def parse_datetime(value: Union[datetime, StrBytesIntFloat]) -> datetime:  # noqa: ARG001
+        ...
+
+    def get_args(t: type[Any]) -> tuple[Any, ...]:  # noqa: ARG001
+        ...
+
+    def is_union(tp: type[Any] | None) -> bool:  # noqa: ARG001
+        ...
+
+    def get_origin(t: type[Any]) -> type[Any] | None:  # noqa: ARG001
+        ...
+
+    def is_literal_type(type_: type[Any]) -> bool:  # noqa: ARG001
+        ...
+
+    def is_typeddict(type_: type[Any]) -> bool:  # noqa: ARG001
+        ...
+
+else:
+    if PYDANTIC_V2:
+        from pydantic.v1.typing import (
+            get_args as get_args,
+            is_union as is_union,
+            get_origin as get_origin,
+            is_typeddict as is_typeddict,
+            is_literal_type as is_literal_type,
+        )
+        from pydantic.v1.datetime_parse import parse_date as parse_date, parse_datetime as parse_datetime
+    else:
+        from pydantic.typing import (
+            get_args as get_args,
+            is_union as is_union,
+            get_origin as get_origin,
+            is_typeddict as is_typeddict,
+            is_literal_type as is_literal_type,
+        )
+        from pydantic.datetime_parse import parse_date as parse_date, parse_datetime as parse_datetime
+
+
+# refactored config
+if TYPE_CHECKING:
+    from pydantic import ConfigDict as ConfigDict
+else:
+    if PYDANTIC_V2:
+        from pydantic import ConfigDict
+    else:
+        # TODO: provide an error message here?
+        ConfigDict = None
+
+
+# renamed methods / properties
+def parse_obj(model: type[_ModelT], value: object) -> _ModelT:
+    if PYDANTIC_V2:
+        return model.model_validate(value)
+    else:
+        return cast(_ModelT, model.parse_obj(value))  # pyright: ignore[reportDeprecated, reportUnnecessaryCast]
+
+
+def field_is_required(field: FieldInfo) -> bool:
+    if PYDANTIC_V2:
+        return field.is_required()
+    return field.required  # type: ignore
+
+
+def field_get_default(field: FieldInfo) -> Any:
+    value = field.get_default()
+    if PYDANTIC_V2:
+        from pydantic_core import PydanticUndefined
+
+        if value == PydanticUndefined:
+            return None
+        return value
+    return value
+
+
+def field_outer_type(field: FieldInfo) -> Any:
+    if PYDANTIC_V2:
+        return field.annotation
+    return field.outer_type_  # type: ignore
+
+
+def get_model_config(model: type[pydantic.BaseModel]) -> Any:
+    if PYDANTIC_V2:
+        return model.model_config
+    return model.__config__  # type: ignore
+
+
+def get_model_fields(model: type[pydantic.BaseModel]) -> dict[str, FieldInfo]:
+    if PYDANTIC_V2:
+        return model.model_fields
+    return model.__fields__  # type: ignore
+
+
+def model_copy(model: _ModelT, *, deep: bool = False) -> _ModelT:
+    if PYDANTIC_V2:
+        return model.model_copy(deep=deep)
+    return model.copy(deep=deep)  # type: ignore
+
+
+def model_json(model: pydantic.BaseModel, *, indent: int | None = None) -> str:
+    if PYDANTIC_V2:
+        return model.model_dump_json(indent=indent)
+    return model.json(indent=indent)  # type: ignore
+
+
+def model_dump(
+    model: pydantic.BaseModel,
+    *,
+    exclude: IncEx | None = None,
+    exclude_unset: bool = False,
+    exclude_defaults: bool = False,
+    warnings: bool = True,
+    mode: Literal["json", "python"] = "python",
+) -> dict[str, Any]:
+    if PYDANTIC_V2 or hasattr(model, "model_dump"):
+        return model.model_dump(
+            mode=mode,
+            exclude=exclude,
+            exclude_unset=exclude_unset,
+            exclude_defaults=exclude_defaults,
+            # warnings are not supported in Pydantic v1
+            warnings=warnings if PYDANTIC_V2 else True,
+        )
+    return cast(
+        "dict[str, Any]",
+        model.dict(  # pyright: ignore[reportDeprecated, reportUnnecessaryCast]
+            exclude=exclude,
+            exclude_unset=exclude_unset,
+            exclude_defaults=exclude_defaults,
+        ),
+    )
+
+
+def model_parse(model: type[_ModelT], data: Any) -> _ModelT:
+    if PYDANTIC_V2:
+        return model.model_validate(data)
+    return model.parse_obj(data)  # pyright: ignore[reportDeprecated]
+
+
+# generic models
+if TYPE_CHECKING:
+
+    class GenericModel(pydantic.BaseModel): ...
+
+else:
+    if PYDANTIC_V2:
+        # there no longer needs to be a distinction in v2 but
+        # we still have to create our own subclass to avoid
+        # inconsistent MRO ordering errors
+        class GenericModel(pydantic.BaseModel): ...
+
+    else:
+        import pydantic.generics
+
+        class GenericModel(pydantic.generics.GenericModel, pydantic.BaseModel): ...
+
+
+# cached properties
+if TYPE_CHECKING:
+    cached_property = property
+
+    # we define a separate type (copied from typeshed)
+    # that represents that `cached_property` is `set`able
+    # at runtime, which differs from `@property`.
+    #
+    # this is a separate type as editors likely special case
+    # `@property` and we don't want to cause issues just to have
+    # more helpful internal types.
+
+    class typed_cached_property(Generic[_T]):
+        func: Callable[[Any], _T]
+        attrname: str | None
+
+        def __init__(self, func: Callable[[Any], _T]) -> None: ...
+
+        @overload
+        def __get__(self, instance: None, owner: type[Any] | None = None) -> Self: ...
+
+        @overload
+        def __get__(self, instance: object, owner: type[Any] | None = None) -> _T: ...
+
+        def __get__(self, instance: object, owner: type[Any] | None = None) -> _T | Self:
+            raise NotImplementedError()
+
+        def __set_name__(self, owner: type[Any], name: str) -> None: ...
+
+        # __set__ is not defined at runtime, but @cached_property is designed to be settable
+        def __set__(self, instance: object, value: _T) -> None: ...
+else:
+    from functools import cached_property as cached_property
+
+    typed_cached_property = cached_property

venv/lib/python3.11/site-packages/groq/_constants.py

@@ -0,0 +1,14 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+import httpx
+
+RAW_RESPONSE_HEADER = "X-Stainless-Raw-Response"
+OVERRIDE_CAST_TO_HEADER = "____stainless_override_cast_to"
+
+# default timeout is 1 minute
+DEFAULT_TIMEOUT = httpx.Timeout(timeout=60, connect=5.0)
+DEFAULT_MAX_RETRIES = 2
+DEFAULT_CONNECTION_LIMITS = httpx.Limits(max_connections=100, max_keepalive_connections=20)
+
+INITIAL_RETRY_DELAY = 0.5
+MAX_RETRY_DELAY = 8.0

venv/lib/python3.11/site-packages/groq/_exceptions.py

@@ -0,0 +1,108 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing_extensions import Literal
+
+import httpx
+
+__all__ = [
+    "BadRequestError",
+    "AuthenticationError",
+    "PermissionDeniedError",
+    "NotFoundError",
+    "ConflictError",
+    "UnprocessableEntityError",
+    "RateLimitError",
+    "InternalServerError",
+]
+
+
+class GroqError(Exception):
+    pass
+
+
+class APIError(GroqError):
+    message: str
+    request: httpx.Request
+
+    body: object | None
+    """The API response body.
+
+    If the API responded with a valid JSON structure then this property will be the
+    decoded result.
+
+    If it isn't a valid JSON structure then this will be the raw response.
+
+    If there was no response associated with this error then it will be `None`.
+    """
+
+    def __init__(self, message: str, request: httpx.Request, *, body: object | None) -> None:  # noqa: ARG002
+        super().__init__(message)
+        self.request = request
+        self.message = message
+        self.body = body
+
+
+class APIResponseValidationError(APIError):
+    response: httpx.Response
+    status_code: int
+
+    def __init__(self, response: httpx.Response, body: object | None, *, message: str | None = None) -> None:
+        super().__init__(message or "Data returned by API invalid for expected schema.", response.request, body=body)
+        self.response = response
+        self.status_code = response.status_code
+
+
+class APIStatusError(APIError):
+    """Raised when an API response has a status code of 4xx or 5xx."""
+
+    response: httpx.Response
+    status_code: int
+
+    def __init__(self, message: str, *, response: httpx.Response, body: object | None) -> None:
+        super().__init__(message, response.request, body=body)
+        self.response = response
+        self.status_code = response.status_code
+
+
+class APIConnectionError(APIError):
+    def __init__(self, *, message: str = "Connection error.", request: httpx.Request) -> None:
+        super().__init__(message, request, body=None)
+
+
+class APITimeoutError(APIConnectionError):
+    def __init__(self, request: httpx.Request) -> None:
+        super().__init__(message="Request timed out.", request=request)
+
+
+class BadRequestError(APIStatusError):
+    status_code: Literal[400] = 400  # pyright: ignore[reportIncompatibleVariableOverride]
+
+
+class AuthenticationError(APIStatusError):
+    status_code: Literal[401] = 401  # pyright: ignore[reportIncompatibleVariableOverride]
+
+
+class PermissionDeniedError(APIStatusError):
+    status_code: Literal[403] = 403  # pyright: ignore[reportIncompatibleVariableOverride]
+
+
+class NotFoundError(APIStatusError):
+    status_code: Literal[404] = 404  # pyright: ignore[reportIncompatibleVariableOverride]
+
+
+class ConflictError(APIStatusError):
+    status_code: Literal[409] = 409  # pyright: ignore[reportIncompatibleVariableOverride]
+
+
+class UnprocessableEntityError(APIStatusError):
+    status_code: Literal[422] = 422  # pyright: ignore[reportIncompatibleVariableOverride]
+
+
+class RateLimitError(APIStatusError):
+    status_code: Literal[429] = 429  # pyright: ignore[reportIncompatibleVariableOverride]
+
+
+class InternalServerError(APIStatusError):
+    pass

venv/lib/python3.11/site-packages/groq/_files.py

@@ -0,0 +1,123 @@
+from __future__ import annotations
+
+import io
+import os
+import pathlib
+from typing import overload
+from typing_extensions import TypeGuard
+
+import anyio
+
+from ._types import (
+    FileTypes,
+    FileContent,
+    RequestFiles,
+    HttpxFileTypes,
+    Base64FileInput,
+    HttpxFileContent,
+    HttpxRequestFiles,
+)
+from ._utils import is_tuple_t, is_mapping_t, is_sequence_t
+
+
+def is_base64_file_input(obj: object) -> TypeGuard[Base64FileInput]:
+    return isinstance(obj, io.IOBase) or isinstance(obj, os.PathLike)
+
+
+def is_file_content(obj: object) -> TypeGuard[FileContent]:
+    return (
+        isinstance(obj, bytes) or isinstance(obj, tuple) or isinstance(obj, io.IOBase) or isinstance(obj, os.PathLike)
+    )
+
+
+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. See https://github.com/groq/groq-python/tree/main#file-uploads"
+        ) from None
+
+
+@overload
+def to_httpx_files(files: None) -> None: ...
+
+
+@overload
+def to_httpx_files(files: RequestFiles) -> HttpxRequestFiles: ...
+
+
+def to_httpx_files(files: RequestFiles | None) -> HttpxRequestFiles | None:
+    if files is None:
+        return None
+
+    if is_mapping_t(files):
+        files = {key: _transform_file(file) for key, file in files.items()}
+    elif is_sequence_t(files):
+        files = [(key, _transform_file(file)) for key, file in files]
+    else:
+        raise TypeError(f"Unexpected file type input {type(files)}, expected mapping or sequence")
+
+    return files
+
+
+def _transform_file(file: FileTypes) -> HttpxFileTypes:
+    if is_file_content(file):
+        if isinstance(file, os.PathLike):
+            path = pathlib.Path(file)
+            return (path.name, path.read_bytes())
+
+        return file
+
+    if is_tuple_t(file):
+        return (file[0], _read_file_content(file[1]), *file[2:])
+
+    raise TypeError(f"Expected file types input to be a FileContent type or to be a tuple")
+
+
+def _read_file_content(file: FileContent) -> HttpxFileContent:
+    if isinstance(file, os.PathLike):
+        return pathlib.Path(file).read_bytes()
+    return file
+
+
+@overload
+async def async_to_httpx_files(files: None) -> None: ...
+
+
+@overload
+async def async_to_httpx_files(files: RequestFiles) -> HttpxRequestFiles: ...
+
+
+async def async_to_httpx_files(files: RequestFiles | None) -> HttpxRequestFiles | None:
+    if files is None:
+        return None
+
+    if is_mapping_t(files):
+        files = {key: await _async_transform_file(file) for key, file in files.items()}
+    elif is_sequence_t(files):
+        files = [(key, await _async_transform_file(file)) for key, file in files]
+    else:
+        raise TypeError("Unexpected file type input {type(files)}, expected mapping or sequence")
+
+    return files
+
+
+async def _async_transform_file(file: FileTypes) -> HttpxFileTypes:
+    if is_file_content(file):
+        if isinstance(file, os.PathLike):
+            path = anyio.Path(file)
+            return (path.name, await path.read_bytes())
+
+        return file
+
+    if is_tuple_t(file):
+        return (file[0], await _async_read_file_content(file[1]), *file[2:])
+
+    raise TypeError(f"Expected file types input to be a FileContent type or to be a tuple")
+
+
+async def _async_read_file_content(file: FileContent) -> HttpxFileContent:
+    if isinstance(file, os.PathLike):
+        return await anyio.Path(file).read_bytes()
+
+    return file

venv/lib/python3.11/site-packages/groq/_models.py

@@ -0,0 +1,808 @@
+from __future__ import annotations
+
+import os
+import inspect
+from typing import TYPE_CHECKING, Any, Type, Union, Generic, TypeVar, Callable, Optional, cast
+from datetime import date, datetime
+from typing_extensions import (
+    List,
+    Unpack,
+    Literal,
+    ClassVar,
+    Protocol,
+    Required,
+    ParamSpec,
+    TypedDict,
+    TypeGuard,
+    final,
+    override,
+    runtime_checkable,
+)
+
+import pydantic
+from pydantic.fields import FieldInfo
+
+from ._types import (
+    Body,
+    IncEx,
+    Query,
+    ModelT,
+    Headers,
+    Timeout,
+    NotGiven,
+    AnyMapping,
+    HttpxRequestFiles,
+)
+from ._utils import (
+    PropertyInfo,
+    is_list,
+    is_given,
+    json_safe,
+    lru_cache,
+    is_mapping,
+    parse_date,
+    coerce_boolean,
+    parse_datetime,
+    strip_not_given,
+    extract_type_arg,
+    is_annotated_type,
+    is_type_alias_type,
+    strip_annotated_type,
+)
+from ._compat import (
+    PYDANTIC_V2,
+    ConfigDict,
+    GenericModel as BaseGenericModel,
+    get_args,
+    is_union,
+    parse_obj,
+    get_origin,
+    is_literal_type,
+    get_model_config,
+    get_model_fields,
+    field_get_default,
+)
+from ._constants import RAW_RESPONSE_HEADER
+
+if TYPE_CHECKING:
+    from pydantic_core.core_schema import ModelField, ModelSchema, LiteralSchema, ModelFieldsSchema
+
+__all__ = ["BaseModel", "GenericModel"]
+
+_T = TypeVar("_T")
+_BaseModelT = TypeVar("_BaseModelT", bound="BaseModel")
+
+P = ParamSpec("P")
+
+
+@runtime_checkable
+class _ConfigProtocol(Protocol):
+    allow_population_by_field_name: bool
+
+
+class BaseModel(pydantic.BaseModel):
+    if PYDANTIC_V2:
+        model_config: ClassVar[ConfigDict] = ConfigDict(
+            extra="allow", defer_build=coerce_boolean(os.environ.get("DEFER_PYDANTIC_BUILD", "true"))
+        )
+    else:
+
+        @property
+        @override
+        def model_fields_set(self) -> set[str]:
+            # a forwards-compat shim for pydantic v2
+            return self.__fields_set__  # type: ignore
+
+        class Config(pydantic.BaseConfig):  # pyright: ignore[reportDeprecated]
+            extra: Any = pydantic.Extra.allow  # type: ignore
+
+    def to_dict(
+        self,
+        *,
+        mode: Literal["json", "python"] = "python",
+        use_api_names: bool = True,
+        exclude_unset: bool = True,
+        exclude_defaults: bool = False,
+        exclude_none: bool = False,
+        warnings: bool = True,
+    ) -> dict[str, object]:
+        """Recursively generate a dictionary representation of the model, optionally specifying which fields to include or exclude.
+
+        By default, fields that were not set by the API will not be included,
+        and keys will match the API response, *not* the property names from the model.
+
+        For example, if the API responds with `"fooBar": true` but we've defined a `foo_bar: bool` property,
+        the output will use the `"fooBar"` key (unless `use_api_names=False` is passed).
+
+        Args:
+            mode:
+                If mode is 'json', the dictionary will only contain JSON serializable types. e.g. `datetime` will be turned into a string, `"2024-3-22T18:11:19.117000Z"`.
+                If mode is 'python', the dictionary may contain any Python objects. e.g. `datetime(2024, 3, 22)`
+
+            use_api_names: Whether to use the key that the API responded with or the property name. Defaults to `True`.
+            exclude_unset: Whether to exclude fields that have not been explicitly set.
+            exclude_defaults: Whether to exclude fields that are set to their default value from the output.
+            exclude_none: Whether to exclude fields that have a value of `None` from the output.
+            warnings: Whether to log warnings when invalid fields are encountered. This is only supported in Pydantic v2.
+        """
+        return self.model_dump(
+            mode=mode,
+            by_alias=use_api_names,
+            exclude_unset=exclude_unset,
+            exclude_defaults=exclude_defaults,
+            exclude_none=exclude_none,
+            warnings=warnings,
+        )
+
+    def to_json(
+        self,
+        *,
+        indent: int | None = 2,
+        use_api_names: bool = True,
+        exclude_unset: bool = True,
+        exclude_defaults: bool = False,
+        exclude_none: bool = False,
+        warnings: bool = True,
+    ) -> str:
+        """Generates a JSON string representing this model as it would be received from or sent to the API (but with indentation).
+
+        By default, fields that were not set by the API will not be included,
+        and keys will match the API response, *not* the property names from the model.
+
+        For example, if the API responds with `"fooBar": true` but we've defined a `foo_bar: bool` property,
+        the output will use the `"fooBar"` key (unless `use_api_names=False` is passed).
+
+        Args:
+            indent: Indentation to use in the JSON output. If `None` is passed, the output will be compact. Defaults to `2`
+            use_api_names: Whether to use the key that the API responded with or the property name. Defaults to `True`.
+            exclude_unset: Whether to exclude fields that have not been explicitly set.
+            exclude_defaults: Whether to exclude fields that have the default value.
+            exclude_none: Whether to exclude fields that have a value of `None`.
+            warnings: Whether to show any warnings that occurred during serialization. This is only supported in Pydantic v2.
+        """
+        return self.model_dump_json(
+            indent=indent,
+            by_alias=use_api_names,
+            exclude_unset=exclude_unset,
+            exclude_defaults=exclude_defaults,
+            exclude_none=exclude_none,
+            warnings=warnings,
+        )
+
+    @override
+    def __str__(self) -> str:
+        # mypy complains about an invalid self arg
+        return f"{self.__repr_name__()}({self.__repr_str__(', ')})"  # type: ignore[misc]
+
+    # Override the 'construct' method in a way that supports recursive parsing without validation.
+    # Based on https://github.com/samuelcolvin/pydantic/issues/1168#issuecomment-817742836.
+    @classmethod
+    @override
+    def construct(  # pyright: ignore[reportIncompatibleMethodOverride]
+        __cls: Type[ModelT],
+        _fields_set: set[str] | None = None,
+        **values: object,
+    ) -> ModelT:
+        m = __cls.__new__(__cls)
+        fields_values: dict[str, object] = {}
+
+        config = get_model_config(__cls)
+        populate_by_name = (
+            config.allow_population_by_field_name
+            if isinstance(config, _ConfigProtocol)
+            else config.get("populate_by_name")
+        )
+
+        if _fields_set is None:
+            _fields_set = set()
+
+        model_fields = get_model_fields(__cls)
+        for name, field in model_fields.items():
+            key = field.alias
+            if key is None or (key not in values and populate_by_name):
+                key = name
+
+            if key in values:
+                fields_values[name] = _construct_field(value=values[key], field=field, key=key)
+                _fields_set.add(name)
+            else:
+                fields_values[name] = field_get_default(field)
+
+        _extra = {}
+        for key, value in values.items():
+            if key not in model_fields:
+                if PYDANTIC_V2:
+                    _extra[key] = value
+                else:
+                    _fields_set.add(key)
+                    fields_values[key] = value
+
+        object.__setattr__(m, "__dict__", fields_values)
+
+        if PYDANTIC_V2:
+            # these properties are copied from Pydantic's `model_construct()` method
+            object.__setattr__(m, "__pydantic_private__", None)
+            object.__setattr__(m, "__pydantic_extra__", _extra)
+            object.__setattr__(m, "__pydantic_fields_set__", _fields_set)
+        else:
+            # init_private_attributes() does not exist in v2
+            m._init_private_attributes()  # type: ignore
+
+            # copied from Pydantic v1's `construct()` method
+            object.__setattr__(m, "__fields_set__", _fields_set)
+
+        return m
+
+    if not TYPE_CHECKING:
+        # type checkers incorrectly complain about this assignment
+        # because the type signatures are technically different
+        # although not in practice
+        model_construct = construct
+
+    if not PYDANTIC_V2:
+        # we define aliases for some of the new pydantic v2 methods so
+        # that we can just document these methods without having to specify
+        # a specific pydantic version as some users may not know which
+        # pydantic version they are currently using
+
+        @override
+        def model_dump(
+            self,
+            *,
+            mode: Literal["json", "python"] | str = "python",
+            include: IncEx | None = None,
+            exclude: IncEx | None = None,
+            by_alias: bool = False,
+            exclude_unset: bool = False,
+            exclude_defaults: bool = False,
+            exclude_none: bool = False,
+            round_trip: bool = False,
+            warnings: bool | Literal["none", "warn", "error"] = True,
+            context: dict[str, Any] | None = None,
+            serialize_as_any: bool = False,
+        ) -> dict[str, Any]:
+            """Usage docs: https://docs.pydantic.dev/2.4/concepts/serialization/#modelmodel_dump
+
+            Generate a dictionary representation of the model, optionally specifying which fields to include or exclude.
+
+            Args:
+                mode: The mode in which `to_python` should run.
+                    If mode is 'json', the dictionary will only contain JSON serializable types.
+                    If mode is 'python', the dictionary may contain any Python objects.
+                include: A list of fields to include in the output.
+                exclude: A list of fields to exclude from the output.
+                by_alias: Whether to use the field's alias in the dictionary key if defined.
+                exclude_unset: Whether to exclude fields that are unset or None from the output.
+                exclude_defaults: Whether to exclude fields that are set to their default value from the output.
+                exclude_none: Whether to exclude fields that have a value of `None` from the output.
+                round_trip: Whether to enable serialization and deserialization round-trip support.
+                warnings: Whether to log warnings when invalid fields are encountered.
+
+            Returns:
+                A dictionary representation of the model.
+            """
+            if mode not in {"json", "python"}:
+                raise ValueError("mode must be either 'json' or 'python'")
+            if round_trip != False:
+                raise ValueError("round_trip is only supported in Pydantic v2")
+            if warnings != True:
+                raise ValueError("warnings is only supported in Pydantic v2")
+            if context is not None:
+                raise ValueError("context is only supported in Pydantic v2")
+            if serialize_as_any != False:
+                raise ValueError("serialize_as_any is only supported in Pydantic v2")
+            dumped = super().dict(  # pyright: ignore[reportDeprecated]
+                include=include,
+                exclude=exclude,
+                by_alias=by_alias,
+                exclude_unset=exclude_unset,
+                exclude_defaults=exclude_defaults,
+                exclude_none=exclude_none,
+            )
+
+            return cast(dict[str, Any], json_safe(dumped)) if mode == "json" else dumped
+
+        @override
+        def model_dump_json(
+            self,
+            *,
+            indent: int | None = None,
+            include: IncEx | None = None,
+            exclude: IncEx | None = None,
+            by_alias: bool = False,
+            exclude_unset: bool = False,
+            exclude_defaults: bool = False,
+            exclude_none: bool = False,
+            round_trip: bool = False,
+            warnings: bool | Literal["none", "warn", "error"] = True,
+            context: dict[str, Any] | None = None,
+            serialize_as_any: bool = False,
+        ) -> str:
+            """Usage docs: https://docs.pydantic.dev/2.4/concepts/serialization/#modelmodel_dump_json
+
+            Generates a JSON representation of the model using Pydantic's `to_json` method.
+
+            Args:
+                indent: Indentation to use in the JSON output. If None is passed, the output will be compact.
+                include: Field(s) to include in the JSON output. Can take either a string or set of strings.
+                exclude: Field(s) to exclude from the JSON output. Can take either a string or set of strings.
+                by_alias: Whether to serialize using field aliases.
+                exclude_unset: Whether to exclude fields that have not been explicitly set.
+                exclude_defaults: Whether to exclude fields that have the default value.
+                exclude_none: Whether to exclude fields that have a value of `None`.
+                round_trip: Whether to use serialization/deserialization between JSON and class instance.
+                warnings: Whether to show any warnings that occurred during serialization.
+
+            Returns:
+                A JSON string representation of the model.
+            """
+            if round_trip != False:
+                raise ValueError("round_trip is only supported in Pydantic v2")
+            if warnings != True:
+                raise ValueError("warnings is only supported in Pydantic v2")
+            if context is not None:
+                raise ValueError("context is only supported in Pydantic v2")
+            if serialize_as_any != False:
+                raise ValueError("serialize_as_any is only supported in Pydantic v2")
+            return super().json(  # type: ignore[reportDeprecated]
+                indent=indent,
+                include=include,
+                exclude=exclude,
+                by_alias=by_alias,
+                exclude_unset=exclude_unset,
+                exclude_defaults=exclude_defaults,
+                exclude_none=exclude_none,
+            )
+
+
+def _construct_field(value: object, field: FieldInfo, key: str) -> object:
+    if value is None:
+        return field_get_default(field)
+
+    if PYDANTIC_V2:
+        type_ = field.annotation
+    else:
+        type_ = cast(type, field.outer_type_)  # type: ignore
+
+    if type_ is None:
+        raise RuntimeError(f"Unexpected field type is None for {key}")
+
+    return construct_type(value=value, type_=type_, metadata=getattr(field, "metadata", None))
+
+
+def is_basemodel(type_: type) -> bool:
+    """Returns whether or not the given type is either a `BaseModel` or a union of `BaseModel`"""
+    if is_union(type_):
+        for variant in get_args(type_):
+            if is_basemodel(variant):
+                return True
+
+        return False
+
+    return is_basemodel_type(type_)
+
+
+def is_basemodel_type(type_: type) -> TypeGuard[type[BaseModel] | type[GenericModel]]:
+    origin = get_origin(type_) or type_
+    if not inspect.isclass(origin):
+        return False
+    return issubclass(origin, BaseModel) or issubclass(origin, GenericModel)
+
+
+def build(
+    base_model_cls: Callable[P, _BaseModelT],
+    *args: P.args,
+    **kwargs: P.kwargs,
+) -> _BaseModelT:
+    """Construct a BaseModel class without validation.
+
+    This is useful for cases where you need to instantiate a `BaseModel`
+    from an API response as this provides type-safe params which isn't supported
+    by helpers like `construct_type()`.
+
+    ```py
+    build(MyModel, my_field_a="foo", my_field_b=123)
+    ```
+    """
+    if args:
+        raise TypeError(
+            "Received positional arguments which are not supported; Keyword arguments must be used instead",
+        )
+
+    return cast(_BaseModelT, construct_type(type_=base_model_cls, value=kwargs))
+
+
+def construct_type_unchecked(*, value: object, type_: type[_T]) -> _T:
+    """Loose coercion to the expected type with construction of nested values.
+
+    Note: the returned value from this function is not guaranteed to match the
+    given type.
+    """
+    return cast(_T, construct_type(value=value, type_=type_))
+
+
+def construct_type(*, value: object, type_: object, metadata: Optional[List[Any]] = None) -> object:
+    """Loose coercion to the expected type with construction of nested values.
+
+    If the given value does not match the expected type then it is returned as-is.
+    """
+
+    # store a reference to the original type we were given before we extract any inner
+    # types so that we can properly resolve forward references in `TypeAliasType` annotations
+    original_type = None
+
+    # we allow `object` as the input type because otherwise, passing things like
+    # `Literal['value']` will be reported as a type error by type checkers
+    type_ = cast("type[object]", type_)
+    if is_type_alias_type(type_):
+        original_type = type_  # type: ignore[unreachable]
+        type_ = type_.__value__  # type: ignore[unreachable]
+
+    # unwrap `Annotated[T, ...]` -> `T`
+    if metadata is not None:
+        meta: tuple[Any, ...] = tuple(metadata)
+    elif is_annotated_type(type_):
+        meta = get_args(type_)[1:]
+        type_ = extract_type_arg(type_, 0)
+    else:
+        meta = tuple()
+
+    # we need to use the origin class for any types that are subscripted generics
+    # e.g. Dict[str, object]
+    origin = get_origin(type_) or type_
+    args = get_args(type_)
+
+    if is_union(origin):
+        try:
+            return validate_type(type_=cast("type[object]", original_type or type_), value=value)
+        except Exception:
+            pass
+
+        # if the type is a discriminated union then we want to construct the right variant
+        # in the union, even if the data doesn't match exactly, otherwise we'd break code
+        # that relies on the constructed class types, e.g.
+        #
+        # class FooType:
+        #   kind: Literal['foo']
+        #   value: str
+        #
+        # class BarType:
+        #   kind: Literal['bar']
+        #   value: int
+        #
+        # without this block, if the data we get is something like `{'kind': 'bar', 'value': 'foo'}` then
+        # we'd end up constructing `FooType` when it should be `BarType`.
+        discriminator = _build_discriminated_union_meta(union=type_, meta_annotations=meta)
+        if discriminator and is_mapping(value):
+            variant_value = value.get(discriminator.field_alias_from or discriminator.field_name)
+            if variant_value and isinstance(variant_value, str):
+                variant_type = discriminator.mapping.get(variant_value)
+                if variant_type:
+                    return construct_type(type_=variant_type, value=value)
+
+        # if the data is not valid, use the first variant that doesn't fail while deserializing
+        for variant in args:
+            try:
+                return construct_type(value=value, type_=variant)
+            except Exception:
+                continue
+
+        raise RuntimeError(f"Could not convert data into a valid instance of {type_}")
+
+    if origin == dict:
+        if not is_mapping(value):
+            return value
+
+        _, items_type = get_args(type_)  # Dict[_, items_type]
+        return {key: construct_type(value=item, type_=items_type) for key, item in value.items()}
+
+    if (
+        not is_literal_type(type_)
+        and inspect.isclass(origin)
+        and (issubclass(origin, BaseModel) or issubclass(origin, GenericModel))
+    ):
+        if is_list(value):
+            return [cast(Any, type_).construct(**entry) if is_mapping(entry) else entry for entry in value]
+
+        if is_mapping(value):
+            if issubclass(type_, BaseModel):
+                return type_.construct(**value)  # type: ignore[arg-type]
+
+            return cast(Any, type_).construct(**value)
+
+    if origin == list:
+        if not is_list(value):
+            return value
+
+        inner_type = args[0]  # List[inner_type]
+        return [construct_type(value=entry, type_=inner_type) for entry in value]
+
+    if origin == float:
+        if isinstance(value, int):
+            coerced = float(value)
+            if coerced != value:
+                return value
+            return coerced
+
+        return value
+
+    if type_ == datetime:
+        try:
+            return parse_datetime(value)  # type: ignore
+        except Exception:
+            return value
+
+    if type_ == date:
+        try:
+            return parse_date(value)  # type: ignore
+        except Exception:
+            return value
+
+    return value
+
+
+@runtime_checkable
+class CachedDiscriminatorType(Protocol):
+    __discriminator__: DiscriminatorDetails
+
+
+class DiscriminatorDetails:
+    field_name: str
+    """The name of the discriminator field in the variant class, e.g.
+
+    ```py
+    class Foo(BaseModel):
+        type: Literal['foo']
+    ```
+
+    Will result in field_name='type'
+    """
+
+    field_alias_from: str | None
+    """The name of the discriminator field in the API response, e.g.
+
+    ```py
+    class Foo(BaseModel):
+        type: Literal['foo'] = Field(alias='type_from_api')
+    ```
+
+    Will result in field_alias_from='type_from_api'
+    """
+
+    mapping: dict[str, type]
+    """Mapping of discriminator value to variant type, e.g.
+
+    {'foo': FooVariant, 'bar': BarVariant}
+    """
+
+    def __init__(
+        self,
+        *,
+        mapping: dict[str, type],
+        discriminator_field: str,
+        discriminator_alias: str | None,
+    ) -> None:
+        self.mapping = mapping
+        self.field_name = discriminator_field
+        self.field_alias_from = discriminator_alias
+
+
+def _build_discriminated_union_meta(*, union: type, meta_annotations: tuple[Any, ...]) -> DiscriminatorDetails | None:
+    if isinstance(union, CachedDiscriminatorType):
+        return union.__discriminator__
+
+    discriminator_field_name: str | None = None
+
+    for annotation in meta_annotations:
+        if isinstance(annotation, PropertyInfo) and annotation.discriminator is not None:
+            discriminator_field_name = annotation.discriminator
+            break
+
+    if not discriminator_field_name:
+        return None
+
+    mapping: dict[str, type] = {}
+    discriminator_alias: str | None = None
+
+    for variant in get_args(union):
+        variant = strip_annotated_type(variant)
+        if is_basemodel_type(variant):
+            if PYDANTIC_V2:
+                field = _extract_field_schema_pv2(variant, discriminator_field_name)
+                if not field:
+                    continue
+
+                # Note: if one variant defines an alias then they all should
+                discriminator_alias = field.get("serialization_alias")
+
+                field_schema = field["schema"]
+
+                if field_schema["type"] == "literal":
+                    for entry in cast("LiteralSchema", field_schema)["expected"]:
+                        if isinstance(entry, str):
+                            mapping[entry] = variant
+            else:
+                field_info = cast("dict[str, FieldInfo]", variant.__fields__).get(discriminator_field_name)  # pyright: ignore[reportDeprecated, reportUnnecessaryCast]
+                if not field_info:
+                    continue
+
+                # Note: if one variant defines an alias then they all should
+                discriminator_alias = field_info.alias
+
+                if (annotation := getattr(field_info, "annotation", None)) and is_literal_type(annotation):
+                    for entry in get_args(annotation):
+                        if isinstance(entry, str):
+                            mapping[entry] = variant
+
+    if not mapping:
+        return None
+
+    details = DiscriminatorDetails(
+        mapping=mapping,
+        discriminator_field=discriminator_field_name,
+        discriminator_alias=discriminator_alias,
+    )
+    cast(CachedDiscriminatorType, union).__discriminator__ = details
+    return details
+
+
+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
+
+    return cast("ModelField", field)  # pyright: ignore[reportUnnecessaryCast]
+
+
+def validate_type(*, type_: type[_T], value: object) -> _T:
+    """Strict validation that the given value matches the expected type"""
+    if inspect.isclass(type_) and issubclass(type_, pydantic.BaseModel):
+        return cast(_T, parse_obj(type_, value))
+
+    return cast(_T, _validate_non_model_type(type_=type_, value=value))
+
+
+def set_pydantic_config(typ: Any, config: pydantic.ConfigDict) -> None:
+    """Add a pydantic config for the given type.
+
+    Note: this is a no-op on Pydantic v1.
+    """
+    setattr(typ, "__pydantic_config__", config)  # noqa: B010
+
+
+# our use of subclassing here causes weirdness for type checkers,
+# so we just pretend that we don't subclass
+if TYPE_CHECKING:
+    GenericModel = BaseModel
+else:
+
+    class GenericModel(BaseGenericModel, BaseModel):
+        pass
+
+
+if PYDANTIC_V2:
+    from pydantic import TypeAdapter as _TypeAdapter
+
+    _CachedTypeAdapter = cast("TypeAdapter[object]", lru_cache(maxsize=None)(_TypeAdapter))
+
+    if TYPE_CHECKING:
+        from pydantic import TypeAdapter
+    else:
+        TypeAdapter = _CachedTypeAdapter
+
+    def _validate_non_model_type(*, type_: type[_T], value: object) -> _T:
+        return TypeAdapter(type_).validate_python(value)
+
+elif not TYPE_CHECKING:  # TODO: condition is weird
+
+    class RootModel(GenericModel, Generic[_T]):
+        """Used as a placeholder to easily convert runtime types to a Pydantic format
+        to provide validation.
+
+        For example:
+        ```py
+        validated = RootModel[int](__root__="5").__root__
+        # validated: 5
+        ```
+        """
+
+        __root__: _T
+
+    def _validate_non_model_type(*, type_: type[_T], value: object) -> _T:
+        model = _create_pydantic_model(type_).validate(value)
+        return cast(_T, model.__root__)
+
+    def _create_pydantic_model(type_: _T) -> Type[RootModel[_T]]:
+        return RootModel[type_]  # type: ignore
+
+
+class FinalRequestOptionsInput(TypedDict, total=False):
+    method: Required[str]
+    url: Required[str]
+    params: Query
+    headers: Headers
+    max_retries: int
+    timeout: float | Timeout | None
+    files: HttpxRequestFiles | None
+    idempotency_key: str
+    json_data: Body
+    extra_json: AnyMapping
+    follow_redirects: bool
+
+
+@final
+class FinalRequestOptions(pydantic.BaseModel):
+    method: str
+    url: str
+    params: Query = {}
+    headers: Union[Headers, NotGiven] = NotGiven()
+    max_retries: Union[int, NotGiven] = NotGiven()
+    timeout: Union[float, Timeout, None, NotGiven] = NotGiven()
+    files: Union[HttpxRequestFiles, None] = None
+    idempotency_key: Union[str, None] = None
+    post_parser: Union[Callable[[Any], Any], NotGiven] = NotGiven()
+    follow_redirects: Union[bool, None] = None
+
+    # It should be noted that we cannot use `json` here as that would override
+    # a BaseModel method in an incompatible fashion.
+    json_data: Union[Body, None] = None
+    extra_json: Union[AnyMapping, None] = None
+
+    if PYDANTIC_V2:
+        model_config: ClassVar[ConfigDict] = ConfigDict(arbitrary_types_allowed=True)
+    else:
+
+        class Config(pydantic.BaseConfig):  # pyright: ignore[reportDeprecated]
+            arbitrary_types_allowed: bool = True
+
+    def get_max_retries(self, max_retries: int) -> int:
+        if isinstance(self.max_retries, NotGiven):
+            return max_retries
+        return self.max_retries
+
+    def _strip_raw_response_header(self) -> None:
+        if not is_given(self.headers):
+            return
+
+        if self.headers.get(RAW_RESPONSE_HEADER):
+            self.headers = {**self.headers}
+            self.headers.pop(RAW_RESPONSE_HEADER)
+
+    # override the `construct` method so that we can run custom transformations.
+    # this is necessary as we don't want to do any actual runtime type checking
+    # (which means we can't use validators) but we do want to ensure that `NotGiven`
+    # values are not present
+    #
+    # type ignore required because we're adding explicit types to `**values`
+    @classmethod
+    def construct(  # type: ignore
+        cls,
+        _fields_set: set[str] | None = None,
+        **values: Unpack[FinalRequestOptionsInput],
+    ) -> FinalRequestOptions:
+        kwargs: dict[str, Any] = {
+            # we unconditionally call `strip_not_given` on any value
+            # as it will just ignore any non-mapping types
+            key: strip_not_given(value)
+            for key, value in values.items()
+        }
+        if PYDANTIC_V2:
+            return super().model_construct(_fields_set, **kwargs)
+        return cast(FinalRequestOptions, super().construct(_fields_set, **kwargs))  # pyright: ignore[reportDeprecated]
+
+    if not TYPE_CHECKING:
+        # type checkers incorrectly complain about this assignment
+        model_construct = construct

venv/lib/python3.11/site-packages/groq/_qs.py

@@ -0,0 +1,150 @@
+from __future__ import annotations
+
+from typing import Any, List, Tuple, Union, Mapping, TypeVar
+from urllib.parse import parse_qs, urlencode
+from typing_extensions import Literal, get_args
+
+from ._types import NOT_GIVEN, NotGiven, NotGivenOr
+from ._utils import flatten
+
+_T = TypeVar("_T")
+
+
+ArrayFormat = Literal["comma", "repeat", "indices", "brackets"]
+NestedFormat = Literal["dots", "brackets"]
+
+PrimitiveData = Union[str, int, float, bool, None]
+# this should be Data = Union[PrimitiveData, "List[Data]", "Tuple[Data]", "Mapping[str, Data]"]
+# https://github.com/microsoft/pyright/issues/3555
+Data = Union[PrimitiveData, List[Any], Tuple[Any], "Mapping[str, Any]"]
+Params = Mapping[str, Data]
+
+
+class Querystring:
+    array_format: ArrayFormat
+    nested_format: NestedFormat
+
+    def __init__(
+        self,
+        *,
+        array_format: ArrayFormat = "repeat",
+        nested_format: NestedFormat = "brackets",
+    ) -> None:
+        self.array_format = array_format
+        self.nested_format = nested_format
+
+    def parse(self, query: str) -> Mapping[str, object]:
+        # Note: custom format syntax is not supported yet
+        return parse_qs(query)
+
+    def stringify(
+        self,
+        params: Params,
+        *,
+        array_format: NotGivenOr[ArrayFormat] = NOT_GIVEN,
+        nested_format: NotGivenOr[NestedFormat] = NOT_GIVEN,
+    ) -> str:
+        return urlencode(
+            self.stringify_items(
+                params,
+                array_format=array_format,
+                nested_format=nested_format,
+            )
+        )
+
+    def stringify_items(
+        self,
+        params: Params,
+        *,
+        array_format: NotGivenOr[ArrayFormat] = NOT_GIVEN,
+        nested_format: NotGivenOr[NestedFormat] = NOT_GIVEN,
+    ) -> list[tuple[str, str]]:
+        opts = Options(
+            qs=self,
+            array_format=array_format,
+            nested_format=nested_format,
+        )
+        return flatten([self._stringify_item(key, value, opts) for key, value in params.items()])
+
+    def _stringify_item(
+        self,
+        key: str,
+        value: Data,
+        opts: Options,
+    ) -> list[tuple[str, str]]:
+        if isinstance(value, Mapping):
+            items: list[tuple[str, str]] = []
+            nested_format = opts.nested_format
+            for subkey, subvalue in value.items():
+                items.extend(
+                    self._stringify_item(
+                        # TODO: error if unknown format
+                        f"{key}.{subkey}" if nested_format == "dots" else f"{key}[{subkey}]",
+                        subvalue,
+                        opts,
+                    )
+                )
+            return items
+
+        if isinstance(value, (list, tuple)):
+            array_format = opts.array_format
+            if array_format == "comma":
+                return [
+                    (
+                        key,
+                        ",".join(self._primitive_value_to_str(item) for item in value if item is not None),
+                    ),
+                ]
+            elif array_format == "repeat":
+                items = []
+                for item in value:
+                    items.extend(self._stringify_item(key, item, opts))
+                return items
+            elif array_format == "indices":
+                raise NotImplementedError("The array indices format is not supported yet")
+            elif array_format == "brackets":
+                items = []
+                key = key + "[]"
+                for item in value:
+                    items.extend(self._stringify_item(key, item, opts))
+                return items
+            else:
+                raise NotImplementedError(
+                    f"Unknown array_format value: {array_format}, choose from {', '.join(get_args(ArrayFormat))}"
+                )
+
+        serialised = self._primitive_value_to_str(value)
+        if not serialised:
+            return []
+        return [(key, serialised)]
+
+    def _primitive_value_to_str(self, value: PrimitiveData) -> str:
+        # copied from httpx
+        if value is True:
+            return "true"
+        elif value is False:
+            return "false"
+        elif value is None:
+            return ""
+        return str(value)
+
+
+_qs = Querystring()
+parse = _qs.parse
+stringify = _qs.stringify
+stringify_items = _qs.stringify_items
+
+
+class Options:
+    array_format: ArrayFormat
+    nested_format: NestedFormat
+
+    def __init__(
+        self,
+        qs: Querystring = _qs,
+        *,
+        array_format: NotGivenOr[ArrayFormat] = NOT_GIVEN,
+        nested_format: NotGivenOr[NestedFormat] = NOT_GIVEN,
+    ) -> None:
+        self.array_format = qs.array_format if isinstance(array_format, NotGiven) else array_format
+        self.nested_format = qs.nested_format if isinstance(nested_format, NotGiven) else nested_format

venv/lib/python3.11/site-packages/groq/_resource.py

@@ -0,0 +1,43 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+import time
+from typing import TYPE_CHECKING
+
+import anyio
+
+if TYPE_CHECKING:
+    from ._client import Groq, AsyncGroq
+
+
+class SyncAPIResource:
+    _client: Groq
+
+    def __init__(self, client: Groq) -> None:
+        self._client = client
+        self._get = client.get
+        self._post = client.post
+        self._patch = client.patch
+        self._put = client.put
+        self._delete = client.delete
+        self._get_api_list = client.get_api_list
+
+    def _sleep(self, seconds: float) -> None:
+        time.sleep(seconds)
+
+
+class AsyncAPIResource:
+    _client: AsyncGroq
+
+    def __init__(self, client: AsyncGroq) -> None:
+        self._client = client
+        self._get = client.get
+        self._post = client.post
+        self._patch = client.patch
+        self._put = client.put
+        self._delete = client.delete
+        self._get_api_list = client.get_api_list
+
+    async def _sleep(self, seconds: float) -> None:
+        await anyio.sleep(seconds)

venv/lib/python3.11/site-packages/groq/_response.py

@@ -0,0 +1,830 @@
+from __future__ import annotations
+
+import os
+import inspect
+import logging
+import datetime
+import functools
+from types import TracebackType
+from typing import (
+    TYPE_CHECKING,
+    Any,
+    Union,
+    Generic,
+    TypeVar,
+    Callable,
+    Iterator,
+    AsyncIterator,
+    cast,
+    overload,
+)
+from typing_extensions import Awaitable, ParamSpec, override, get_origin
+
+import anyio
+import httpx
+import pydantic
+
+from ._types import NoneType
+from ._utils import is_given, extract_type_arg, is_annotated_type, is_type_alias_type, extract_type_var_from_base
+from ._models import BaseModel, is_basemodel
+from ._constants import RAW_RESPONSE_HEADER, OVERRIDE_CAST_TO_HEADER
+from ._streaming import Stream, AsyncStream, is_stream_class_type, extract_stream_chunk_type
+from ._exceptions import GroqError, APIResponseValidationError
+
+if TYPE_CHECKING:
+    from ._models import FinalRequestOptions
+    from ._base_client import BaseClient
+
+
+P = ParamSpec("P")
+R = TypeVar("R")
+_T = TypeVar("_T")
+_APIResponseT = TypeVar("_APIResponseT", bound="APIResponse[Any]")
+_AsyncAPIResponseT = TypeVar("_AsyncAPIResponseT", bound="AsyncAPIResponse[Any]")
+
+log: logging.Logger = logging.getLogger(__name__)
+
+
+class BaseAPIResponse(Generic[R]):
+    _cast_to: type[R]
+    _client: BaseClient[Any, Any]
+    _parsed_by_type: dict[type[Any], Any]
+    _is_sse_stream: bool
+    _stream_cls: type[Stream[Any]] | type[AsyncStream[Any]] | None
+    _options: FinalRequestOptions
+
+    http_response: httpx.Response
+
+    retries_taken: int
+    """The number of retries made. If no retries happened this will be `0`"""
+
+    def __init__(
+        self,
+        *,
+        raw: httpx.Response,
+        cast_to: type[R],
+        client: BaseClient[Any, Any],
+        stream: bool,
+        stream_cls: type[Stream[Any]] | type[AsyncStream[Any]] | None,
+        options: FinalRequestOptions,
+        retries_taken: int = 0,
+    ) -> None:
+        self._cast_to = cast_to
+        self._client = client
+        self._parsed_by_type = {}
+        self._is_sse_stream = stream
+        self._stream_cls = stream_cls
+        self._options = options
+        self.http_response = raw
+        self.retries_taken = retries_taken
+
+    @property
+    def headers(self) -> httpx.Headers:
+        return self.http_response.headers
+
+    @property
+    def http_request(self) -> httpx.Request:
+        """Returns the httpx Request instance associated with the current response."""
+        return self.http_response.request
+
+    @property
+    def status_code(self) -> int:
+        return self.http_response.status_code
+
+    @property
+    def url(self) -> httpx.URL:
+        """Returns the URL for which the request was made."""
+        return self.http_response.url
+
+    @property
+    def method(self) -> str:
+        return self.http_request.method
+
+    @property
+    def http_version(self) -> str:
+        return self.http_response.http_version
+
+    @property
+    def elapsed(self) -> datetime.timedelta:
+        """The time taken for the complete request/response cycle to complete."""
+        return self.http_response.elapsed
+
+    @property
+    def is_closed(self) -> bool:
+        """Whether or not the response body has been closed.
+
+        If this is False then there is response data that has not been read yet.
+        You must either fully consume the response body or call `.close()`
+        before discarding the response to prevent resource leaks.
+        """
+        return self.http_response.is_closed
+
+    @override
+    def __repr__(self) -> str:
+        return (
+            f"<{self.__class__.__name__} [{self.status_code} {self.http_response.reason_phrase}] type={self._cast_to}>"
+        )
+
+    def _parse(self, *, to: type[_T] | None = None) -> R | _T:
+        cast_to = to if to is not None else self._cast_to
+
+        # unwrap `TypeAlias('Name', T)` -> `T`
+        if is_type_alias_type(cast_to):
+            cast_to = cast_to.__value__  # type: ignore[unreachable]
+
+        # unwrap `Annotated[T, ...]` -> `T`
+        if cast_to and is_annotated_type(cast_to):
+            cast_to = extract_type_arg(cast_to, 0)
+
+        origin = get_origin(cast_to) or cast_to
+
+        if self._is_sse_stream:
+            if to:
+                if not is_stream_class_type(to):
+                    raise TypeError(f"Expected custom parse type to be a subclass of {Stream} or {AsyncStream}")
+
+                return cast(
+                    _T,
+                    to(
+                        cast_to=extract_stream_chunk_type(
+                            to,
+                            failure_message="Expected custom stream type to be passed with a type argument, e.g. Stream[ChunkType]",
+                        ),
+                        response=self.http_response,
+                        client=cast(Any, self._client),
+                    ),
+                )
+
+            if self._stream_cls:
+                return cast(
+                    R,
+                    self._stream_cls(
+                        cast_to=extract_stream_chunk_type(self._stream_cls),
+                        response=self.http_response,
+                        client=cast(Any, self._client),
+                    ),
+                )
+
+            stream_cls = cast("type[Stream[Any]] | type[AsyncStream[Any]] | None", self._client._default_stream_cls)
+            if stream_cls is None:
+                raise MissingStreamClassError()
+
+            return cast(
+                R,
+                stream_cls(
+                    cast_to=cast_to,
+                    response=self.http_response,
+                    client=cast(Any, self._client),
+                ),
+            )
+
+        if cast_to is NoneType:
+            return cast(R, None)
+
+        response = self.http_response
+        if cast_to == str:
+            return cast(R, response.text)
+
+        if cast_to == bytes:
+            return cast(R, response.content)
+
+        if cast_to == int:
+            return cast(R, int(response.text))
+
+        if cast_to == float:
+            return cast(R, float(response.text))
+
+        if cast_to == bool:
+            return cast(R, response.text.lower() == "true")
+
+        if origin == APIResponse:
+            raise RuntimeError("Unexpected state - cast_to is `APIResponse`")
+
+        if inspect.isclass(origin) and issubclass(origin, httpx.Response):
+            # Because of the invariance of our ResponseT TypeVar, users can subclass httpx.Response
+            # and pass that class to our request functions. We cannot change the variance to be either
+            # covariant or contravariant as that makes our usage of ResponseT illegal. We could construct
+            # the response class ourselves but that is something that should be supported directly in httpx
+            # as it would be easy to incorrectly construct the Response object due to the multitude of arguments.
+            if cast_to != httpx.Response:
+                raise ValueError(f"Subclasses of httpx.Response cannot be passed to `cast_to`")
+            return cast(R, response)
+
+        if (
+            inspect.isclass(
+                origin  # pyright: ignore[reportUnknownArgumentType]
+            )
+            and not issubclass(origin, BaseModel)
+            and issubclass(origin, pydantic.BaseModel)
+        ):
+            raise TypeError("Pydantic models must subclass our base model type, e.g. `from groq import BaseModel`")
+
+        if (
+            cast_to is not object
+            and not origin is list
+            and not origin is dict
+            and not origin is Union
+            and not issubclass(origin, BaseModel)
+        ):
+            raise RuntimeError(
+                f"Unsupported type, expected {cast_to} to be a subclass of {BaseModel}, {dict}, {list}, {Union}, {NoneType}, {str} or {httpx.Response}."
+            )
+
+        # split is required to handle cases where additional information is included
+        # in the response, e.g. application/json; charset=utf-8
+        content_type, *_ = response.headers.get("content-type", "*").split(";")
+        if not content_type.endswith("json"):
+            if is_basemodel(cast_to):
+                try:
+                    data = response.json()
+                except Exception as exc:
+                    log.debug("Could not read JSON from response data due to %s - %s", type(exc), exc)
+                else:
+                    return self._client._process_response_data(
+                        data=data,
+                        cast_to=cast_to,  # type: ignore
+                        response=response,
+                    )
+
+            if self._client._strict_response_validation:
+                raise APIResponseValidationError(
+                    response=response,
+                    message=f"Expected Content-Type response header to be `application/json` but received `{content_type}` instead.",
+                    body=response.text,
+                )
+
+            # If the API responds with content that isn't JSON then we just return
+            # the (decoded) text without performing any parsing so that you can still
+            # handle the response however you need to.
+            return response.text  # type: ignore
+
+        data = response.json()
+
+        return self._client._process_response_data(
+            data=data,
+            cast_to=cast_to,  # type: ignore
+            response=response,
+        )
+
+
+class APIResponse(BaseAPIResponse[R]):
+    @overload
+    def parse(self, *, to: type[_T]) -> _T: ...
+
+    @overload
+    def parse(self) -> R: ...
+
+    def parse(self, *, to: type[_T] | None = None) -> R | _T:
+        """Returns the rich python representation of this response's data.
+
+        For lower-level control, see `.read()`, `.json()`, `.iter_bytes()`.
+
+        You can customise the type that the response is parsed into through
+        the `to` argument, e.g.
+
+        ```py
+        from groq import BaseModel
+
+
+        class MyModel(BaseModel):
+            foo: str
+
+
+        obj = response.parse(to=MyModel)
+        print(obj.foo)
+        ```
+
+        We support parsing:
+          - `BaseModel`
+          - `dict`
+          - `list`
+          - `Union`
+          - `str`
+          - `int`
+          - `float`
+          - `httpx.Response`
+        """
+        cache_key = to if to is not None else self._cast_to
+        cached = self._parsed_by_type.get(cache_key)
+        if cached is not None:
+            return cached  # type: ignore[no-any-return]
+
+        if not self._is_sse_stream:
+            self.read()
+
+        parsed = self._parse(to=to)
+        if is_given(self._options.post_parser):
+            parsed = self._options.post_parser(parsed)
+
+        self._parsed_by_type[cache_key] = parsed
+        return parsed
+
+    def read(self) -> bytes:
+        """Read and return the binary response content."""
+        try:
+            return self.http_response.read()
+        except httpx.StreamConsumed as exc:
+            # The default error raised by httpx isn't very
+            # helpful in our case so we re-raise it with
+            # a different error message.
+            raise StreamAlreadyConsumed() from exc
+
+    def text(self) -> str:
+        """Read and decode the response content into a string."""
+        self.read()
+        return self.http_response.text
+
+    def json(self) -> object:
+        """Read and decode the JSON response content."""
+        self.read()
+        return self.http_response.json()
+
+    def close(self) -> None:
+        """Close the response and release the connection.
+
+        Automatically called if the response body is read to completion.
+        """
+        self.http_response.close()
+
+    def iter_bytes(self, chunk_size: int | None = None) -> Iterator[bytes]:
+        """
+        A byte-iterator over the decoded response content.
+
+        This automatically handles gzip, deflate and brotli encoded responses.
+        """
+        for chunk in self.http_response.iter_bytes(chunk_size):
+            yield chunk
+
+    def iter_text(self, chunk_size: int | None = None) -> Iterator[str]:
+        """A str-iterator over the decoded response content
+        that handles both gzip, deflate, etc but also detects the content's
+        string encoding.
+        """
+        for chunk in self.http_response.iter_text(chunk_size):
+            yield chunk
+
+    def iter_lines(self) -> Iterator[str]:
+        """Like `iter_text()` but will only yield chunks for each line"""
+        for chunk in self.http_response.iter_lines():
+            yield chunk
+
+
+class AsyncAPIResponse(BaseAPIResponse[R]):
+    @overload
+    async def parse(self, *, to: type[_T]) -> _T: ...
+
+    @overload
+    async def parse(self) -> R: ...
+
+    async def parse(self, *, to: type[_T] | None = None) -> R | _T:
+        """Returns the rich python representation of this response's data.
+
+        For lower-level control, see `.read()`, `.json()`, `.iter_bytes()`.
+
+        You can customise the type that the response is parsed into through
+        the `to` argument, e.g.
+
+        ```py
+        from groq import BaseModel
+
+
+        class MyModel(BaseModel):
+            foo: str
+
+
+        obj = response.parse(to=MyModel)
+        print(obj.foo)
+        ```
+
+        We support parsing:
+          - `BaseModel`
+          - `dict`
+          - `list`
+          - `Union`
+          - `str`
+          - `httpx.Response`
+        """
+        cache_key = to if to is not None else self._cast_to
+        cached = self._parsed_by_type.get(cache_key)
+        if cached is not None:
+            return cached  # type: ignore[no-any-return]
+
+        if not self._is_sse_stream:
+            await self.read()
+
+        parsed = self._parse(to=to)
+        if is_given(self._options.post_parser):
+            parsed = self._options.post_parser(parsed)
+
+        self._parsed_by_type[cache_key] = parsed
+        return parsed
+
+    async def read(self) -> bytes:
+        """Read and return the binary response content."""
+        try:
+            return await self.http_response.aread()
+        except httpx.StreamConsumed as exc:
+            # the default error raised by httpx isn't very
+            # helpful in our case so we re-raise it with
+            # a different error message
+            raise StreamAlreadyConsumed() from exc
+
+    async def text(self) -> str:
+        """Read and decode the response content into a string."""
+        await self.read()
+        return self.http_response.text
+
+    async def json(self) -> object:
+        """Read and decode the JSON response content."""
+        await self.read()
+        return self.http_response.json()
+
+    async def close(self) -> None:
+        """Close the response and release the connection.
+
+        Automatically called if the response body is read to completion.
+        """
+        await self.http_response.aclose()
+
+    async def iter_bytes(self, chunk_size: int | None = None) -> AsyncIterator[bytes]:
+        """
+        A byte-iterator over the decoded response content.
+
+        This automatically handles gzip, deflate and brotli encoded responses.
+        """
+        async for chunk in self.http_response.aiter_bytes(chunk_size):
+            yield chunk
+
+    async def iter_text(self, chunk_size: int | None = None) -> AsyncIterator[str]:
+        """A str-iterator over the decoded response content
+        that handles both gzip, deflate, etc but also detects the content's
+        string encoding.
+        """
+        async for chunk in self.http_response.aiter_text(chunk_size):
+            yield chunk
+
+    async def iter_lines(self) -> AsyncIterator[str]:
+        """Like `iter_text()` but will only yield chunks for each line"""
+        async for chunk in self.http_response.aiter_lines():
+            yield chunk
+
+
+class BinaryAPIResponse(APIResponse[bytes]):
+    """Subclass of APIResponse providing helpers for dealing with binary data.
+
+    Note: If you want to stream the response data instead of eagerly reading it
+    all at once then you should use `.with_streaming_response` when making
+    the API request, e.g. `.with_streaming_response.get_binary_response()`
+    """
+
+    def write_to_file(
+        self,
+        file: str | os.PathLike[str],
+    ) -> None:
+        """Write the output to the given file.
+
+        Accepts a filename or any path-like object, e.g. pathlib.Path
+
+        Note: if you want to stream the data to the file instead of writing
+        all at once then you should use `.with_streaming_response` when making
+        the API request, e.g. `.with_streaming_response.get_binary_response()`
+        """
+        with open(file, mode="wb") as f:
+            for data in self.iter_bytes():
+                f.write(data)
+
+
+class AsyncBinaryAPIResponse(AsyncAPIResponse[bytes]):
+    """Subclass of APIResponse providing helpers for dealing with binary data.
+
+    Note: If you want to stream the response data instead of eagerly reading it
+    all at once then you should use `.with_streaming_response` when making
+    the API request, e.g. `.with_streaming_response.get_binary_response()`
+    """
+
+    async def write_to_file(
+        self,
+        file: str | os.PathLike[str],
+    ) -> None:
+        """Write the output to the given file.
+
+        Accepts a filename or any path-like object, e.g. pathlib.Path
+
+        Note: if you want to stream the data to the file instead of writing
+        all at once then you should use `.with_streaming_response` when making
+        the API request, e.g. `.with_streaming_response.get_binary_response()`
+        """
+        path = anyio.Path(file)
+        async with await path.open(mode="wb") as f:
+            async for data in self.iter_bytes():
+                await f.write(data)
+
+
+class StreamedBinaryAPIResponse(APIResponse[bytes]):
+    def stream_to_file(
+        self,
+        file: str | os.PathLike[str],
+        *,
+        chunk_size: int | None = None,
+    ) -> None:
+        """Streams the output to the given file.
+
+        Accepts a filename or any path-like object, e.g. pathlib.Path
+        """
+        with open(file, mode="wb") as f:
+            for data in self.iter_bytes(chunk_size):
+                f.write(data)
+
+
+class AsyncStreamedBinaryAPIResponse(AsyncAPIResponse[bytes]):
+    async def stream_to_file(
+        self,
+        file: str | os.PathLike[str],
+        *,
+        chunk_size: int | None = None,
+    ) -> None:
+        """Streams the output to the given file.
+
+        Accepts a filename or any path-like object, e.g. pathlib.Path
+        """
+        path = anyio.Path(file)
+        async with await path.open(mode="wb") as f:
+            async for data in self.iter_bytes(chunk_size):
+                await f.write(data)
+
+
+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 `groq._streaming` for reference",
+        )
+
+
+class StreamAlreadyConsumed(GroqError):
+    """
+    Attempted to read or stream content, but the content has already
+    been streamed.
+
+    This can happen if you use a method like `.iter_lines()` and then attempt
+    to read th entire response body afterwards, e.g.
+
+    ```py
+    response = await client.post(...)
+    async for line in response.iter_lines():
+        ...  # do something with `line`
+
+    content = await response.read()
+    # ^ error
+    ```
+
+    If you want this behaviour you'll need to either manually accumulate the response
+    content or call `await response.read()` before iterating over the stream.
+    """
+
+    def __init__(self) -> None:
+        message = (
+            "Attempted to read or stream some content, but the content has "
+            "already been streamed. "
+            "This could be due to attempting to stream the response "
+            "content more than once."
+            "\n\n"
+            "You can fix this by manually accumulating the response content while streaming "
+            "or by calling `.read()` before starting to stream."
+        )
+        super().__init__(message)
+
+
+class ResponseContextManager(Generic[_APIResponseT]):
+    """Context manager for ensuring that a request is not made
+    until it is entered and that the response will always be closed
+    when the context manager exits
+    """
+
+    def __init__(self, request_func: Callable[[], _APIResponseT]) -> None:
+        self._request_func = request_func
+        self.__response: _APIResponseT | None = None
+
+    def __enter__(self) -> _APIResponseT:
+        self.__response = self._request_func()
+        return self.__response
+
+    def __exit__(
+        self,
+        exc_type: type[BaseException] | None,
+        exc: BaseException | None,
+        exc_tb: TracebackType | None,
+    ) -> None:
+        if self.__response is not None:
+            self.__response.close()
+
+
+class AsyncResponseContextManager(Generic[_AsyncAPIResponseT]):
+    """Context manager for ensuring that a request is not made
+    until it is entered and that the response will always be closed
+    when the context manager exits
+    """
+
+    def __init__(self, api_request: Awaitable[_AsyncAPIResponseT]) -> None:
+        self._api_request = api_request
+        self.__response: _AsyncAPIResponseT | None = None
+
+    async def __aenter__(self) -> _AsyncAPIResponseT:
+        self.__response = await self._api_request
+        return self.__response
+
+    async def __aexit__(
+        self,
+        exc_type: type[BaseException] | None,
+        exc: BaseException | None,
+        exc_tb: TracebackType | None,
+    ) -> None:
+        if self.__response is not None:
+            await self.__response.close()
+
+
+def to_streamed_response_wrapper(func: Callable[P, R]) -> Callable[P, ResponseContextManager[APIResponse[R]]]:
+    """Higher order function that takes one of our bound API methods and wraps it
+    to support streaming and returning the raw `APIResponse` object directly.
+    """
+
+    @functools.wraps(func)
+    def wrapped(*args: P.args, **kwargs: P.kwargs) -> ResponseContextManager[APIResponse[R]]:
+        extra_headers: dict[str, str] = {**(cast(Any, kwargs.get("extra_headers")) or {})}
+        extra_headers[RAW_RESPONSE_HEADER] = "stream"
+
+        kwargs["extra_headers"] = extra_headers
+
+        make_request = functools.partial(func, *args, **kwargs)
+
+        return ResponseContextManager(cast(Callable[[], APIResponse[R]], make_request))
+
+    return wrapped
+
+
+def async_to_streamed_response_wrapper(
+    func: Callable[P, Awaitable[R]],
+) -> Callable[P, AsyncResponseContextManager[AsyncAPIResponse[R]]]:
+    """Higher order function that takes one of our bound API methods and wraps it
+    to support streaming and returning the raw `APIResponse` object directly.
+    """
+
+    @functools.wraps(func)
+    def wrapped(*args: P.args, **kwargs: P.kwargs) -> AsyncResponseContextManager[AsyncAPIResponse[R]]:
+        extra_headers: dict[str, str] = {**(cast(Any, kwargs.get("extra_headers")) or {})}
+        extra_headers[RAW_RESPONSE_HEADER] = "stream"
+
+        kwargs["extra_headers"] = extra_headers
+
+        make_request = func(*args, **kwargs)
+
+        return AsyncResponseContextManager(cast(Awaitable[AsyncAPIResponse[R]], make_request))
+
+    return wrapped
+
+
+def to_custom_streamed_response_wrapper(
+    func: Callable[P, object],
+    response_cls: type[_APIResponseT],
+) -> Callable[P, ResponseContextManager[_APIResponseT]]:
+    """Higher order function that takes one of our bound API methods and an `APIResponse` class
+    and wraps the method to support streaming and returning the given response class directly.
+
+    Note: the given `response_cls` *must* be concrete, e.g. `class BinaryAPIResponse(APIResponse[bytes])`
+    """
+
+    @functools.wraps(func)
+    def wrapped(*args: P.args, **kwargs: P.kwargs) -> ResponseContextManager[_APIResponseT]:
+        extra_headers: dict[str, Any] = {**(cast(Any, kwargs.get("extra_headers")) or {})}
+        extra_headers[RAW_RESPONSE_HEADER] = "stream"
+        extra_headers[OVERRIDE_CAST_TO_HEADER] = response_cls
+
+        kwargs["extra_headers"] = extra_headers
+
+        make_request = functools.partial(func, *args, **kwargs)
+
+        return ResponseContextManager(cast(Callable[[], _APIResponseT], make_request))
+
+    return wrapped
+
+
+def async_to_custom_streamed_response_wrapper(
+    func: Callable[P, Awaitable[object]],
+    response_cls: type[_AsyncAPIResponseT],
+) -> Callable[P, AsyncResponseContextManager[_AsyncAPIResponseT]]:
+    """Higher order function that takes one of our bound API methods and an `APIResponse` class
+    and wraps the method to support streaming and returning the given response class directly.
+
+    Note: the given `response_cls` *must* be concrete, e.g. `class BinaryAPIResponse(APIResponse[bytes])`
+    """
+
+    @functools.wraps(func)
+    def wrapped(*args: P.args, **kwargs: P.kwargs) -> AsyncResponseContextManager[_AsyncAPIResponseT]:
+        extra_headers: dict[str, Any] = {**(cast(Any, kwargs.get("extra_headers")) or {})}
+        extra_headers[RAW_RESPONSE_HEADER] = "stream"
+        extra_headers[OVERRIDE_CAST_TO_HEADER] = response_cls
+
+        kwargs["extra_headers"] = extra_headers
+
+        make_request = func(*args, **kwargs)
+
+        return AsyncResponseContextManager(cast(Awaitable[_AsyncAPIResponseT], make_request))
+
+    return wrapped
+
+
+def to_raw_response_wrapper(func: Callable[P, R]) -> Callable[P, APIResponse[R]]:
+    """Higher order function that takes one of our bound API methods and wraps it
+    to support returning the raw `APIResponse` object directly.
+    """
+
+    @functools.wraps(func)
+    def wrapped(*args: P.args, **kwargs: P.kwargs) -> APIResponse[R]:
+        extra_headers: dict[str, str] = {**(cast(Any, kwargs.get("extra_headers")) or {})}
+        extra_headers[RAW_RESPONSE_HEADER] = "raw"
+
+        kwargs["extra_headers"] = extra_headers
+
+        return cast(APIResponse[R], func(*args, **kwargs))
+
+    return wrapped
+
+
+def async_to_raw_response_wrapper(func: Callable[P, Awaitable[R]]) -> Callable[P, Awaitable[AsyncAPIResponse[R]]]:
+    """Higher order function that takes one of our bound API methods and wraps it
+    to support returning the raw `APIResponse` object directly.
+    """
+
+    @functools.wraps(func)
+    async def wrapped(*args: P.args, **kwargs: P.kwargs) -> AsyncAPIResponse[R]:
+        extra_headers: dict[str, str] = {**(cast(Any, kwargs.get("extra_headers")) or {})}
+        extra_headers[RAW_RESPONSE_HEADER] = "raw"
+
+        kwargs["extra_headers"] = extra_headers
+
+        return cast(AsyncAPIResponse[R], await func(*args, **kwargs))
+
+    return wrapped
+
+
+def to_custom_raw_response_wrapper(
+    func: Callable[P, object],
+    response_cls: type[_APIResponseT],
+) -> Callable[P, _APIResponseT]:
+    """Higher order function that takes one of our bound API methods and an `APIResponse` class
+    and wraps the method to support returning the given response class directly.
+
+    Note: the given `response_cls` *must* be concrete, e.g. `class BinaryAPIResponse(APIResponse[bytes])`
+    """
+
+    @functools.wraps(func)
+    def wrapped(*args: P.args, **kwargs: P.kwargs) -> _APIResponseT:
+        extra_headers: dict[str, Any] = {**(cast(Any, kwargs.get("extra_headers")) or {})}
+        extra_headers[RAW_RESPONSE_HEADER] = "raw"
+        extra_headers[OVERRIDE_CAST_TO_HEADER] = response_cls
+
+        kwargs["extra_headers"] = extra_headers
+
+        return cast(_APIResponseT, func(*args, **kwargs))
+
+    return wrapped
+
+
+def async_to_custom_raw_response_wrapper(
+    func: Callable[P, Awaitable[object]],
+    response_cls: type[_AsyncAPIResponseT],
+) -> Callable[P, Awaitable[_AsyncAPIResponseT]]:
+    """Higher order function that takes one of our bound API methods and an `APIResponse` class
+    and wraps the method to support returning the given response class directly.
+
+    Note: the given `response_cls` *must* be concrete, e.g. `class BinaryAPIResponse(APIResponse[bytes])`
+    """
+
+    @functools.wraps(func)
+    def wrapped(*args: P.args, **kwargs: P.kwargs) -> Awaitable[_AsyncAPIResponseT]:
+        extra_headers: dict[str, Any] = {**(cast(Any, kwargs.get("extra_headers")) or {})}
+        extra_headers[RAW_RESPONSE_HEADER] = "raw"
+        extra_headers[OVERRIDE_CAST_TO_HEADER] = response_cls
+
+        kwargs["extra_headers"] = extra_headers
+
+        return cast(Awaitable[_AsyncAPIResponseT], func(*args, **kwargs))
+
+    return wrapped
+
+
+def extract_response_type(typ: type[BaseAPIResponse[Any]]) -> type:
+    """Given a type like `APIResponse[T]`, returns the generic type variable `T`.
+
+    This also handles the case where a concrete subclass is given, e.g.
+    ```py
+    class MyResponse(APIResponse[bytes]):
+        ...
+
+    extract_response_type(MyResponse) -> bytes
+    ```
+    """
+    return extract_type_var_from_base(
+        typ,
+        generic_bases=cast("tuple[type, ...]", (BaseAPIResponse, APIResponse, AsyncAPIResponse)),
+        index=0,
+    )

venv/lib/python3.11/site-packages/groq/_streaming.py

@@ -0,0 +1,410 @@
+# Note: initially copied from https://github.com/florimondmanca/httpx-sse/blob/master/src/httpx_sse/_decoders.py
+from __future__ import annotations
+
+import json
+import inspect
+from types import TracebackType
+from typing import TYPE_CHECKING, Any, Generic, TypeVar, Iterator, AsyncIterator, cast
+from typing_extensions import Self, Protocol, TypeGuard, override, get_origin, runtime_checkable
+
+import httpx
+
+from ._utils import is_mapping, extract_type_var_from_base
+from ._exceptions import APIError
+
+if TYPE_CHECKING:
+    from ._client import Groq, AsyncGroq
+
+
+_T = TypeVar("_T")
+
+
+class Stream(Generic[_T]):
+    """Provides the core interface to iterate over a synchronous stream response."""
+
+    response: httpx.Response
+
+    _decoder: SSEBytesDecoder
+
+    def __init__(
+        self,
+        *,
+        cast_to: type[_T],
+        response: httpx.Response,
+        client: Groq,
+    ) -> None:
+        self.response = response
+        self._cast_to = cast_to
+        self._client = client
+        self._decoder = client._make_sse_decoder()
+        self._iterator = self.__stream__()
+
+    def __next__(self) -> _T:
+        return self._iterator.__next__()
+
+    def __iter__(self) -> Iterator[_T]:
+        for item in self._iterator:
+            yield item
+
+    def _iter_events(self) -> Iterator[ServerSentEvent]:
+        yield from self._decoder.iter_bytes(self.response.iter_bytes())
+
+    def __stream__(self) -> Iterator[_T]:
+        cast_to = cast(Any, self._cast_to)
+        response = self.response
+        process_data = self._client._process_response_data
+        iterator = self._iter_events()
+
+        for sse in iterator:
+            if sse.data.startswith("[DONE]"):
+                break
+
+            if sse.event is None:
+                data = sse.json()
+                if is_mapping(data) and data.get("error"):
+                    message = None
+                    error = data.get("error")
+                    if is_mapping(error):
+                        message = error.get("message")
+                    if not message or not isinstance(message, str):
+                        message = "An error occurred during streaming"
+
+                    raise APIError(
+                        message=message,
+                        request=self.response.request,
+                        body=data["error"],
+                    )
+
+                yield process_data(data=data, cast_to=cast_to, response=response)
+
+            else:
+                data = sse.json()
+
+                if sse.event == "error" and is_mapping(data) and data.get("error"):
+                    message = None
+                    error = data.get("error")
+                    if is_mapping(error):
+                        message = error.get("message")
+                    if not message or not isinstance(message, str):
+                        message = "An error occurred during streaming"
+
+                    raise APIError(
+                        message=message,
+                        request=self.response.request,
+                        body=data["error"],
+                    )
+
+                yield process_data(data={"data": data, "event": sse.event}, cast_to=cast_to, response=response)
+
+        # Ensure the entire stream is consumed
+        for _sse in iterator:
+            ...
+
+    def __enter__(self) -> Self:
+        return self
+
+    def __exit__(
+        self,
+        exc_type: type[BaseException] | None,
+        exc: BaseException | None,
+        exc_tb: TracebackType | None,
+    ) -> None:
+        self.close()
+
+    def close(self) -> None:
+        """
+        Close the response and release the connection.
+
+        Automatically called if the response body is read to completion.
+        """
+        self.response.close()
+
+
+class AsyncStream(Generic[_T]):
+    """Provides the core interface to iterate over an asynchronous stream response."""
+
+    response: httpx.Response
+
+    _decoder: SSEDecoder | SSEBytesDecoder
+
+    def __init__(
+        self,
+        *,
+        cast_to: type[_T],
+        response: httpx.Response,
+        client: AsyncGroq,
+    ) -> None:
+        self.response = response
+        self._cast_to = cast_to
+        self._client = client
+        self._decoder = client._make_sse_decoder()
+        self._iterator = self.__stream__()
+
+    async def __anext__(self) -> _T:
+        return await self._iterator.__anext__()
+
+    async def __aiter__(self) -> AsyncIterator[_T]:
+        async for item in self._iterator:
+            yield item
+
+    async def _iter_events(self) -> AsyncIterator[ServerSentEvent]:
+        async for sse in self._decoder.aiter_bytes(self.response.aiter_bytes()):
+            yield sse
+
+    async def __stream__(self) -> AsyncIterator[_T]:
+        cast_to = cast(Any, self._cast_to)
+        response = self.response
+        process_data = self._client._process_response_data
+        iterator = self._iter_events()
+
+        async for sse in iterator:
+            if sse.data.startswith("[DONE]"):
+                break
+
+            if sse.event is None:
+                data = sse.json()
+                if is_mapping(data) and data.get("error"):
+                    message = None
+                    error = data.get("error")
+                    if is_mapping(error):
+                        message = error.get("message")
+                    if not message or not isinstance(message, str):
+                        message = "An error occurred during streaming"
+
+                    raise APIError(
+                        message=message,
+                        request=self.response.request,
+                        body=data["error"],
+                    )
+
+                yield process_data(data=data, cast_to=cast_to, response=response)
+
+            else:
+                data = sse.json()
+
+                if sse.event == "error" and is_mapping(data) and data.get("error"):
+                    message = None
+                    error = data.get("error")
+                    if is_mapping(error):
+                        message = error.get("message")
+                    if not message or not isinstance(message, str):
+                        message = "An error occurred during streaming"
+
+                    raise APIError(
+                        message=message,
+                        request=self.response.request,
+                        body=data["error"],
+                    )
+
+                yield process_data(data={"data": data, "event": sse.event}, cast_to=cast_to, response=response)
+
+        # Ensure the entire stream is consumed
+        async for _sse in iterator:
+            ...
+
+    async def __aenter__(self) -> Self:
+        return self
+
+    async def __aexit__(
+        self,
+        exc_type: type[BaseException] | None,
+        exc: BaseException | None,
+        exc_tb: TracebackType | None,
+    ) -> None:
+        await self.close()
+
+    async def close(self) -> None:
+        """
+        Close the response and release the connection.
+
+        Automatically called if the response body is read to completion.
+        """
+        await self.response.aclose()
+
+
+class ServerSentEvent:
+    def __init__(
+        self,
+        *,
+        event: str | None = None,
+        data: str | None = None,
+        id: str | None = None,
+        retry: int | None = None,
+    ) -> None:
+        if data is None:
+            data = ""
+
+        self._id = id
+        self._data = data
+        self._event = event or None
+        self._retry = retry
+
+    @property
+    def event(self) -> str | None:
+        return self._event
+
+    @property
+    def id(self) -> str | None:
+        return self._id
+
+    @property
+    def retry(self) -> int | None:
+        return self._retry
+
+    @property
+    def data(self) -> str:
+        return self._data
+
+    def json(self) -> Any:
+        return json.loads(self.data)
+
+    @override
+    def __repr__(self) -> str:
+        return f"ServerSentEvent(event={self.event}, data={self.data}, id={self.id}, retry={self.retry})"
+
+
+class SSEDecoder:
+    _data: list[str]
+    _event: str | None
+    _retry: int | None
+    _last_event_id: str | None
+
+    def __init__(self) -> None:
+        self._event = None
+        self._data = []
+        self._last_event_id = None
+        self._retry = None
+
+    def iter_bytes(self, iterator: Iterator[bytes]) -> Iterator[ServerSentEvent]:
+        """Given an iterator that yields raw binary data, iterate over it & yield every event encountered"""
+        for chunk in self._iter_chunks(iterator):
+            # Split before decoding so splitlines() only uses \r and \n
+            for raw_line in chunk.splitlines():
+                line = raw_line.decode("utf-8")
+                sse = self.decode(line)
+                if sse:
+                    yield sse
+
+    def _iter_chunks(self, iterator: Iterator[bytes]) -> Iterator[bytes]:
+        """Given an iterator that yields raw binary data, iterate over it and yield individual SSE chunks"""
+        data = b""
+        for chunk in iterator:
+            for line in chunk.splitlines(keepends=True):
+                data += line
+                if data.endswith((b"\r\r", b"\n\n", b"\r\n\r\n")):
+                    yield data
+                    data = b""
+        if data:
+            yield data
+
+    async def aiter_bytes(self, iterator: AsyncIterator[bytes]) -> AsyncIterator[ServerSentEvent]:
+        """Given an iterator that yields raw binary data, iterate over it & yield every event encountered"""
+        async for chunk in self._aiter_chunks(iterator):
+            # Split before decoding so splitlines() only uses \r and \n
+            for raw_line in chunk.splitlines():
+                line = raw_line.decode("utf-8")
+                sse = self.decode(line)
+                if sse:
+                    yield sse
+
+    async def _aiter_chunks(self, iterator: AsyncIterator[bytes]) -> AsyncIterator[bytes]:
+        """Given an iterator that yields raw binary data, iterate over it and yield individual SSE chunks"""
+        data = b""
+        async for chunk in iterator:
+            for line in chunk.splitlines(keepends=True):
+                data += line
+                if data.endswith((b"\r\r", b"\n\n", b"\r\n\r\n")):
+                    yield data
+                    data = b""
+        if data:
+            yield data
+
+    def decode(self, line: str) -> ServerSentEvent | None:
+        # See: https://html.spec.whatwg.org/multipage/server-sent-events.html#event-stream-interpretation  # noqa: E501
+
+        if not line:
+            if not self._event and not self._data and not self._last_event_id and self._retry is None:
+                return None
+
+            sse = ServerSentEvent(
+                event=self._event,
+                data="\n".join(self._data),
+                id=self._last_event_id,
+                retry=self._retry,
+            )
+
+            # NOTE: as per the SSE spec, do not reset last_event_id.
+            self._event = None
+            self._data = []
+            self._retry = None
+
+            return sse
+
+        if line.startswith(":"):
+            return None
+
+        fieldname, _, value = line.partition(":")
+
+        if value.startswith(" "):
+            value = value[1:]
+
+        if fieldname == "event":
+            self._event = value
+        elif fieldname == "data":
+            self._data.append(value)
+        elif fieldname == "id":
+            if "\0" in value:
+                pass
+            else:
+                self._last_event_id = value
+        elif fieldname == "retry":
+            try:
+                self._retry = int(value)
+            except (TypeError, ValueError):
+                pass
+        else:
+            pass  # Field is ignored.
+
+        return None
+
+
+@runtime_checkable
+class SSEBytesDecoder(Protocol):
+    def iter_bytes(self, iterator: Iterator[bytes]) -> Iterator[ServerSentEvent]:
+        """Given an iterator that yields raw binary data, iterate over it & yield every event encountered"""
+        ...
+
+    def aiter_bytes(self, iterator: AsyncIterator[bytes]) -> AsyncIterator[ServerSentEvent]:
+        """Given an async iterator that yields raw binary data, iterate over it & yield every event encountered"""
+        ...
+
+
+def is_stream_class_type(typ: type) -> TypeGuard[type[Stream[object]] | type[AsyncStream[object]]]:
+    """TypeGuard for determining whether or not the given type is a subclass of `Stream` / `AsyncStream`"""
+    origin = get_origin(typ) or typ
+    return inspect.isclass(origin) and issubclass(origin, (Stream, AsyncStream))
+
+
+def extract_stream_chunk_type(
+    stream_cls: type,
+    *,
+    failure_message: str | None = None,
+) -> type:
+    """Given a type like `Stream[T]`, returns the generic type variable `T`.
+
+    This also handles the case where a concrete subclass is given, e.g.
+    ```py
+    class MyStream(Stream[bytes]):
+        ...
+
+    extract_stream_chunk_type(MyStream) -> bytes
+    ```
+    """
+    from ._base_client import Stream, AsyncStream
+
+    return extract_type_var_from_base(
+        stream_cls,
+        index=0,
+        generic_bases=cast("tuple[type, ...]", (Stream, AsyncStream)),
+        failure_message=failure_message,
+    )

venv/lib/python3.11/site-packages/groq/_types.py

@@ -0,0 +1,219 @@
+from __future__ import annotations
+
+from os import PathLike
+from typing import (
+    IO,
+    TYPE_CHECKING,
+    Any,
+    Dict,
+    List,
+    Type,
+    Tuple,
+    Union,
+    Mapping,
+    TypeVar,
+    Callable,
+    Optional,
+    Sequence,
+)
+from typing_extensions import Set, Literal, Protocol, TypeAlias, TypedDict, override, runtime_checkable
+
+import httpx
+import pydantic
+from httpx import URL, Proxy, Timeout, Response, BaseTransport, AsyncBaseTransport
+
+if TYPE_CHECKING:
+    from ._models import BaseModel
+    from ._response import APIResponse, AsyncAPIResponse
+
+Transport = BaseTransport
+AsyncTransport = AsyncBaseTransport
+Query = Mapping[str, object]
+Body = object
+AnyMapping = Mapping[str, object]
+ModelT = TypeVar("ModelT", bound=pydantic.BaseModel)
+_T = TypeVar("_T")
+
+
+# Approximates httpx internal ProxiesTypes and RequestFiles types
+# while adding support for `PathLike` instances
+ProxiesDict = Dict["str | URL", Union[None, str, URL, Proxy]]
+ProxiesTypes = Union[str, Proxy, ProxiesDict]
+if TYPE_CHECKING:
+    Base64FileInput = Union[IO[bytes], PathLike[str]]
+    FileContent = Union[IO[bytes], bytes, PathLike[str]]
+else:
+    Base64FileInput = Union[IO[bytes], PathLike]
+    FileContent = Union[IO[bytes], bytes, PathLike]  # PathLike is not subscriptable in Python 3.8.
+FileTypes = Union[
+    # file (or bytes)
+    FileContent,
+    # (filename, file (or bytes))
+    Tuple[Optional[str], FileContent],
+    # (filename, file (or bytes), content_type)
+    Tuple[Optional[str], FileContent, Optional[str]],
+    # (filename, file (or bytes), content_type, headers)
+    Tuple[Optional[str], FileContent, Optional[str], Mapping[str, str]],
+]
+RequestFiles = Union[Mapping[str, FileTypes], Sequence[Tuple[str, FileTypes]]]
+
+# duplicate of the above but without our custom file support
+HttpxFileContent = Union[IO[bytes], bytes]
+HttpxFileTypes = Union[
+    # file (or bytes)
+    HttpxFileContent,
+    # (filename, file (or bytes))
+    Tuple[Optional[str], HttpxFileContent],
+    # (filename, file (or bytes), content_type)
+    Tuple[Optional[str], HttpxFileContent, Optional[str]],
+    # (filename, file (or bytes), content_type, headers)
+    Tuple[Optional[str], HttpxFileContent, Optional[str], Mapping[str, str]],
+]
+HttpxRequestFiles = Union[Mapping[str, HttpxFileTypes], Sequence[Tuple[str, HttpxFileTypes]]]
+
+# Workaround to support (cast_to: Type[ResponseT]) -> ResponseT
+# where ResponseT includes `None`. In order to support directly
+# passing `None`, overloads would have to be defined for every
+# method that uses `ResponseT` which would lead to an unacceptable
+# amount of code duplication and make it unreadable. See _base_client.py
+# for example usage.
+#
+# This unfortunately means that you will either have
+# to import this type and pass it explicitly:
+#
+# from groq import NoneType
+# client.get('/foo', cast_to=NoneType)
+#
+# or build it yourself:
+#
+# client.get('/foo', cast_to=type(None))
+if TYPE_CHECKING:
+    NoneType: Type[None]
+else:
+    NoneType = type(None)
+
+
+class RequestOptions(TypedDict, total=False):
+    headers: Headers
+    max_retries: int
+    timeout: float | Timeout | None
+    params: Query
+    extra_json: AnyMapping
+    idempotency_key: str
+    follow_redirects: bool
+
+
+# Sentinel class used until PEP 0661 is accepted
+class NotGiven:
+    """
+    A sentinel singleton class used to distinguish omitted keyword arguments
+    from those passed in with the value None (which may have different behavior).
+
+    For example:
+
+    ```py
+    def get(timeout: Union[int, NotGiven, None] = NotGiven()) -> Response: ...
+
+
+    get(timeout=1)  # 1s timeout
+    get(timeout=None)  # No timeout
+    get()  # Default timeout behavior, which may not be statically known at the method definition.
+    ```
+    """
+
+    def __bool__(self) -> Literal[False]:
+        return False
+
+    @override
+    def __repr__(self) -> str:
+        return "NOT_GIVEN"
+
+
+NotGivenOr = Union[_T, NotGiven]
+NOT_GIVEN = NotGiven()
+
+
+class Omit:
+    """In certain situations you need to be able to represent a case where a default value has
+    to be explicitly removed and `None` is not an appropriate substitute, for example:
+
+    ```py
+    # as the default `Content-Type` header is `application/json` that will be sent
+    client.post("/upload/files", files={"file": b"my raw file content"})
+
+    # you can't explicitly override the header as it has to be dynamically generated
+    # to look something like: 'multipart/form-data; boundary=0d8382fcf5f8c3be01ca2e11002d2983'
+    client.post(..., headers={"Content-Type": "multipart/form-data"})
+
+    # instead you can remove the default `application/json` header by passing Omit
+    client.post(..., headers={"Content-Type": Omit()})
+    ```
+    """
+
+    def __bool__(self) -> Literal[False]:
+        return False
+
+
+@runtime_checkable
+class ModelBuilderProtocol(Protocol):
+    @classmethod
+    def build(
+        cls: type[_T],
+        *,
+        response: Response,
+        data: object,
+    ) -> _T: ...
+
+
+Headers = Mapping[str, Union[str, Omit]]
+
+
+class HeadersLikeProtocol(Protocol):
+    def get(self, __key: str) -> str | None: ...
+
+
+HeadersLike = Union[Headers, HeadersLikeProtocol]
+
+ResponseT = TypeVar(
+    "ResponseT",
+    bound=Union[
+        object,
+        str,
+        None,
+        "BaseModel",
+        List[Any],
+        Dict[str, Any],
+        Response,
+        ModelBuilderProtocol,
+        "APIResponse[Any]",
+        "AsyncAPIResponse[Any]",
+    ],
+)
+
+StrBytesIntFloat = Union[str, bytes, int, float]
+
+# Note: copied from Pydantic
+# https://github.com/pydantic/pydantic/blob/6f31f8f68ef011f84357330186f603ff295312fd/pydantic/main.py#L79
+IncEx: TypeAlias = Union[Set[int], Set[str], Mapping[int, Union["IncEx", bool]], Mapping[str, Union["IncEx", bool]]]
+
+PostParser = Callable[[Any], Any]
+
+
+@runtime_checkable
+class InheritsGeneric(Protocol):
+    """Represents a type that has inherited from `Generic`
+
+    The `__orig_bases__` property can be used to determine the resolved
+    type variable for a given base class.
+    """
+
+    __orig_bases__: tuple[_GenericAlias]
+
+
+class _GenericAlias(Protocol):
+    __origin__: type[object]
+
+
+class HttpxSendArgs(TypedDict, total=False):
+    auth: httpx.Auth
+    follow_redirects: bool

venv/lib/python3.11/site-packages/groq/_utils/__init__.py

@@ -0,0 +1,57 @@
+from ._sync import asyncify as asyncify
+from ._proxy import LazyProxy as LazyProxy
+from ._utils import (
+    flatten as flatten,
+    is_dict as is_dict,
+    is_list as is_list,
+    is_given as is_given,
+    is_tuple as is_tuple,
+    json_safe as json_safe,
+    lru_cache as lru_cache,
+    is_mapping as is_mapping,
+    is_tuple_t as is_tuple_t,
+    parse_date as parse_date,
+    is_iterable as is_iterable,
+    is_sequence as is_sequence,
+    coerce_float as coerce_float,
+    is_mapping_t as is_mapping_t,
+    removeprefix as removeprefix,
+    removesuffix as removesuffix,
+    extract_files as extract_files,
+    is_sequence_t as is_sequence_t,
+    required_args as required_args,
+    coerce_boolean as coerce_boolean,
+    coerce_integer as coerce_integer,
+    file_from_path as file_from_path,
+    parse_datetime as parse_datetime,
+    strip_not_given as strip_not_given,
+    deepcopy_minimal as deepcopy_minimal,
+    get_async_library as get_async_library,
+    maybe_coerce_float as maybe_coerce_float,
+    get_required_header as get_required_header,
+    maybe_coerce_boolean as maybe_coerce_boolean,
+    maybe_coerce_integer as maybe_coerce_integer,
+)
+from ._typing import (
+    is_list_type as is_list_type,
+    is_union_type as is_union_type,
+    extract_type_arg as extract_type_arg,
+    is_iterable_type as is_iterable_type,
+    is_required_type as is_required_type,
+    is_annotated_type as is_annotated_type,
+    is_type_alias_type as is_type_alias_type,
+    strip_annotated_type as strip_annotated_type,
+    extract_type_var_from_base as extract_type_var_from_base,
+)
+from ._streams import consume_sync_iterator as consume_sync_iterator, consume_async_iterator as consume_async_iterator
+from ._transform import (
+    PropertyInfo as PropertyInfo,
+    transform as transform,
+    async_transform as async_transform,
+    maybe_transform as maybe_transform,
+    async_maybe_transform as async_maybe_transform,
+)
+from ._reflection import (
+    function_has_argument as function_has_argument,
+    assert_signatures_in_sync as assert_signatures_in_sync,
+)

venv/lib/python3.11/site-packages/groq/_utils/_logs.py

@@ -0,0 +1,25 @@
+import os
+import logging
+
+logger: logging.Logger = logging.getLogger("groq")
+httpx_logger: logging.Logger = logging.getLogger("httpx")
+
+
+def _basic_config() -> None:
+    # e.g. [2023-10-05 14:12:26 - groq._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",
+    )
+
+
+def setup_logging() -> None:
+    env = os.environ.get("GROQ_LOG")
+    if env == "debug":
+        _basic_config()
+        logger.setLevel(logging.DEBUG)
+        httpx_logger.setLevel(logging.DEBUG)
+    elif env == "info":
+        _basic_config()
+        logger.setLevel(logging.INFO)
+        httpx_logger.setLevel(logging.INFO)

venv/lib/python3.11/site-packages/groq/_utils/_proxy.py

@@ -0,0 +1,65 @@
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+from typing import Generic, TypeVar, Iterable, cast
+from typing_extensions import override
+
+T = TypeVar("T")
+
+
+class LazyProxy(Generic[T], ABC):
+    """Implements data methods to pretend that an instance is another instance.
+
+    This includes forwarding attribute access and other methods.
+    """
+
+    # Note: we have to special case proxies that themselves return proxies
+    # to support using a proxy as a catch-all for any random access, e.g. `proxy.foo.bar.baz`
+
+    def __getattr__(self, attr: str) -> object:
+        proxied = self.__get_proxied__()
+        if isinstance(proxied, LazyProxy):
+            return proxied  # pyright: ignore
+        return getattr(proxied, attr)
+
+    @override
+    def __repr__(self) -> str:
+        proxied = self.__get_proxied__()
+        if isinstance(proxied, LazyProxy):
+            return proxied.__class__.__name__
+        return repr(self.__get_proxied__())
+
+    @override
+    def __str__(self) -> str:
+        proxied = self.__get_proxied__()
+        if isinstance(proxied, LazyProxy):
+            return proxied.__class__.__name__
+        return str(proxied)
+
+    @override
+    def __dir__(self) -> Iterable[str]:
+        proxied = self.__get_proxied__()
+        if isinstance(proxied, LazyProxy):
+            return []
+        return proxied.__dir__()
+
+    @property  # type: ignore
+    @override
+    def __class__(self) -> type:  # pyright: ignore
+        try:
+            proxied = self.__get_proxied__()
+        except Exception:
+            return type(self)
+        if issubclass(type(proxied), LazyProxy):
+            return type(proxied)
+        return proxied.__class__
+
+    def __get_proxied__(self) -> T:
+        return self.__load__()
+
+    def __as_proxied__(self) -> T:
+        """Helper method that returns the current proxy, typed as the loaded object"""
+        return cast(T, self)
+
+    @abstractmethod
+    def __load__(self) -> T: ...

venv/lib/python3.11/site-packages/groq/_utils/_reflection.py

@@ -0,0 +1,42 @@
+from __future__ import annotations
+
+import inspect
+from typing import Any, Callable
+
+
+def function_has_argument(func: Callable[..., Any], arg_name: str) -> bool:
+    """Returns whether or not the given function has a specific parameter"""
+    sig = inspect.signature(func)
+    return arg_name in sig.parameters
+
+
+def assert_signatures_in_sync(
+    source_func: Callable[..., Any],
+    check_func: Callable[..., Any],
+    *,
+    exclude_params: set[str] = set(),
+) -> None:
+    """Ensure that the signature of the second function matches the first."""
+
+    check_sig = inspect.signature(check_func)
+    source_sig = inspect.signature(source_func)
+
+    errors: list[str] = []
+
+    for name, source_param in source_sig.parameters.items():
+        if name in exclude_params:
+            continue
+
+        custom_param = check_sig.parameters.get(name)
+        if not custom_param:
+            errors.append(f"the `{name}` param is missing")
+            continue
+
+        if custom_param.annotation != source_param.annotation:
+            errors.append(
+                f"types for the `{name}` param are do not match; source={repr(source_param.annotation)} checking={repr(custom_param.annotation)}"
+            )
+            continue
+
+    if errors:
+        raise AssertionError(f"{len(errors)} errors encountered when comparing signatures:\n\n" + "\n\n".join(errors))

venv/lib/python3.11/site-packages/groq/_utils/_resources_proxy.py

@@ -0,0 +1,24 @@
+from __future__ import annotations
+
+from typing import Any
+from typing_extensions import override
+
+from ._proxy import LazyProxy
+
+
+class ResourcesProxy(LazyProxy[Any]):
+    """A proxy for the `groq.resources` module.
+
+    This is used so that we can lazily import `groq.resources` only when
+    needed *and* so that users can just import `groq` and reference `groq.resources`
+    """
+
+    @override
+    def __load__(self) -> Any:
+        import importlib
+
+        mod = importlib.import_module("groq.resources")
+        return mod
+
+
+resources = ResourcesProxy().__as_proxied__()

venv/lib/python3.11/site-packages/groq/_utils/_streams.py

@@ -0,0 +1,12 @@
+from typing import Any
+from typing_extensions import Iterator, AsyncIterator
+
+
+def consume_sync_iterator(iterator: Iterator[Any]) -> None:
+    for _ in iterator:
+        ...
+
+
+async def consume_async_iterator(iterator: AsyncIterator[Any]) -> None:
+    async for _ in iterator:
+        ...

venv/lib/python3.11/site-packages/groq/_utils/_sync.py

@@ -0,0 +1,86 @@
+from __future__ import annotations
+
+import sys
+import asyncio
+import functools
+import contextvars
+from typing import Any, TypeVar, Callable, Awaitable
+from typing_extensions import ParamSpec
+
+import anyio
+import sniffio
+import anyio.to_thread
+
+T_Retval = TypeVar("T_Retval")
+T_ParamSpec = ParamSpec("T_ParamSpec")
+
+
+if sys.version_info >= (3, 9):
+    _asyncio_to_thread = asyncio.to_thread
+else:
+    # backport of https://docs.python.org/3/library/asyncio-task.html#asyncio.to_thread
+    # for Python 3.8 support
+    async def _asyncio_to_thread(
+        func: Callable[T_ParamSpec, T_Retval], /, *args: T_ParamSpec.args, **kwargs: T_ParamSpec.kwargs
+    ) -> Any:
+        """Asynchronously run function *func* in a separate thread.
+
+        Any *args and **kwargs supplied for this function are directly passed
+        to *func*. Also, the current :class:`contextvars.Context` is propagated,
+        allowing context variables from the main thread to be accessed in the
+        separate thread.
+
+        Returns a coroutine that can be awaited to get the eventual result of *func*.
+        """
+        loop = asyncio.events.get_running_loop()
+        ctx = contextvars.copy_context()
+        func_call = functools.partial(ctx.run, func, *args, **kwargs)
+        return await loop.run_in_executor(None, func_call)
+
+
+async def to_thread(
+    func: Callable[T_ParamSpec, T_Retval], /, *args: T_ParamSpec.args, **kwargs: T_ParamSpec.kwargs
+) -> T_Retval:
+    if sniffio.current_async_library() == "asyncio":
+        return await _asyncio_to_thread(func, *args, **kwargs)
+
+    return await anyio.to_thread.run_sync(
+        functools.partial(func, *args, **kwargs),
+    )
+
+
+# inspired by `asyncer`, https://github.com/tiangolo/asyncer
+def asyncify(function: Callable[T_ParamSpec, T_Retval]) -> Callable[T_ParamSpec, Awaitable[T_Retval]]:
+    """
+    Take a blocking function and create an async one that receives the same
+    positional and keyword arguments. For python version 3.9 and above, it uses
+    asyncio.to_thread to run the function in a separate thread. For python version
+    3.8, it uses locally defined copy of the asyncio.to_thread function which was
+    introduced in python 3.9.
+
+    Usage:
+
+    ```python
+    def blocking_func(arg1, arg2, kwarg1=None):
+        # blocking code
+        return result
+
+
+    result = asyncify(blocking_function)(arg1, arg2, kwarg1=value1)
+    ```
+
+    ## Arguments
+
+    `function`: a blocking regular callable (e.g. a function)
+
+    ## Return
+
+    An async function that takes the same positional and keyword arguments as the
+    original one, that when called runs the same original function in a thread worker
+    and returns the result.
+    """
+
+    async def wrapper(*args: T_ParamSpec.args, **kwargs: T_ParamSpec.kwargs) -> T_Retval:
+        return await to_thread(function, *args, **kwargs)
+
+    return wrapper

venv/lib/python3.11/site-packages/groq/_utils/_transform.py

@@ -0,0 +1,447 @@
+from __future__ import annotations
+
+import io
+import base64
+import pathlib
+from typing import Any, Mapping, TypeVar, cast
+from datetime import date, datetime
+from typing_extensions import Literal, get_args, override, get_type_hints as _get_type_hints
+
+import anyio
+import pydantic
+
+from ._utils import (
+    is_list,
+    is_given,
+    lru_cache,
+    is_mapping,
+    is_iterable,
+)
+from .._files import is_base64_file_input
+from ._typing import (
+    is_list_type,
+    is_union_type,
+    extract_type_arg,
+    is_iterable_type,
+    is_required_type,
+    is_annotated_type,
+    strip_annotated_type,
+)
+from .._compat import get_origin, model_dump, is_typeddict
+
+_T = TypeVar("_T")
+
+
+# TODO: support for drilling globals() and locals()
+# TODO: ensure works correctly with forward references in all cases
+
+
+PropertyFormat = Literal["iso8601", "base64", "custom"]
+
+
+class PropertyInfo:
+    """Metadata class to be used in Annotated types to provide information about a given type.
+
+    For example:
+
+    class MyParams(TypedDict):
+        account_holder_name: Annotated[str, PropertyInfo(alias='accountHolderName')]
+
+    This means that {'account_holder_name': 'Robert'} will be transformed to {'accountHolderName': 'Robert'} before being sent to the API.
+    """
+
+    alias: str | None
+    format: PropertyFormat | None
+    format_template: str | None
+    discriminator: str | None
+
+    def __init__(
+        self,
+        *,
+        alias: str | None = None,
+        format: PropertyFormat | None = None,
+        format_template: str | None = None,
+        discriminator: str | None = None,
+    ) -> None:
+        self.alias = alias
+        self.format = format
+        self.format_template = format_template
+        self.discriminator = discriminator
+
+    @override
+    def __repr__(self) -> str:
+        return f"{self.__class__.__name__}(alias='{self.alias}', format={self.format}, format_template='{self.format_template}', discriminator='{self.discriminator}')"
+
+
+def maybe_transform(
+    data: object,
+    expected_type: object,
+) -> Any | None:
+    """Wrapper over `transform()` that allows `None` to be passed.
+
+    See `transform()` for more details.
+    """
+    if data is None:
+        return None
+    return transform(data, expected_type)
+
+
+# Wrapper over _transform_recursive providing fake types
+def transform(
+    data: _T,
+    expected_type: object,
+) -> _T:
+    """Transform dictionaries based off of type information from the given type, for example:
+
+    ```py
+    class Params(TypedDict, total=False):
+        card_id: Required[Annotated[str, PropertyInfo(alias="cardID")]]
+
+
+    transformed = transform({"card_id": "<my card ID>"}, Params)
+    # {'cardID': '<my card ID>'}
+    ```
+
+    Any keys / data that does not have type information given will be included as is.
+
+    It should be noted that the transformations that this function does are not represented in the type system.
+    """
+    transformed = _transform_recursive(data, annotation=cast(type, expected_type))
+    return cast(_T, transformed)
+
+
+@lru_cache(maxsize=8096)
+def _get_annotated_type(type_: type) -> type | None:
+    """If the given type is an `Annotated` type then it is returned, if not `None` is returned.
+
+    This also unwraps the type when applicable, e.g. `Required[Annotated[T, ...]]`
+    """
+    if is_required_type(type_):
+        # Unwrap `Required[Annotated[T, ...]]` to `Annotated[T, ...]`
+        type_ = get_args(type_)[0]
+
+    if is_annotated_type(type_):
+        return type_
+
+    return None
+
+
+def _maybe_transform_key(key: str, type_: type) -> str:
+    """Transform the given `data` based on the annotations provided in `type_`.
+
+    Note: this function only looks at `Annotated` types that contain `PropertyInfo` metadata.
+    """
+    annotated_type = _get_annotated_type(type_)
+    if annotated_type is None:
+        # no `Annotated` definition for this type, no transformation needed
+        return key
+
+    # ignore the first argument as it is the actual type
+    annotations = get_args(annotated_type)[1:]
+    for annotation in annotations:
+        if isinstance(annotation, PropertyInfo) and annotation.alias is not None:
+            return annotation.alias
+
+    return key
+
+
+def _no_transform_needed(annotation: type) -> bool:
+    return annotation == float or annotation == int
+
+
+def _transform_recursive(
+    data: object,
+    *,
+    annotation: type,
+    inner_type: type | None = None,
+) -> object:
+    """Transform the given data against the expected type.
+
+    Args:
+        annotation: The direct type annotation given to the particular piece of data.
+            This may or may not be wrapped in metadata types, e.g. `Required[T]`, `Annotated[T, ...]` etc
+
+        inner_type: If applicable, this is the "inside" type. This is useful in certain cases where the outside type
+            is a container type such as `List[T]`. In that case `inner_type` should be set to `T` so that each entry in
+            the list can be transformed using the metadata from the container type.
+
+            Defaults to the same value as the `annotation` argument.
+    """
+    if inner_type is None:
+        inner_type = annotation
+
+    stripped_type = strip_annotated_type(inner_type)
+    origin = get_origin(stripped_type) or stripped_type
+    if is_typeddict(stripped_type) and is_mapping(data):
+        return _transform_typeddict(data, stripped_type)
+
+    if origin == dict and is_mapping(data):
+        items_type = get_args(stripped_type)[1]
+        return {key: _transform_recursive(value, annotation=items_type) for key, value in data.items()}
+
+    if (
+        # List[T]
+        (is_list_type(stripped_type) and is_list(data))
+        # Iterable[T]
+        or (is_iterable_type(stripped_type) and is_iterable(data) and not isinstance(data, str))
+    ):
+        # dicts are technically iterable, but it is an iterable on the keys of the dict and is not usually
+        # intended as an iterable, so we don't transform it.
+        if isinstance(data, dict):
+            return cast(object, data)
+
+        inner_type = extract_type_arg(stripped_type, 0)
+        if _no_transform_needed(inner_type):
+            # for some types there is no need to transform anything, so we can get a small
+            # perf boost from skipping that work.
+            #
+            # but we still need to convert to a list to ensure the data is json-serializable
+            if is_list(data):
+                return data
+            return list(data)
+
+        return [_transform_recursive(d, annotation=annotation, inner_type=inner_type) for d in data]
+
+    if is_union_type(stripped_type):
+        # For union types we run the transformation against all subtypes to ensure that everything is transformed.
+        #
+        # TODO: there may be edge cases where the same normalized field name will transform to two different names
+        # in different subtypes.
+        for subtype in get_args(stripped_type):
+            data = _transform_recursive(data, annotation=annotation, inner_type=subtype)
+        return data
+
+    if isinstance(data, pydantic.BaseModel):
+        return model_dump(data, exclude_unset=True, mode="json")
+
+    annotated_type = _get_annotated_type(annotation)
+    if annotated_type is None:
+        return data
+
+    # ignore the first argument as it is the actual type
+    annotations = get_args(annotated_type)[1:]
+    for annotation in annotations:
+        if isinstance(annotation, PropertyInfo) and annotation.format is not None:
+            return _format_data(data, annotation.format, annotation.format_template)
+
+    return data
+
+
+def _format_data(data: object, format_: PropertyFormat, format_template: str | None) -> object:
+    if isinstance(data, (date, datetime)):
+        if format_ == "iso8601":
+            return data.isoformat()
+
+        if format_ == "custom" and format_template is not None:
+            return data.strftime(format_template)
+
+    if format_ == "base64" and is_base64_file_input(data):
+        binary: str | bytes | None = None
+
+        if isinstance(data, pathlib.Path):
+            binary = data.read_bytes()
+        elif isinstance(data, io.IOBase):
+            binary = data.read()
+
+            if isinstance(binary, str):  # type: ignore[unreachable]
+                binary = binary.encode()
+
+        if not isinstance(binary, bytes):
+            raise RuntimeError(f"Could not read bytes from {data}; Received {type(binary)}")
+
+        return base64.b64encode(binary).decode("ascii")
+
+    return data
+
+
+def _transform_typeddict(
+    data: Mapping[str, object],
+    expected_type: type,
+) -> Mapping[str, object]:
+    result: dict[str, object] = {}
+    annotations = get_type_hints(expected_type, include_extras=True)
+    for key, value in data.items():
+        if not is_given(value):
+            # we don't need to include `NotGiven` values here as they'll
+            # be stripped out before the request is sent anyway
+            continue
+
+        type_ = annotations.get(key)
+        if type_ is None:
+            # we do not have a type annotation for this field, leave it as is
+            result[key] = value
+        else:
+            result[_maybe_transform_key(key, type_)] = _transform_recursive(value, annotation=type_)
+    return result
+
+
+async def async_maybe_transform(
+    data: object,
+    expected_type: object,
+) -> Any | None:
+    """Wrapper over `async_transform()` that allows `None` to be passed.
+
+    See `async_transform()` for more details.
+    """
+    if data is None:
+        return None
+    return await async_transform(data, expected_type)
+
+
+async def async_transform(
+    data: _T,
+    expected_type: object,
+) -> _T:
+    """Transform dictionaries based off of type information from the given type, for example:
+
+    ```py
+    class Params(TypedDict, total=False):
+        card_id: Required[Annotated[str, PropertyInfo(alias="cardID")]]
+
+
+    transformed = transform({"card_id": "<my card ID>"}, Params)
+    # {'cardID': '<my card ID>'}
+    ```
+
+    Any keys / data that does not have type information given will be included as is.
+
+    It should be noted that the transformations that this function does are not represented in the type system.
+    """
+    transformed = await _async_transform_recursive(data, annotation=cast(type, expected_type))
+    return cast(_T, transformed)
+
+
+async def _async_transform_recursive(
+    data: object,
+    *,
+    annotation: type,
+    inner_type: type | None = None,
+) -> object:
+    """Transform the given data against the expected type.
+
+    Args:
+        annotation: The direct type annotation given to the particular piece of data.
+            This may or may not be wrapped in metadata types, e.g. `Required[T]`, `Annotated[T, ...]` etc
+
+        inner_type: If applicable, this is the "inside" type. This is useful in certain cases where the outside type
+            is a container type such as `List[T]`. In that case `inner_type` should be set to `T` so that each entry in
+            the list can be transformed using the metadata from the container type.
+
+            Defaults to the same value as the `annotation` argument.
+    """
+    if inner_type is None:
+        inner_type = annotation
+
+    stripped_type = strip_annotated_type(inner_type)
+    origin = get_origin(stripped_type) or stripped_type
+    if is_typeddict(stripped_type) and is_mapping(data):
+        return await _async_transform_typeddict(data, stripped_type)
+
+    if origin == dict and is_mapping(data):
+        items_type = get_args(stripped_type)[1]
+        return {key: _transform_recursive(value, annotation=items_type) for key, value in data.items()}
+
+    if (
+        # List[T]
+        (is_list_type(stripped_type) and is_list(data))
+        # Iterable[T]
+        or (is_iterable_type(stripped_type) and is_iterable(data) and not isinstance(data, str))
+    ):
+        # dicts are technically iterable, but it is an iterable on the keys of the dict and is not usually
+        # intended as an iterable, so we don't transform it.
+        if isinstance(data, dict):
+            return cast(object, data)
+
+        inner_type = extract_type_arg(stripped_type, 0)
+        if _no_transform_needed(inner_type):
+            # for some types there is no need to transform anything, so we can get a small
+            # perf boost from skipping that work.
+            #
+            # but we still need to convert to a list to ensure the data is json-serializable
+            if is_list(data):
+                return data
+            return list(data)
+
+        return [await _async_transform_recursive(d, annotation=annotation, inner_type=inner_type) for d in data]
+
+    if is_union_type(stripped_type):
+        # For union types we run the transformation against all subtypes to ensure that everything is transformed.
+        #
+        # TODO: there may be edge cases where the same normalized field name will transform to two different names
+        # in different subtypes.
+        for subtype in get_args(stripped_type):
+            data = await _async_transform_recursive(data, annotation=annotation, inner_type=subtype)
+        return data
+
+    if isinstance(data, pydantic.BaseModel):
+        return model_dump(data, exclude_unset=True, mode="json")
+
+    annotated_type = _get_annotated_type(annotation)
+    if annotated_type is None:
+        return data
+
+    # ignore the first argument as it is the actual type
+    annotations = get_args(annotated_type)[1:]
+    for annotation in annotations:
+        if isinstance(annotation, PropertyInfo) and annotation.format is not None:
+            return await _async_format_data(data, annotation.format, annotation.format_template)
+
+    return data
+
+
+async def _async_format_data(data: object, format_: PropertyFormat, format_template: str | None) -> object:
+    if isinstance(data, (date, datetime)):
+        if format_ == "iso8601":
+            return data.isoformat()
+
+        if format_ == "custom" and format_template is not None:
+            return data.strftime(format_template)
+
+    if format_ == "base64" and is_base64_file_input(data):
+        binary: str | bytes | None = None
+
+        if isinstance(data, pathlib.Path):
+            binary = await anyio.Path(data).read_bytes()
+        elif isinstance(data, io.IOBase):
+            binary = data.read()
+
+            if isinstance(binary, str):  # type: ignore[unreachable]
+                binary = binary.encode()
+
+        if not isinstance(binary, bytes):
+            raise RuntimeError(f"Could not read bytes from {data}; Received {type(binary)}")
+
+        return base64.b64encode(binary).decode("ascii")
+
+    return data
+
+
+async def _async_transform_typeddict(
+    data: Mapping[str, object],
+    expected_type: type,
+) -> Mapping[str, object]:
+    result: dict[str, object] = {}
+    annotations = get_type_hints(expected_type, include_extras=True)
+    for key, value in data.items():
+        if not is_given(value):
+            # we don't need to include `NotGiven` values here as they'll
+            # be stripped out before the request is sent anyway
+            continue
+
+        type_ = annotations.get(key)
+        if type_ is None:
+            # we do not have a type annotation for this field, leave it as is
+            result[key] = value
+        else:
+            result[_maybe_transform_key(key, type_)] = await _async_transform_recursive(value, annotation=type_)
+    return result
+
+
+@lru_cache(maxsize=8096)
+def get_type_hints(
+    obj: Any,
+    globalns: dict[str, Any] | None = None,
+    localns: Mapping[str, Any] | None = None,
+    include_extras: bool = False,
+) -> dict[str, Any]:
+    return _get_type_hints(obj, globalns=globalns, localns=localns, include_extras=include_extras)

venv/lib/python3.11/site-packages/groq/_utils/_typing.py

@@ -0,0 +1,151 @@
+from __future__ import annotations
+
+import sys
+import typing
+import typing_extensions
+from typing import Any, TypeVar, Iterable, cast
+from collections import abc as _c_abc
+from typing_extensions import (
+    TypeIs,
+    Required,
+    Annotated,
+    get_args,
+    get_origin,
+)
+
+from ._utils import lru_cache
+from .._types import InheritsGeneric
+from .._compat import is_union as _is_union
+
+
+def is_annotated_type(typ: type) -> bool:
+    return get_origin(typ) == Annotated
+
+
+def is_list_type(typ: type) -> bool:
+    return (get_origin(typ) or typ) == list
+
+
+def is_iterable_type(typ: type) -> bool:
+    """If the given type is `typing.Iterable[T]`"""
+    origin = get_origin(typ) or typ
+    return origin == Iterable or origin == _c_abc.Iterable
+
+
+def is_union_type(typ: type) -> bool:
+    return _is_union(get_origin(typ))
+
+
+def is_required_type(typ: type) -> bool:
+    return get_origin(typ) == Required
+
+
+def is_typevar(typ: type) -> bool:
+    # type ignore is required because type checkers
+    # think this expression will always return False
+    return type(typ) == TypeVar  # type: ignore
+
+
+_TYPE_ALIAS_TYPES: tuple[type[typing_extensions.TypeAliasType], ...] = (typing_extensions.TypeAliasType,)
+if sys.version_info >= (3, 12):
+    _TYPE_ALIAS_TYPES = (*_TYPE_ALIAS_TYPES, typing.TypeAliasType)
+
+
+def is_type_alias_type(tp: Any, /) -> TypeIs[typing_extensions.TypeAliasType]:
+    """Return whether the provided argument is an instance of `TypeAliasType`.
+
+    ```python
+    type Int = int
+    is_type_alias_type(Int)
+    # > True
+    Str = TypeAliasType("Str", str)
+    is_type_alias_type(Str)
+    # > True
+    ```
+    """
+    return isinstance(tp, _TYPE_ALIAS_TYPES)
+
+
+# Extracts T from Annotated[T, ...] or from Required[Annotated[T, ...]]
+@lru_cache(maxsize=8096)
+def strip_annotated_type(typ: type) -> type:
+    if is_required_type(typ) or is_annotated_type(typ):
+        return strip_annotated_type(cast(type, get_args(typ)[0]))
+
+    return typ
+
+
+def extract_type_arg(typ: type, index: int) -> type:
+    args = get_args(typ)
+    try:
+        return cast(type, args[index])
+    except IndexError as err:
+        raise RuntimeError(f"Expected type {typ} to have a type argument at index {index} but it did not") from err
+
+
+def extract_type_var_from_base(
+    typ: type,
+    *,
+    generic_bases: tuple[type, ...],
+    index: int,
+    failure_message: str | None = None,
+) -> type:
+    """Given a type like `Foo[T]`, returns the generic type variable `T`.
+
+    This also handles the case where a concrete subclass is given, e.g.
+    ```py
+    class MyResponse(Foo[bytes]):
+        ...
+
+    extract_type_var(MyResponse, bases=(Foo,), index=0) -> bytes
+    ```
+
+    And where a generic subclass is given:
+    ```py
+    _T = TypeVar('_T')
+    class MyResponse(Foo[_T]):
+        ...
+
+    extract_type_var(MyResponse[bytes], bases=(Foo,), index=0) -> bytes
+    ```
+    """
+    cls = cast(object, get_origin(typ) or typ)
+    if cls in generic_bases:  # pyright: ignore[reportUnnecessaryContains]
+        # we're given the class directly
+        return extract_type_arg(typ, index)
+
+    # if a subclass is given
+    # ---
+    # this is needed as __orig_bases__ is not present in the typeshed stubs
+    # because it is intended to be for internal use only, however there does
+    # not seem to be a way to resolve generic TypeVars for inherited subclasses
+    # without using it.
+    if isinstance(cls, InheritsGeneric):
+        target_base_class: Any | None = None
+        for base in cls.__orig_bases__:
+            if base.__origin__ in generic_bases:
+                target_base_class = base
+                break
+
+        if target_base_class is None:
+            raise RuntimeError(
+                "Could not find the generic base class;\n"
+                "This should never happen;\n"
+                f"Does {cls} inherit from one of {generic_bases} ?"
+            )
+
+        extracted = extract_type_arg(target_base_class, index)
+        if is_typevar(extracted):
+            # If the extracted type argument is itself a type variable
+            # then that means the subclass itself is generic, so we have
+            # to resolve the type argument from the class itself, not
+            # the base class.
+            #
+            # Note: if there is more than 1 type argument, the subclass could
+            # change the ordering of the type arguments, this is not currently
+            # supported.
+            return extract_type_arg(typ, index)
+
+        return extracted
+
+    raise RuntimeError(failure_message or f"Could not resolve inner type variable at index {index} for {typ}")

venv/lib/python3.11/site-packages/groq/_utils/_utils.py

@@ -0,0 +1,422 @@
+from __future__ import annotations
+
+import os
+import re
+import inspect
+import functools
+from typing import (
+    Any,
+    Tuple,
+    Mapping,
+    TypeVar,
+    Callable,
+    Iterable,
+    Sequence,
+    cast,
+    overload,
+)
+from pathlib import Path
+from datetime import date, datetime
+from typing_extensions import TypeGuard
+
+import sniffio
+
+from .._types import NotGiven, FileTypes, NotGivenOr, HeadersLike
+from .._compat import parse_date as parse_date, parse_datetime as parse_datetime
+
+_T = TypeVar("_T")
+_TupleT = TypeVar("_TupleT", bound=Tuple[object, ...])
+_MappingT = TypeVar("_MappingT", bound=Mapping[str, object])
+_SequenceT = TypeVar("_SequenceT", bound=Sequence[object])
+CallableT = TypeVar("CallableT", bound=Callable[..., Any])
+
+
+def flatten(t: Iterable[Iterable[_T]]) -> list[_T]:
+    return [item for sublist in t for item in sublist]
+
+
+def extract_files(
+    # TODO: this needs to take Dict but variance issues.....
+    # create protocol type ?
+    query: Mapping[str, object],
+    *,
+    paths: Sequence[Sequence[str]],
+) -> list[tuple[str, FileTypes]]:
+    """Recursively extract files from the given dictionary based on specified paths.
+
+    A path may look like this ['foo', 'files', '<array>', 'data'].
+
+    Note: this mutates the given dictionary.
+    """
+    files: list[tuple[str, FileTypes]] = []
+    for path in paths:
+        files.extend(_extract_items(query, path, index=0, flattened_key=None))
+    return files
+
+
+def _extract_items(
+    obj: object,
+    path: Sequence[str],
+    *,
+    index: int,
+    flattened_key: str | None,
+) -> list[tuple[str, FileTypes]]:
+    try:
+        key = path[index]
+    except IndexError:
+        if isinstance(obj, NotGiven):
+            # no value was provided - we can safely ignore
+            return []
+
+        # cyclical import
+        from .._files import assert_is_file_content
+
+        # We have exhausted the path, return the entry we found.
+        assert flattened_key is not None
+
+        if is_list(obj):
+            files: list[tuple[str, FileTypes]] = []
+            for entry in obj:
+                assert_is_file_content(entry, key=flattened_key + "[]" if flattened_key else "")
+                files.append((flattened_key + "[]", cast(FileTypes, entry)))
+            return files
+
+        assert_is_file_content(obj, key=flattened_key)
+        return [(flattened_key, cast(FileTypes, obj))]
+
+    index += 1
+    if is_dict(obj):
+        try:
+            # We are at the last entry in the path so we must remove the field
+            if (len(path)) == index:
+                item = obj.pop(key)
+            else:
+                item = obj[key]
+        except KeyError:
+            # Key was not present in the dictionary, this is not indicative of an error
+            # as the given path may not point to a required field. We also do not want
+            # to enforce required fields as the API may differ from the spec in some cases.
+            return []
+        if flattened_key is None:
+            flattened_key = key
+        else:
+            flattened_key += f"[{key}]"
+        return _extract_items(
+            item,
+            path,
+            index=index,
+            flattened_key=flattened_key,
+        )
+    elif is_list(obj):
+        if key != "<array>":
+            return []
+
+        return flatten(
+            [
+                _extract_items(
+                    item,
+                    path,
+                    index=index,
+                    flattened_key=flattened_key + "[]" if flattened_key is not None else "[]",
+                )
+                for item in obj
+            ]
+        )
+
+    # Something unexpected was passed, just ignore it.
+    return []
+
+
+def is_given(obj: NotGivenOr[_T]) -> TypeGuard[_T]:
+    return not isinstance(obj, NotGiven)
+
+
+# Type safe methods for narrowing types with TypeVars.
+# The default narrowing for isinstance(obj, dict) is dict[unknown, unknown],
+# however this cause Pyright to rightfully report errors. As we know we don't
+# care about the contained types we can safely use `object` in it's place.
+#
+# There are two separate functions defined, `is_*` and `is_*_t` for different use cases.
+# `is_*` is for when you're dealing with an unknown input
+# `is_*_t` is for when you're narrowing a known union type to a specific subset
+
+
+def is_tuple(obj: object) -> TypeGuard[tuple[object, ...]]:
+    return isinstance(obj, tuple)
+
+
+def is_tuple_t(obj: _TupleT | object) -> TypeGuard[_TupleT]:
+    return isinstance(obj, tuple)
+
+
+def is_sequence(obj: object) -> TypeGuard[Sequence[object]]:
+    return isinstance(obj, Sequence)
+
+
+def is_sequence_t(obj: _SequenceT | object) -> TypeGuard[_SequenceT]:
+    return isinstance(obj, Sequence)
+
+
+def is_mapping(obj: object) -> TypeGuard[Mapping[str, object]]:
+    return isinstance(obj, Mapping)
+
+
+def is_mapping_t(obj: _MappingT | object) -> TypeGuard[_MappingT]:
+    return isinstance(obj, Mapping)
+
+
+def is_dict(obj: object) -> TypeGuard[dict[object, object]]:
+    return isinstance(obj, dict)
+
+
+def is_list(obj: object) -> TypeGuard[list[object]]:
+    return isinstance(obj, list)
+
+
+def is_iterable(obj: object) -> TypeGuard[Iterable[object]]:
+    return isinstance(obj, Iterable)
+
+
+def deepcopy_minimal(item: _T) -> _T:
+    """Minimal reimplementation of copy.deepcopy() that will only copy certain object types:
+
+    - mappings, e.g. `dict`
+    - list
+
+    This is done for performance reasons.
+    """
+    if is_mapping(item):
+        return cast(_T, {k: deepcopy_minimal(v) for k, v in item.items()})
+    if is_list(item):
+        return cast(_T, [deepcopy_minimal(entry) for entry in item])
+    return item
+
+
+# copied from https://github.com/Rapptz/RoboDanny
+def human_join(seq: Sequence[str], *, delim: str = ", ", final: str = "or") -> str:
+    size = len(seq)
+    if size == 0:
+        return ""
+
+    if size == 1:
+        return seq[0]
+
+    if size == 2:
+        return f"{seq[0]} {final} {seq[1]}"
+
+    return delim.join(seq[:-1]) + f" {final} {seq[-1]}"
+
+
+def quote(string: str) -> str:
+    """Add single quotation marks around the given string. Does *not* do any escaping."""
+    return f"'{string}'"
+
+
+def required_args(*variants: Sequence[str]) -> Callable[[CallableT], CallableT]:
+    """Decorator to enforce a given set of arguments or variants of arguments are passed to the decorated function.
+
+    Useful for enforcing runtime validation of overloaded functions.
+
+    Example usage:
+    ```py
+    @overload
+    def foo(*, a: str) -> str: ...
+
+
+    @overload
+    def foo(*, b: bool) -> str: ...
+
+
+    # This enforces the same constraints that a static type checker would
+    # i.e. that either a or b must be passed to the function
+    @required_args(["a"], ["b"])
+    def foo(*, a: str | None = None, b: bool | None = None) -> str: ...
+    ```
+    """
+
+    def inner(func: CallableT) -> CallableT:
+        params = inspect.signature(func).parameters
+        positional = [
+            name
+            for name, param in params.items()
+            if param.kind
+            in {
+                param.POSITIONAL_ONLY,
+                param.POSITIONAL_OR_KEYWORD,
+            }
+        ]
+
+        @functools.wraps(func)
+        def wrapper(*args: object, **kwargs: object) -> object:
+            given_params: set[str] = set()
+            for i, _ in enumerate(args):
+                try:
+                    given_params.add(positional[i])
+                except IndexError:
+                    raise TypeError(
+                        f"{func.__name__}() takes {len(positional)} argument(s) but {len(args)} were given"
+                    ) from None
+
+            for key in kwargs.keys():
+                given_params.add(key)
+
+            for variant in variants:
+                matches = all((param in given_params for param in variant))
+                if matches:
+                    break
+            else:  # no break
+                if len(variants) > 1:
+                    variations = human_join(
+                        ["(" + human_join([quote(arg) for arg in variant], final="and") + ")" for variant in variants]
+                    )
+                    msg = f"Missing required arguments; Expected either {variations} arguments to be given"
+                else:
+                    assert len(variants) > 0
+
+                    # TODO: this error message is not deterministic
+                    missing = list(set(variants[0]) - given_params)
+                    if len(missing) > 1:
+                        msg = f"Missing required arguments: {human_join([quote(arg) for arg in missing])}"
+                    else:
+                        msg = f"Missing required argument: {quote(missing[0])}"
+                raise TypeError(msg)
+            return func(*args, **kwargs)
+
+        return wrapper  # type: ignore
+
+    return inner
+
+
+_K = TypeVar("_K")
+_V = TypeVar("_V")
+
+
+@overload
+def strip_not_given(obj: None) -> None: ...
+
+
+@overload
+def strip_not_given(obj: Mapping[_K, _V | NotGiven]) -> dict[_K, _V]: ...
+
+
+@overload
+def strip_not_given(obj: object) -> object: ...
+
+
+def strip_not_given(obj: object | None) -> object:
+    """Remove all top-level keys where their values are instances of `NotGiven`"""
+    if obj is None:
+        return None
+
+    if not is_mapping(obj):
+        return obj
+
+    return {key: value for key, value in obj.items() if not isinstance(value, NotGiven)}
+
+
+def coerce_integer(val: str) -> int:
+    return int(val, base=10)
+
+
+def coerce_float(val: str) -> float:
+    return float(val)
+
+
+def coerce_boolean(val: str) -> bool:
+    return val == "true" or val == "1" or val == "on"
+
+
+def maybe_coerce_integer(val: str | None) -> int | None:
+    if val is None:
+        return None
+    return coerce_integer(val)
+
+
+def maybe_coerce_float(val: str | None) -> float | None:
+    if val is None:
+        return None
+    return coerce_float(val)
+
+
+def maybe_coerce_boolean(val: str | None) -> bool | None:
+    if val is None:
+        return None
+    return coerce_boolean(val)
+
+
+def removeprefix(string: str, prefix: str) -> str:
+    """Remove a prefix from a string.
+
+    Backport of `str.removeprefix` for Python < 3.9
+    """
+    if string.startswith(prefix):
+        return string[len(prefix) :]
+    return string
+
+
+def removesuffix(string: str, suffix: str) -> str:
+    """Remove a suffix from a string.
+
+    Backport of `str.removesuffix` for Python < 3.9
+    """
+    if string.endswith(suffix):
+        return string[: -len(suffix)]
+    return string
+
+
+def file_from_path(path: str) -> FileTypes:
+    contents = Path(path).read_bytes()
+    file_name = os.path.basename(path)
+    return (file_name, contents)
+
+
+def get_required_header(headers: HeadersLike, header: str) -> str:
+    lower_header = header.lower()
+    if is_mapping_t(headers):
+        # mypy doesn't understand the type narrowing here
+        for k, v in headers.items():  # type: ignore
+            if k.lower() == lower_header and isinstance(v, str):
+                return v
+
+    # to deal with the case where the header looks like Stainless-Event-Id
+    intercaps_header = re.sub(r"([^\w])(\w)", lambda pat: pat.group(1) + pat.group(2).upper(), header.capitalize())
+
+    for normalized_header in [header, lower_header, header.upper(), intercaps_header]:
+        value = headers.get(normalized_header)
+        if value:
+            return value
+
+    raise ValueError(f"Could not find {header} header")
+
+
+def get_async_library() -> str:
+    try:
+        return sniffio.current_async_library()
+    except Exception:
+        return "false"
+
+
+def lru_cache(*, maxsize: int | None = 128) -> Callable[[CallableT], CallableT]:
+    """A version of functools.lru_cache that retains the type signature
+    for the wrapped function arguments.
+    """
+    wrapper = functools.lru_cache(  # noqa: TID251
+        maxsize=maxsize,
+    )
+    return cast(Any, wrapper)  # type: ignore[no-any-return]
+
+
+def json_safe(data: object) -> object:
+    """Translates a mapping / sequence recursively in the same fashion
+    as `pydantic` v2's `model_dump(mode="json")`.
+    """
+    if is_mapping(data):
+        return {json_safe(key): json_safe(value) for key, value in data.items()}
+
+    if is_iterable(data) and not isinstance(data, (str, bytes, bytearray)):
+        return [json_safe(item) for item in data]
+
+    if isinstance(data, (datetime, date)):
+        return data.isoformat()
+
+    return data

venv/lib/python3.11/site-packages/groq/_version.py

@@ -0,0 +1,4 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+__title__ = "groq"
+__version__ = "0.30.0"  # x-release-please-version

venv/lib/python3.11/site-packages/groq/lib/.keep

@@ -0,0 +1,4 @@
+File generated from our OpenAPI spec by Stainless.
+
+This directory can be used to store custom files to expand the SDK.
+It is ignored by Stainless code generation and its content (other than this keep file) won't be touched.

venv/lib/python3.11/site-packages/groq/resources/__init__.py

@@ -0,0 +1,89 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from .chat import (
+    Chat,
+    AsyncChat,
+    ChatWithRawResponse,
+    AsyncChatWithRawResponse,
+    ChatWithStreamingResponse,
+    AsyncChatWithStreamingResponse,
+)
+from .audio import (
+    Audio,
+    AsyncAudio,
+    AudioWithRawResponse,
+    AsyncAudioWithRawResponse,
+    AudioWithStreamingResponse,
+    AsyncAudioWithStreamingResponse,
+)
+from .files import (
+    Files,
+    AsyncFiles,
+    FilesWithRawResponse,
+    AsyncFilesWithRawResponse,
+    FilesWithStreamingResponse,
+    AsyncFilesWithStreamingResponse,
+)
+from .models import (
+    Models,
+    AsyncModels,
+    ModelsWithRawResponse,
+    AsyncModelsWithRawResponse,
+    ModelsWithStreamingResponse,
+    AsyncModelsWithStreamingResponse,
+)
+from .batches import (
+    Batches,
+    AsyncBatches,
+    BatchesWithRawResponse,
+    AsyncBatchesWithRawResponse,
+    BatchesWithStreamingResponse,
+    AsyncBatchesWithStreamingResponse,
+)
+from .embeddings import (
+    Embeddings,
+    AsyncEmbeddings,
+    EmbeddingsWithRawResponse,
+    AsyncEmbeddingsWithRawResponse,
+    EmbeddingsWithStreamingResponse,
+    AsyncEmbeddingsWithStreamingResponse,
+)
+
+__all__ = [
+    "Chat",
+    "AsyncChat",
+    "ChatWithRawResponse",
+    "AsyncChatWithRawResponse",
+    "ChatWithStreamingResponse",
+    "AsyncChatWithStreamingResponse",
+    "Embeddings",
+    "AsyncEmbeddings",
+    "EmbeddingsWithRawResponse",
+    "AsyncEmbeddingsWithRawResponse",
+    "EmbeddingsWithStreamingResponse",
+    "AsyncEmbeddingsWithStreamingResponse",
+    "Audio",
+    "AsyncAudio",
+    "AudioWithRawResponse",
+    "AsyncAudioWithRawResponse",
+    "AudioWithStreamingResponse",
+    "AsyncAudioWithStreamingResponse",
+    "Models",
+    "AsyncModels",
+    "ModelsWithRawResponse",
+    "AsyncModelsWithRawResponse",
+    "ModelsWithStreamingResponse",
+    "AsyncModelsWithStreamingResponse",
+    "Batches",
+    "AsyncBatches",
+    "BatchesWithRawResponse",
+    "AsyncBatchesWithRawResponse",
+    "BatchesWithStreamingResponse",
+    "AsyncBatchesWithStreamingResponse",
+    "Files",
+    "AsyncFiles",
+    "FilesWithRawResponse",
+    "AsyncFilesWithRawResponse",
+    "FilesWithStreamingResponse",
+    "AsyncFilesWithStreamingResponse",
+]

venv/lib/python3.11/site-packages/groq/resources/audio/__init__.py

@@ -0,0 +1,61 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from .audio import (
+    Audio,
+    AsyncAudio,
+    AudioWithRawResponse,
+    AsyncAudioWithRawResponse,
+    AudioWithStreamingResponse,
+    AsyncAudioWithStreamingResponse,
+)
+from .speech import (
+    Speech,
+    AsyncSpeech,
+    SpeechWithRawResponse,
+    AsyncSpeechWithRawResponse,
+    SpeechWithStreamingResponse,
+    AsyncSpeechWithStreamingResponse,
+)
+from .translations import (
+    Translations,
+    AsyncTranslations,
+    TranslationsWithRawResponse,
+    AsyncTranslationsWithRawResponse,
+    TranslationsWithStreamingResponse,
+    AsyncTranslationsWithStreamingResponse,
+)
+from .transcriptions import (
+    Transcriptions,
+    AsyncTranscriptions,
+    TranscriptionsWithRawResponse,
+    AsyncTranscriptionsWithRawResponse,
+    TranscriptionsWithStreamingResponse,
+    AsyncTranscriptionsWithStreamingResponse,
+)
+
+__all__ = [
+    "Speech",
+    "AsyncSpeech",
+    "SpeechWithRawResponse",
+    "AsyncSpeechWithRawResponse",
+    "SpeechWithStreamingResponse",
+    "AsyncSpeechWithStreamingResponse",
+    "Transcriptions",
+    "AsyncTranscriptions",
+    "TranscriptionsWithRawResponse",
+    "AsyncTranscriptionsWithRawResponse",
+    "TranscriptionsWithStreamingResponse",
+    "AsyncTranscriptionsWithStreamingResponse",
+    "Translations",
+    "AsyncTranslations",
+    "TranslationsWithRawResponse",
+    "AsyncTranslationsWithRawResponse",
+    "TranslationsWithStreamingResponse",
+    "AsyncTranslationsWithStreamingResponse",
+    "Audio",
+    "AsyncAudio",
+    "AudioWithRawResponse",
+    "AsyncAudioWithRawResponse",
+    "AudioWithStreamingResponse",
+    "AsyncAudioWithStreamingResponse",
+]

venv/lib/python3.11/site-packages/groq/resources/audio/audio.py

@@ -0,0 +1,166 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from .speech import (
+    Speech,
+    AsyncSpeech,
+    SpeechWithRawResponse,
+    AsyncSpeechWithRawResponse,
+    SpeechWithStreamingResponse,
+    AsyncSpeechWithStreamingResponse,
+)
+from ..._compat import cached_property
+from ..._resource import SyncAPIResource, AsyncAPIResource
+from .translations import (
+    Translations,
+    AsyncTranslations,
+    TranslationsWithRawResponse,
+    AsyncTranslationsWithRawResponse,
+    TranslationsWithStreamingResponse,
+    AsyncTranslationsWithStreamingResponse,
+)
+from .transcriptions import (
+    Transcriptions,
+    AsyncTranscriptions,
+    TranscriptionsWithRawResponse,
+    AsyncTranscriptionsWithRawResponse,
+    TranscriptionsWithStreamingResponse,
+    AsyncTranscriptionsWithStreamingResponse,
+)
+
+__all__ = ["Audio", "AsyncAudio"]
+
+
+class Audio(SyncAPIResource):
+    @cached_property
+    def speech(self) -> Speech:
+        return Speech(self._client)
+
+    @cached_property
+    def transcriptions(self) -> Transcriptions:
+        return Transcriptions(self._client)
+
+    @cached_property
+    def translations(self) -> Translations:
+        return Translations(self._client)
+
+    @cached_property
+    def with_raw_response(self) -> AudioWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/groq/groq-python#accessing-raw-response-data-eg-headers
+        """
+        return AudioWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AudioWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/groq/groq-python#with_streaming_response
+        """
+        return AudioWithStreamingResponse(self)
+
+
+class AsyncAudio(AsyncAPIResource):
+    @cached_property
+    def speech(self) -> AsyncSpeech:
+        return AsyncSpeech(self._client)
+
+    @cached_property
+    def transcriptions(self) -> AsyncTranscriptions:
+        return AsyncTranscriptions(self._client)
+
+    @cached_property
+    def translations(self) -> AsyncTranslations:
+        return AsyncTranslations(self._client)
+
+    @cached_property
+    def with_raw_response(self) -> AsyncAudioWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/groq/groq-python#accessing-raw-response-data-eg-headers
+        """
+        return AsyncAudioWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AsyncAudioWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/groq/groq-python#with_streaming_response
+        """
+        return AsyncAudioWithStreamingResponse(self)
+
+
+class AudioWithRawResponse:
+    def __init__(self, audio: Audio) -> None:
+        self._audio = audio
+
+    @cached_property
+    def speech(self) -> SpeechWithRawResponse:
+        return SpeechWithRawResponse(self._audio.speech)
+
+    @cached_property
+    def transcriptions(self) -> TranscriptionsWithRawResponse:
+        return TranscriptionsWithRawResponse(self._audio.transcriptions)
+
+    @cached_property
+    def translations(self) -> TranslationsWithRawResponse:
+        return TranslationsWithRawResponse(self._audio.translations)
+
+
+class AsyncAudioWithRawResponse:
+    def __init__(self, audio: AsyncAudio) -> None:
+        self._audio = audio
+
+    @cached_property
+    def speech(self) -> AsyncSpeechWithRawResponse:
+        return AsyncSpeechWithRawResponse(self._audio.speech)
+
+    @cached_property
+    def transcriptions(self) -> AsyncTranscriptionsWithRawResponse:
+        return AsyncTranscriptionsWithRawResponse(self._audio.transcriptions)
+
+    @cached_property
+    def translations(self) -> AsyncTranslationsWithRawResponse:
+        return AsyncTranslationsWithRawResponse(self._audio.translations)
+
+
+class AudioWithStreamingResponse:
+    def __init__(self, audio: Audio) -> None:
+        self._audio = audio
+
+    @cached_property
+    def speech(self) -> SpeechWithStreamingResponse:
+        return SpeechWithStreamingResponse(self._audio.speech)
+
+    @cached_property
+    def transcriptions(self) -> TranscriptionsWithStreamingResponse:
+        return TranscriptionsWithStreamingResponse(self._audio.transcriptions)
+
+    @cached_property
+    def translations(self) -> TranslationsWithStreamingResponse:
+        return TranslationsWithStreamingResponse(self._audio.translations)
+
+
+class AsyncAudioWithStreamingResponse:
+    def __init__(self, audio: AsyncAudio) -> None:
+        self._audio = audio
+
+    @cached_property
+    def speech(self) -> AsyncSpeechWithStreamingResponse:
+        return AsyncSpeechWithStreamingResponse(self._audio.speech)
+
+    @cached_property
+    def transcriptions(self) -> AsyncTranscriptionsWithStreamingResponse:
+        return AsyncTranscriptionsWithStreamingResponse(self._audio.transcriptions)
+
+    @cached_property
+    def translations(self) -> AsyncTranslationsWithStreamingResponse:
+        return AsyncTranslationsWithStreamingResponse(self._audio.translations)

venv/lib/python3.11/site-packages/groq/resources/audio/speech.py

@@ -0,0 +1,233 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Union
+from typing_extensions import Literal
+
+import httpx
+
+from ..._types import NOT_GIVEN, Body, Query, Headers, NotGiven
+from ..._utils import maybe_transform, async_maybe_transform
+from ..._compat import cached_property
+from ..._resource import SyncAPIResource, AsyncAPIResource
+from ..._response import (
+    BinaryAPIResponse,
+    AsyncBinaryAPIResponse,
+    StreamedBinaryAPIResponse,
+    AsyncStreamedBinaryAPIResponse,
+    to_custom_raw_response_wrapper,
+    to_custom_streamed_response_wrapper,
+    async_to_custom_raw_response_wrapper,
+    async_to_custom_streamed_response_wrapper,
+)
+from ...types.audio import speech_create_params
+from ..._base_client import make_request_options
+
+__all__ = ["Speech", "AsyncSpeech"]
+
+
+class Speech(SyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> SpeechWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/groq/groq-python#accessing-raw-response-data-eg-headers
+        """
+        return SpeechWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> SpeechWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/groq/groq-python#with_streaming_response
+        """
+        return SpeechWithStreamingResponse(self)
+
+    def create(
+        self,
+        *,
+        input: str,
+        model: Union[str, Literal["playai-tts", "playai-tts-arabic"]],
+        voice: str,
+        response_format: Literal["flac", "mp3", "mulaw", "ogg", "wav"] | NotGiven = NOT_GIVEN,
+        sample_rate: Literal[8000, 16000, 22050, 24000, 32000, 44100, 48000] | NotGiven = NOT_GIVEN,
+        speed: float | NotGiven = NOT_GIVEN,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> BinaryAPIResponse:
+        """
+        Generates audio from the input text.
+
+        Args:
+          input: The text to generate audio for.
+
+          model: One of the [available TTS models](/docs/text-to-speech).
+
+          voice: The voice to use when generating the audio. List of voices can be found
+              [here](/docs/text-to-speech).
+
+          response_format: The format of the generated audio. Supported formats are
+              `flac, mp3, mulaw, ogg, wav`.
+
+          sample_rate: The sample rate for generated audio
+
+          speed: The speed of the generated audio.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        extra_headers = {"Accept": "audio/wav", **(extra_headers or {})}
+        return self._post(
+            "/openai/v1/audio/speech",
+            body=maybe_transform(
+                {
+                    "input": input,
+                    "model": model,
+                    "voice": voice,
+                    "response_format": response_format,
+                    "sample_rate": sample_rate,
+                    "speed": speed,
+                },
+                speech_create_params.SpeechCreateParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=BinaryAPIResponse,
+        )
+
+
+class AsyncSpeech(AsyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> AsyncSpeechWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/groq/groq-python#accessing-raw-response-data-eg-headers
+        """
+        return AsyncSpeechWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AsyncSpeechWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/groq/groq-python#with_streaming_response
+        """
+        return AsyncSpeechWithStreamingResponse(self)
+
+    async def create(
+        self,
+        *,
+        input: str,
+        model: Union[str, Literal["playai-tts", "playai-tts-arabic"]],
+        voice: str,
+        response_format: Literal["flac", "mp3", "mulaw", "ogg", "wav"] | NotGiven = NOT_GIVEN,
+        sample_rate: Literal[8000, 16000, 22050, 24000, 32000, 44100, 48000] | NotGiven = NOT_GIVEN,
+        speed: float | NotGiven = NOT_GIVEN,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> AsyncBinaryAPIResponse:
+        """
+        Generates audio from the input text.
+
+        Args:
+          input: The text to generate audio for.
+
+          model: One of the [available TTS models](/docs/text-to-speech).
+
+          voice: The voice to use when generating the audio. List of voices can be found
+              [here](/docs/text-to-speech).
+
+          response_format: The format of the generated audio. Supported formats are
+              `flac, mp3, mulaw, ogg, wav`.
+
+          sample_rate: The sample rate for generated audio
+
+          speed: The speed of the generated audio.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        extra_headers = {"Accept": "audio/wav", **(extra_headers or {})}
+        return await self._post(
+            "/openai/v1/audio/speech",
+            body=await async_maybe_transform(
+                {
+                    "input": input,
+                    "model": model,
+                    "voice": voice,
+                    "response_format": response_format,
+                    "sample_rate": sample_rate,
+                    "speed": speed,
+                },
+                speech_create_params.SpeechCreateParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=AsyncBinaryAPIResponse,
+        )
+
+
+class SpeechWithRawResponse:
+    def __init__(self, speech: Speech) -> None:
+        self._speech = speech
+
+        self.create = to_custom_raw_response_wrapper(
+            speech.create,
+            BinaryAPIResponse,
+        )
+
+
+class AsyncSpeechWithRawResponse:
+    def __init__(self, speech: AsyncSpeech) -> None:
+        self._speech = speech
+
+        self.create = async_to_custom_raw_response_wrapper(
+            speech.create,
+            AsyncBinaryAPIResponse,
+        )
+
+
+class SpeechWithStreamingResponse:
+    def __init__(self, speech: Speech) -> None:
+        self._speech = speech
+
+        self.create = to_custom_streamed_response_wrapper(
+            speech.create,
+            StreamedBinaryAPIResponse,
+        )
+
+
+class AsyncSpeechWithStreamingResponse:
+    def __init__(self, speech: AsyncSpeech) -> None:
+        self._speech = speech
+
+        self.create = async_to_custom_streamed_response_wrapper(
+            speech.create,
+            AsyncStreamedBinaryAPIResponse,
+        )

venv/lib/python3.11/site-packages/groq/resources/audio/transcriptions.py

@@ -0,0 +1,494 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import List, Union, Mapping, cast
+from typing_extensions import Literal
+
+import httpx
+
+from ..._types import NOT_GIVEN, Body, Query, Headers, NotGiven, FileTypes
+from ..._utils import extract_files, maybe_transform, deepcopy_minimal, async_maybe_transform
+from ..._compat import cached_property
+from ..._resource import SyncAPIResource, AsyncAPIResource
+from ..._response import (
+    to_raw_response_wrapper,
+    to_streamed_response_wrapper,
+    async_to_raw_response_wrapper,
+    async_to_streamed_response_wrapper,
+)
+from ...types.audio import transcription_create_params
+from ..._base_client import make_request_options
+from ...types.audio.transcription import Transcription
+
+__all__ = ["Transcriptions", "AsyncTranscriptions"]
+
+
+class Transcriptions(SyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> TranscriptionsWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/groq/groq-python#accessing-raw-response-data-eg-headers
+        """
+        return TranscriptionsWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> TranscriptionsWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/groq/groq-python#with_streaming_response
+        """
+        return TranscriptionsWithStreamingResponse(self)
+
+    def create(
+        self,
+        *,
+        model: Union[str, Literal["whisper-large-v3", "whisper-large-v3-turbo"]],
+        file: FileTypes | NotGiven = NOT_GIVEN,
+        language: Union[
+            str,
+            Literal[
+                "en",
+                "zh",
+                "de",
+                "es",
+                "ru",
+                "ko",
+                "fr",
+                "ja",
+                "pt",
+                "tr",
+                "pl",
+                "ca",
+                "nl",
+                "ar",
+                "sv",
+                "it",
+                "id",
+                "hi",
+                "fi",
+                "vi",
+                "he",
+                "uk",
+                "el",
+                "ms",
+                "cs",
+                "ro",
+                "da",
+                "hu",
+                "ta",
+                "no",
+                "th",
+                "ur",
+                "hr",
+                "bg",
+                "lt",
+                "la",
+                "mi",
+                "ml",
+                "cy",
+                "sk",
+                "te",
+                "fa",
+                "lv",
+                "bn",
+                "sr",
+                "az",
+                "sl",
+                "kn",
+                "et",
+                "mk",
+                "br",
+                "eu",
+                "is",
+                "hy",
+                "ne",
+                "mn",
+                "bs",
+                "kk",
+                "sq",
+                "sw",
+                "gl",
+                "mr",
+                "pa",
+                "si",
+                "km",
+                "sn",
+                "yo",
+                "so",
+                "af",
+                "oc",
+                "ka",
+                "be",
+                "tg",
+                "sd",
+                "gu",
+                "am",
+                "yi",
+                "lo",
+                "uz",
+                "fo",
+                "ht",
+                "ps",
+                "tk",
+                "nn",
+                "mt",
+                "sa",
+                "lb",
+                "my",
+                "bo",
+                "tl",
+                "mg",
+                "as",
+                "tt",
+                "haw",
+                "ln",
+                "ha",
+                "ba",
+                "jv",
+                "su",
+                "yue",
+            ],
+        ]
+        | NotGiven = NOT_GIVEN,
+        prompt: str | NotGiven = NOT_GIVEN,
+        response_format: Literal["json", "text", "verbose_json"] | NotGiven = NOT_GIVEN,
+        temperature: float | NotGiven = NOT_GIVEN,
+        timestamp_granularities: List[Literal["word", "segment"]] | NotGiven = NOT_GIVEN,
+        url: str | NotGiven = NOT_GIVEN,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> Transcription:
+        """
+        Transcribes audio into the input language.
+
+        Args:
+          model: ID of the model to use. `whisper-large-v3` and `whisper-large-v3-turbo` are
+              currently available.
+
+          file:
+              The audio file object (not file name) to transcribe, in one of these formats:
+              flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm. Either a file or a URL must
+              be provided. Note that the file field is not supported in Batch API requests.
+
+          language: The language of the input audio. Supplying the input language in
+              [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) format will
+              improve accuracy and latency.
+
+          prompt: An optional text to guide the model's style or continue a previous audio
+              segment. The [prompt](/docs/speech-text) should match the audio language.
+
+          response_format: The format of the transcript output, in one of these options: `json`, `text`, or
+              `verbose_json`.
+
+          temperature: The sampling temperature, between 0 and 1. Higher values like 0.8 will make the
+              output more random, while lower values like 0.2 will make it more focused and
+              deterministic. If set to 0, the model will use
+              [log probability](https://en.wikipedia.org/wiki/Log_probability) to
+              automatically increase the temperature until certain thresholds are hit.
+
+          timestamp_granularities: The timestamp granularities to populate for this transcription.
+              `response_format` must be set `verbose_json` to use timestamp granularities.
+              Either or both of these options are supported: `word`, or `segment`. Note: There
+              is no additional latency for segment timestamps, but generating word timestamps
+              incurs additional latency.
+
+          url: The audio URL to translate/transcribe (supports Base64URL). Either a file or a
+              URL must be provided. For Batch API requests, the URL field is required since
+              the file field is not supported.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        body = deepcopy_minimal(
+            {
+                "model": model,
+                "file": file,
+                "language": language,
+                "prompt": prompt,
+                "response_format": response_format,
+                "temperature": temperature,
+                "timestamp_granularities": timestamp_granularities,
+                "url": url,
+            }
+        )
+        files = extract_files(cast(Mapping[str, object], body), paths=[["file"]])
+        # It should be noted that the actual Content-Type header that will be
+        # sent to the server will contain a `boundary` parameter, e.g.
+        # multipart/form-data; boundary=---abc--
+        extra_headers = {"Content-Type": "multipart/form-data", **(extra_headers or {})}
+        return self._post(
+            "/openai/v1/audio/transcriptions",
+            body=maybe_transform(body, transcription_create_params.TranscriptionCreateParams),
+            files=files,
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=Transcription,
+        )
+
+
+class AsyncTranscriptions(AsyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> AsyncTranscriptionsWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/groq/groq-python#accessing-raw-response-data-eg-headers
+        """
+        return AsyncTranscriptionsWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AsyncTranscriptionsWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/groq/groq-python#with_streaming_response
+        """
+        return AsyncTranscriptionsWithStreamingResponse(self)
+
+    async def create(
+        self,
+        *,
+        model: Union[str, Literal["whisper-large-v3", "whisper-large-v3-turbo"]],
+        file: FileTypes | NotGiven = NOT_GIVEN,
+        language: Union[
+            str,
+            Literal[
+                "en",
+                "zh",
+                "de",
+                "es",
+                "ru",
+                "ko",
+                "fr",
+                "ja",
+                "pt",
+                "tr",
+                "pl",
+                "ca",
+                "nl",
+                "ar",
+                "sv",
+                "it",
+                "id",
+                "hi",
+                "fi",
+                "vi",
+                "he",
+                "uk",
+                "el",
+                "ms",
+                "cs",
+                "ro",
+                "da",
+                "hu",
+                "ta",
+                "no",
+                "th",
+                "ur",
+                "hr",
+                "bg",
+                "lt",
+                "la",
+                "mi",
+                "ml",
+                "cy",
+                "sk",
+                "te",
+                "fa",
+                "lv",
+                "bn",
+                "sr",
+                "az",
+                "sl",
+                "kn",
+                "et",
+                "mk",
+                "br",
+                "eu",
+                "is",
+                "hy",
+                "ne",
+                "mn",
+                "bs",
+                "kk",
+                "sq",
+                "sw",
+                "gl",
+                "mr",
+                "pa",
+                "si",
+                "km",
+                "sn",
+                "yo",
+                "so",
+                "af",
+                "oc",
+                "ka",
+                "be",
+                "tg",
+                "sd",
+                "gu",
+                "am",
+                "yi",
+                "lo",
+                "uz",
+                "fo",
+                "ht",
+                "ps",
+                "tk",
+                "nn",
+                "mt",
+                "sa",
+                "lb",
+                "my",
+                "bo",
+                "tl",
+                "mg",
+                "as",
+                "tt",
+                "haw",
+                "ln",
+                "ha",
+                "ba",
+                "jv",
+                "su",
+                "yue",
+            ],
+        ]
+        | NotGiven = NOT_GIVEN,
+        prompt: str | NotGiven = NOT_GIVEN,
+        response_format: Literal["json", "text", "verbose_json"] | NotGiven = NOT_GIVEN,
+        temperature: float | NotGiven = NOT_GIVEN,
+        timestamp_granularities: List[Literal["word", "segment"]] | NotGiven = NOT_GIVEN,
+        url: str | NotGiven = NOT_GIVEN,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> Transcription:
+        """
+        Transcribes audio into the input language.
+
+        Args:
+          model: ID of the model to use. `whisper-large-v3` and `whisper-large-v3-turbo` are
+              currently available.
+
+          file:
+              The audio file object (not file name) to transcribe, in one of these formats:
+              flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm. Either a file or a URL must
+              be provided. Note that the file field is not supported in Batch API requests.
+
+          language: The language of the input audio. Supplying the input language in
+              [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) format will
+              improve accuracy and latency.
+
+          prompt: An optional text to guide the model's style or continue a previous audio
+              segment. The [prompt](/docs/speech-text) should match the audio language.
+
+          response_format: The format of the transcript output, in one of these options: `json`, `text`, or
+              `verbose_json`.
+
+          temperature: The sampling temperature, between 0 and 1. Higher values like 0.8 will make the
+              output more random, while lower values like 0.2 will make it more focused and
+              deterministic. If set to 0, the model will use
+              [log probability](https://en.wikipedia.org/wiki/Log_probability) to
+              automatically increase the temperature until certain thresholds are hit.
+
+          timestamp_granularities: The timestamp granularities to populate for this transcription.
+              `response_format` must be set `verbose_json` to use timestamp granularities.
+              Either or both of these options are supported: `word`, or `segment`. Note: There
+              is no additional latency for segment timestamps, but generating word timestamps
+              incurs additional latency.
+
+          url: The audio URL to translate/transcribe (supports Base64URL). Either a file or a
+              URL must be provided. For Batch API requests, the URL field is required since
+              the file field is not supported.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        body = deepcopy_minimal(
+            {
+                "model": model,
+                "file": file,
+                "language": language,
+                "prompt": prompt,
+                "response_format": response_format,
+                "temperature": temperature,
+                "timestamp_granularities": timestamp_granularities,
+                "url": url,
+            }
+        )
+        files = extract_files(cast(Mapping[str, object], body), paths=[["file"]])
+        # It should be noted that the actual Content-Type header that will be
+        # sent to the server will contain a `boundary` parameter, e.g.
+        # multipart/form-data; boundary=---abc--
+        extra_headers = {"Content-Type": "multipart/form-data", **(extra_headers or {})}
+        return await self._post(
+            "/openai/v1/audio/transcriptions",
+            body=await async_maybe_transform(body, transcription_create_params.TranscriptionCreateParams),
+            files=files,
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=Transcription,
+        )
+
+
+class TranscriptionsWithRawResponse:
+    def __init__(self, transcriptions: Transcriptions) -> None:
+        self._transcriptions = transcriptions
+
+        self.create = to_raw_response_wrapper(
+            transcriptions.create,
+        )
+
+
+class AsyncTranscriptionsWithRawResponse:
+    def __init__(self, transcriptions: AsyncTranscriptions) -> None:
+        self._transcriptions = transcriptions
+
+        self.create = async_to_raw_response_wrapper(
+            transcriptions.create,
+        )
+
+
+class TranscriptionsWithStreamingResponse:
+    def __init__(self, transcriptions: Transcriptions) -> None:
+        self._transcriptions = transcriptions
+
+        self.create = to_streamed_response_wrapper(
+            transcriptions.create,
+        )
+
+
+class AsyncTranscriptionsWithStreamingResponse:
+    def __init__(self, transcriptions: AsyncTranscriptions) -> None:
+        self._transcriptions = transcriptions
+
+        self.create = async_to_streamed_response_wrapper(
+            transcriptions.create,
+        )

venv/lib/python3.11/site-packages/groq/resources/audio/translations.py

@@ -0,0 +1,254 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Union, Mapping, cast
+from typing_extensions import Literal
+
+import httpx
+
+from ..._types import NOT_GIVEN, Body, Query, Headers, NotGiven, FileTypes
+from ..._utils import extract_files, maybe_transform, deepcopy_minimal, async_maybe_transform
+from ..._compat import cached_property
+from ..._resource import SyncAPIResource, AsyncAPIResource
+from ..._response import (
+    to_raw_response_wrapper,
+    to_streamed_response_wrapper,
+    async_to_raw_response_wrapper,
+    async_to_streamed_response_wrapper,
+)
+from ...types.audio import translation_create_params
+from ..._base_client import make_request_options
+from ...types.audio.translation import Translation
+
+__all__ = ["Translations", "AsyncTranslations"]
+
+
+class Translations(SyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> TranslationsWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/groq/groq-python#accessing-raw-response-data-eg-headers
+        """
+        return TranslationsWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> TranslationsWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/groq/groq-python#with_streaming_response
+        """
+        return TranslationsWithStreamingResponse(self)
+
+    def create(
+        self,
+        *,
+        model: Union[str, Literal["whisper-large-v3", "whisper-large-v3-turbo"]],
+        file: FileTypes | NotGiven = NOT_GIVEN,
+        prompt: str | NotGiven = NOT_GIVEN,
+        response_format: Literal["json", "text", "verbose_json"] | NotGiven = NOT_GIVEN,
+        temperature: float | NotGiven = NOT_GIVEN,
+        url: str | NotGiven = NOT_GIVEN,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> Translation:
+        """Translates audio into English.
+
+        Args:
+          model: ID of the model to use.
+
+        `whisper-large-v3` and `whisper-large-v3-turbo` are
+              currently available.
+
+          file: The audio file object (not file name) translate, in one of these formats: flac,
+              mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
+
+          prompt: An optional text to guide the model's style or continue a previous audio
+              segment. The [prompt](/docs/guides/speech-to-text/prompting) should be in
+              English.
+
+          response_format: The format of the transcript output, in one of these options: `json`, `text`, or
+              `verbose_json`.
+
+          temperature: The sampling temperature, between 0 and 1. Higher values like 0.8 will make the
+              output more random, while lower values like 0.2 will make it more focused and
+              deterministic. If set to 0, the model will use
+              [log probability](https://en.wikipedia.org/wiki/Log_probability) to
+              automatically increase the temperature until certain thresholds are hit.
+
+          url: The audio URL to translate/transcribe (supports Base64URL). Either file or url
+              must be provided. When using the Batch API only url is supported.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        body = deepcopy_minimal(
+            {
+                "model": model,
+                "file": file,
+                "prompt": prompt,
+                "response_format": response_format,
+                "temperature": temperature,
+                "url": url,
+            }
+        )
+        files = extract_files(cast(Mapping[str, object], body), paths=[["file"]])
+        # It should be noted that the actual Content-Type header that will be
+        # sent to the server will contain a `boundary` parameter, e.g.
+        # multipart/form-data; boundary=---abc--
+        extra_headers = {"Content-Type": "multipart/form-data", **(extra_headers or {})}
+        return self._post(
+            "/openai/v1/audio/translations",
+            body=maybe_transform(body, translation_create_params.TranslationCreateParams),
+            files=files,
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=Translation,
+        )
+
+
+class AsyncTranslations(AsyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> AsyncTranslationsWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/groq/groq-python#accessing-raw-response-data-eg-headers
+        """
+        return AsyncTranslationsWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AsyncTranslationsWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/groq/groq-python#with_streaming_response
+        """
+        return AsyncTranslationsWithStreamingResponse(self)
+
+    async def create(
+        self,
+        *,
+        model: Union[str, Literal["whisper-large-v3", "whisper-large-v3-turbo"]],
+        file: FileTypes | NotGiven = NOT_GIVEN,
+        prompt: str | NotGiven = NOT_GIVEN,
+        response_format: Literal["json", "text", "verbose_json"] | NotGiven = NOT_GIVEN,
+        temperature: float | NotGiven = NOT_GIVEN,
+        url: str | NotGiven = NOT_GIVEN,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> Translation:
+        """Translates audio into English.
+
+        Args:
+          model: ID of the model to use.
+
+        `whisper-large-v3` and `whisper-large-v3-turbo` are
+              currently available.
+
+          file: The audio file object (not file name) translate, in one of these formats: flac,
+              mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
+
+          prompt: An optional text to guide the model's style or continue a previous audio
+              segment. The [prompt](/docs/guides/speech-to-text/prompting) should be in
+              English.
+
+          response_format: The format of the transcript output, in one of these options: `json`, `text`, or
+              `verbose_json`.
+
+          temperature: The sampling temperature, between 0 and 1. Higher values like 0.8 will make the
+              output more random, while lower values like 0.2 will make it more focused and
+              deterministic. If set to 0, the model will use
+              [log probability](https://en.wikipedia.org/wiki/Log_probability) to
+              automatically increase the temperature until certain thresholds are hit.
+
+          url: The audio URL to translate/transcribe (supports Base64URL). Either file or url
+              must be provided. When using the Batch API only url is supported.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        body = deepcopy_minimal(
+            {
+                "model": model,
+                "file": file,
+                "prompt": prompt,
+                "response_format": response_format,
+                "temperature": temperature,
+                "url": url,
+            }
+        )
+        files = extract_files(cast(Mapping[str, object], body), paths=[["file"]])
+        # It should be noted that the actual Content-Type header that will be
+        # sent to the server will contain a `boundary` parameter, e.g.
+        # multipart/form-data; boundary=---abc--
+        extra_headers = {"Content-Type": "multipart/form-data", **(extra_headers or {})}
+        return await self._post(
+            "/openai/v1/audio/translations",
+            body=await async_maybe_transform(body, translation_create_params.TranslationCreateParams),
+            files=files,
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=Translation,
+        )
+
+
+class TranslationsWithRawResponse:
+    def __init__(self, translations: Translations) -> None:
+        self._translations = translations
+
+        self.create = to_raw_response_wrapper(
+            translations.create,
+        )
+
+
+class AsyncTranslationsWithRawResponse:
+    def __init__(self, translations: AsyncTranslations) -> None:
+        self._translations = translations
+
+        self.create = async_to_raw_response_wrapper(
+            translations.create,
+        )
+
+
+class TranslationsWithStreamingResponse:
+    def __init__(self, translations: Translations) -> None:
+        self._translations = translations
+
+        self.create = to_streamed_response_wrapper(
+            translations.create,
+        )
+
+
+class AsyncTranslationsWithStreamingResponse:
+    def __init__(self, translations: AsyncTranslations) -> None:
+        self._translations = translations
+
+        self.create = async_to_streamed_response_wrapper(
+            translations.create,
+        )

venv/lib/python3.11/site-packages/groq/resources/batches.py

@@ -0,0 +1,429 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Dict, Optional
+from typing_extensions import Literal
+
+import httpx
+
+from ..types import batch_create_params
+from .._types import NOT_GIVEN, Body, Query, Headers, NotGiven
+from .._utils import maybe_transform, async_maybe_transform
+from .._compat import cached_property
+from .._resource import SyncAPIResource, AsyncAPIResource
+from .._response import (
+    to_raw_response_wrapper,
+    to_streamed_response_wrapper,
+    async_to_raw_response_wrapper,
+    async_to_streamed_response_wrapper,
+)
+from .._base_client import make_request_options
+from ..types.batch_list_response import BatchListResponse
+from ..types.batch_cancel_response import BatchCancelResponse
+from ..types.batch_create_response import BatchCreateResponse
+from ..types.batch_retrieve_response import BatchRetrieveResponse
+
+__all__ = ["Batches", "AsyncBatches"]
+
+
+class Batches(SyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> BatchesWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/groq/groq-python#accessing-raw-response-data-eg-headers
+        """
+        return BatchesWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> BatchesWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/groq/groq-python#with_streaming_response
+        """
+        return BatchesWithStreamingResponse(self)
+
+    def create(
+        self,
+        *,
+        completion_window: str,
+        endpoint: Literal["/v1/chat/completions"],
+        input_file_id: str,
+        metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> BatchCreateResponse:
+        """
+        Creates and executes a batch from an uploaded file of requests.
+        [Learn more](/docs/batch).
+
+        Args:
+          completion_window: The time frame within which the batch should be processed. Durations from `24h`
+              to `7d` are supported.
+
+          endpoint: The endpoint to be used for all requests in the batch. Currently
+              `/v1/chat/completions` is supported.
+
+          input_file_id: The ID of an uploaded file that contains requests for the new batch.
+
+              See [upload file](/docs/api-reference#files-upload) for how to upload a file.
+
+              Your input file must be formatted as a [JSONL file](/docs/batch), and must be
+              uploaded with the purpose `batch`. The file can be up to 100 MB in size.
+
+          metadata: Optional custom metadata for the batch.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        return self._post(
+            "/openai/v1/batches",
+            body=maybe_transform(
+                {
+                    "completion_window": completion_window,
+                    "endpoint": endpoint,
+                    "input_file_id": input_file_id,
+                    "metadata": metadata,
+                },
+                batch_create_params.BatchCreateParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=BatchCreateResponse,
+        )
+
+    def retrieve(
+        self,
+        batch_id: str,
+        *,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> BatchRetrieveResponse:
+        """
+        Retrieves a batch.
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not batch_id:
+            raise ValueError(f"Expected a non-empty value for `batch_id` but received {batch_id!r}")
+        return self._get(
+            f"/openai/v1/batches/{batch_id}",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=BatchRetrieveResponse,
+        )
+
+    def list(
+        self,
+        *,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> BatchListResponse:
+        """List your organization's batches."""
+        return self._get(
+            "/openai/v1/batches",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=BatchListResponse,
+        )
+
+    def cancel(
+        self,
+        batch_id: str,
+        *,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> BatchCancelResponse:
+        """
+        Cancels a batch.
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not batch_id:
+            raise ValueError(f"Expected a non-empty value for `batch_id` but received {batch_id!r}")
+        return self._post(
+            f"/openai/v1/batches/{batch_id}/cancel",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=BatchCancelResponse,
+        )
+
+
+class AsyncBatches(AsyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> AsyncBatchesWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/groq/groq-python#accessing-raw-response-data-eg-headers
+        """
+        return AsyncBatchesWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AsyncBatchesWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/groq/groq-python#with_streaming_response
+        """
+        return AsyncBatchesWithStreamingResponse(self)
+
+    async def create(
+        self,
+        *,
+        completion_window: str,
+        endpoint: Literal["/v1/chat/completions"],
+        input_file_id: str,
+        metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> BatchCreateResponse:
+        """
+        Creates and executes a batch from an uploaded file of requests.
+        [Learn more](/docs/batch).
+
+        Args:
+          completion_window: The time frame within which the batch should be processed. Durations from `24h`
+              to `7d` are supported.
+
+          endpoint: The endpoint to be used for all requests in the batch. Currently
+              `/v1/chat/completions` is supported.
+
+          input_file_id: The ID of an uploaded file that contains requests for the new batch.
+
+              See [upload file](/docs/api-reference#files-upload) for how to upload a file.
+
+              Your input file must be formatted as a [JSONL file](/docs/batch), and must be
+              uploaded with the purpose `batch`. The file can be up to 100 MB in size.
+
+          metadata: Optional custom metadata for the batch.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        return await self._post(
+            "/openai/v1/batches",
+            body=await async_maybe_transform(
+                {
+                    "completion_window": completion_window,
+                    "endpoint": endpoint,
+                    "input_file_id": input_file_id,
+                    "metadata": metadata,
+                },
+                batch_create_params.BatchCreateParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=BatchCreateResponse,
+        )
+
+    async def retrieve(
+        self,
+        batch_id: str,
+        *,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> BatchRetrieveResponse:
+        """
+        Retrieves a batch.
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not batch_id:
+            raise ValueError(f"Expected a non-empty value for `batch_id` but received {batch_id!r}")
+        return await self._get(
+            f"/openai/v1/batches/{batch_id}",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=BatchRetrieveResponse,
+        )
+
+    async def list(
+        self,
+        *,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> BatchListResponse:
+        """List your organization's batches."""
+        return await self._get(
+            "/openai/v1/batches",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=BatchListResponse,
+        )
+
+    async def cancel(
+        self,
+        batch_id: str,
+        *,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> BatchCancelResponse:
+        """
+        Cancels a batch.
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not batch_id:
+            raise ValueError(f"Expected a non-empty value for `batch_id` but received {batch_id!r}")
+        return await self._post(
+            f"/openai/v1/batches/{batch_id}/cancel",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=BatchCancelResponse,
+        )
+
+
+class BatchesWithRawResponse:
+    def __init__(self, batches: Batches) -> None:
+        self._batches = batches
+
+        self.create = to_raw_response_wrapper(
+            batches.create,
+        )
+        self.retrieve = to_raw_response_wrapper(
+            batches.retrieve,
+        )
+        self.list = to_raw_response_wrapper(
+            batches.list,
+        )
+        self.cancel = to_raw_response_wrapper(
+            batches.cancel,
+        )
+
+
+class AsyncBatchesWithRawResponse:
+    def __init__(self, batches: AsyncBatches) -> None:
+        self._batches = batches
+
+        self.create = async_to_raw_response_wrapper(
+            batches.create,
+        )
+        self.retrieve = async_to_raw_response_wrapper(
+            batches.retrieve,
+        )
+        self.list = async_to_raw_response_wrapper(
+            batches.list,
+        )
+        self.cancel = async_to_raw_response_wrapper(
+            batches.cancel,
+        )
+
+
+class BatchesWithStreamingResponse:
+    def __init__(self, batches: Batches) -> None:
+        self._batches = batches
+
+        self.create = to_streamed_response_wrapper(
+            batches.create,
+        )
+        self.retrieve = to_streamed_response_wrapper(
+            batches.retrieve,
+        )
+        self.list = to_streamed_response_wrapper(
+            batches.list,
+        )
+        self.cancel = to_streamed_response_wrapper(
+            batches.cancel,
+        )
+
+
+class AsyncBatchesWithStreamingResponse:
+    def __init__(self, batches: AsyncBatches) -> None:
+        self._batches = batches
+
+        self.create = async_to_streamed_response_wrapper(
+            batches.create,
+        )
+        self.retrieve = async_to_streamed_response_wrapper(
+            batches.retrieve,
+        )
+        self.list = async_to_streamed_response_wrapper(
+            batches.list,
+        )
+        self.cancel = async_to_streamed_response_wrapper(
+            batches.cancel,
+        )

venv/lib/python3.11/site-packages/groq/resources/chat/__init__.py

@@ -0,0 +1,33 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from .chat import (
+    Chat,
+    AsyncChat,
+    ChatWithRawResponse,
+    AsyncChatWithRawResponse,
+    ChatWithStreamingResponse,
+    AsyncChatWithStreamingResponse,
+)
+from .completions import (
+    Completions,
+    AsyncCompletions,
+    CompletionsWithRawResponse,
+    AsyncCompletionsWithRawResponse,
+    CompletionsWithStreamingResponse,
+    AsyncCompletionsWithStreamingResponse,
+)
+
+__all__ = [
+    "Completions",
+    "AsyncCompletions",
+    "CompletionsWithRawResponse",
+    "AsyncCompletionsWithRawResponse",
+    "CompletionsWithStreamingResponse",
+    "AsyncCompletionsWithStreamingResponse",
+    "Chat",
+    "AsyncChat",
+    "ChatWithRawResponse",
+    "AsyncChatWithRawResponse",
+    "ChatWithStreamingResponse",
+    "AsyncChatWithStreamingResponse",
+]

venv/lib/python3.11/site-packages/groq/resources/chat/chat.py

@@ -0,0 +1,102 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from ..._compat import cached_property
+from ..._resource import SyncAPIResource, AsyncAPIResource
+from .completions import (
+    Completions,
+    AsyncCompletions,
+    CompletionsWithRawResponse,
+    AsyncCompletionsWithRawResponse,
+    CompletionsWithStreamingResponse,
+    AsyncCompletionsWithStreamingResponse,
+)
+
+__all__ = ["Chat", "AsyncChat"]
+
+
+class Chat(SyncAPIResource):
+    @cached_property
+    def completions(self) -> Completions:
+        return Completions(self._client)
+
+    @cached_property
+    def with_raw_response(self) -> ChatWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/groq/groq-python#accessing-raw-response-data-eg-headers
+        """
+        return ChatWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> ChatWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/groq/groq-python#with_streaming_response
+        """
+        return ChatWithStreamingResponse(self)
+
+
+class AsyncChat(AsyncAPIResource):
+    @cached_property
+    def completions(self) -> AsyncCompletions:
+        return AsyncCompletions(self._client)
+
+    @cached_property
+    def with_raw_response(self) -> AsyncChatWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/groq/groq-python#accessing-raw-response-data-eg-headers
+        """
+        return AsyncChatWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AsyncChatWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/groq/groq-python#with_streaming_response
+        """
+        return AsyncChatWithStreamingResponse(self)
+
+
+class ChatWithRawResponse:
+    def __init__(self, chat: Chat) -> None:
+        self._chat = chat
+
+    @cached_property
+    def completions(self) -> CompletionsWithRawResponse:
+        return CompletionsWithRawResponse(self._chat.completions)
+
+
+class AsyncChatWithRawResponse:
+    def __init__(self, chat: AsyncChat) -> None:
+        self._chat = chat
+
+    @cached_property
+    def completions(self) -> AsyncCompletionsWithRawResponse:
+        return AsyncCompletionsWithRawResponse(self._chat.completions)
+
+
+class ChatWithStreamingResponse:
+    def __init__(self, chat: Chat) -> None:
+        self._chat = chat
+
+    @cached_property
+    def completions(self) -> CompletionsWithStreamingResponse:
+        return CompletionsWithStreamingResponse(self._chat.completions)
+
+
+class AsyncChatWithStreamingResponse:
+    def __init__(self, chat: AsyncChat) -> None:
+        self._chat = chat
+
+    @cached_property
+    def completions(self) -> AsyncCompletionsWithStreamingResponse:
+        return AsyncCompletionsWithStreamingResponse(self._chat.completions)

venv/lib/python3.11/site-packages/groq/resources/chat/completions.py

@@ -0,0 +1,829 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Dict, List, Union, Iterable, Optional, overload
+from typing_extensions import Literal
+
+import httpx
+
+from ..._types import NOT_GIVEN, Body, Query, Headers, NotGiven
+from ..._utils import maybe_transform, async_maybe_transform
+from ..._compat import cached_property
+from ..._resource import SyncAPIResource, AsyncAPIResource
+from ..._response import (
+    to_raw_response_wrapper,
+    to_streamed_response_wrapper,
+    async_to_raw_response_wrapper,
+    async_to_streamed_response_wrapper,
+)
+from ..._streaming import Stream, AsyncStream
+from ...types.chat import completion_create_params
+from ..._base_client import make_request_options
+from ...types.chat.chat_completion import ChatCompletion
+from ...types.chat.chat_completion_chunk import ChatCompletionChunk
+from ...types.chat.chat_completion_tool_param import ChatCompletionToolParam
+from ...types.chat.chat_completion_message_param import ChatCompletionMessageParam
+from ...types.chat.chat_completion_tool_choice_option_param import ChatCompletionToolChoiceOptionParam
+
+__all__ = ["Completions", "AsyncCompletions"]
+
+
+class Completions(SyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> CompletionsWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/groq/groq-python#accessing-raw-response-data-eg-headers
+        """
+        return CompletionsWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> CompletionsWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/groq/groq-python#with_streaming_response
+        """
+        return CompletionsWithStreamingResponse(self)
+
+    @overload
+    def create(
+        self,
+        *,
+        messages: Iterable[ChatCompletionMessageParam],
+        model: str,
+        exclude_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
+        frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
+        function_call: Optional[completion_create_params.FunctionCall] | NotGiven = NOT_GIVEN,
+        functions: Optional[Iterable[completion_create_params.Function]] | NotGiven = NOT_GIVEN,
+        include_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
+        logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
+        logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
+        max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
+        metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN,
+        n: Optional[int] | NotGiven = NOT_GIVEN,
+        parallel_tool_calls: Optional[bool] | NotGiven = NOT_GIVEN,
+        presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["none", "default"]] | NotGiven = NOT_GIVEN,
+        reasoning_format: Optional[Literal["hidden", "raw", "parsed"]] | NotGiven = NOT_GIVEN,
+        response_format: Optional[completion_create_params.ResponseFormat] | NotGiven = NOT_GIVEN,
+        search_settings: Optional[completion_create_params.SearchSettings] | NotGiven = NOT_GIVEN,
+        seed: Optional[int] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "on_demand", "flex", "performance"]] | NotGiven = NOT_GIVEN,
+        stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
+        store: Optional[bool] | NotGiven = NOT_GIVEN,
+        stream: Optional[Literal[False]] | NotGiven = NOT_GIVEN,
+        temperature: Optional[float] | NotGiven = NOT_GIVEN,
+        tool_choice: Optional[ChatCompletionToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
+        tools: Optional[Iterable[ChatCompletionToolParam]] | NotGiven = NOT_GIVEN,
+        top_logprobs: Optional[int] | NotGiven = NOT_GIVEN,
+        top_p: Optional[float] | NotGiven = NOT_GIVEN,
+        user: Optional[str] | NotGiven = NOT_GIVEN,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> ChatCompletion:
+        ...
+
+    @overload
+    def create(
+        self,
+        *,
+        messages: Iterable[ChatCompletionMessageParam],
+        model: str,
+        exclude_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
+        frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
+        function_call: Optional[completion_create_params.FunctionCall] | NotGiven = NOT_GIVEN,
+        functions: Optional[Iterable[completion_create_params.Function]] | NotGiven = NOT_GIVEN,
+        include_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
+        logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
+        logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
+        max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
+        metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN,
+        n: Optional[int] | NotGiven = NOT_GIVEN,
+        parallel_tool_calls: Optional[bool] | NotGiven = NOT_GIVEN,
+        presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["none", "default"]] | NotGiven = NOT_GIVEN,
+        reasoning_format: Optional[Literal["hidden", "raw", "parsed"]] | NotGiven = NOT_GIVEN,
+        response_format: Optional[completion_create_params.ResponseFormat] | NotGiven = NOT_GIVEN,
+        search_settings: Optional[completion_create_params.SearchSettings] | NotGiven = NOT_GIVEN,
+        seed: Optional[int] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "on_demand", "flex", "performance"]] | NotGiven = NOT_GIVEN,
+        stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
+        store: Optional[bool] | NotGiven = NOT_GIVEN,
+        stream: Literal[True],
+        temperature: Optional[float] | NotGiven = NOT_GIVEN,
+        tool_choice: Optional[ChatCompletionToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
+        tools: Optional[Iterable[ChatCompletionToolParam]] | NotGiven = NOT_GIVEN,
+        top_logprobs: Optional[int] | NotGiven = NOT_GIVEN,
+        top_p: Optional[float] | NotGiven = NOT_GIVEN,
+        user: Optional[str] | NotGiven = NOT_GIVEN,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> Stream[ChatCompletionChunk]:
+        ...
+
+    @overload
+    def create(
+        self,
+        *,
+        messages: Iterable[ChatCompletionMessageParam],
+        model: str,
+        exclude_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
+        frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
+        function_call: Optional[completion_create_params.FunctionCall] | NotGiven = NOT_GIVEN,
+        functions: Optional[Iterable[completion_create_params.Function]] | NotGiven = NOT_GIVEN,
+        include_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
+        logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
+        logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
+        max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
+        metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN,
+        n: Optional[int] | NotGiven = NOT_GIVEN,
+        parallel_tool_calls: Optional[bool] | NotGiven = NOT_GIVEN,
+        presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["none", "default"]] | NotGiven = NOT_GIVEN,
+        reasoning_format: Optional[Literal["hidden", "raw", "parsed"]] | NotGiven = NOT_GIVEN,
+        response_format: Optional[completion_create_params.ResponseFormat] | NotGiven = NOT_GIVEN,
+        search_settings: Optional[completion_create_params.SearchSettings] | NotGiven = NOT_GIVEN,
+        seed: Optional[int] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "on_demand", "flex", "performance"]] | NotGiven = NOT_GIVEN,
+        stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
+        store: Optional[bool] | NotGiven = NOT_GIVEN,
+        stream: bool,
+        temperature: Optional[float] | NotGiven = NOT_GIVEN,
+        tool_choice: Optional[ChatCompletionToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
+        tools: Optional[Iterable[ChatCompletionToolParam]] | NotGiven = NOT_GIVEN,
+        top_logprobs: Optional[int] | NotGiven = NOT_GIVEN,
+        top_p: Optional[float] | NotGiven = NOT_GIVEN,
+        user: Optional[str] | NotGiven = NOT_GIVEN,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> ChatCompletion | Stream[ChatCompletionChunk]:
+        ...
+
+    def create(
+        self,
+        *,
+        messages: Iterable[ChatCompletionMessageParam],
+        model: Union[
+            str,
+            Literal[
+                "gemma2-9b-it",
+                "llama-3.3-70b-versatile",
+                "llama-3.1-8b-instant",
+                "llama-guard-3-8b",
+                "llama3-70b-8192",
+                "llama3-8b-8192",
+            ],
+        ],
+        exclude_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
+        frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
+        function_call: Optional[completion_create_params.FunctionCall] | NotGiven = NOT_GIVEN,
+        functions: Optional[Iterable[completion_create_params.Function]] | NotGiven = NOT_GIVEN,
+        include_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
+        logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
+        logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
+        max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
+        metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN,
+        n: Optional[int] | NotGiven = NOT_GIVEN,
+        parallel_tool_calls: Optional[bool] | NotGiven = NOT_GIVEN,
+        presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["none", "default"]] | NotGiven = NOT_GIVEN,
+        reasoning_format: Optional[Literal["hidden", "raw", "parsed"]] | NotGiven = NOT_GIVEN,
+        response_format: Optional[completion_create_params.ResponseFormat] | NotGiven = NOT_GIVEN,
+        search_settings: Optional[completion_create_params.SearchSettings] | NotGiven = NOT_GIVEN,
+        seed: Optional[int] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "on_demand", "flex", "performance"]] | NotGiven = NOT_GIVEN,
+        stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
+        store: Optional[bool] | NotGiven = NOT_GIVEN,
+        stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN,
+        temperature: Optional[float] | NotGiven = NOT_GIVEN,
+        tool_choice: Optional[ChatCompletionToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
+        tools: Optional[Iterable[ChatCompletionToolParam]] | NotGiven = NOT_GIVEN,
+        top_logprobs: Optional[int] | NotGiven = NOT_GIVEN,
+        top_p: Optional[float] | NotGiven = NOT_GIVEN,
+        user: Optional[str] | NotGiven = NOT_GIVEN,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> ChatCompletion | Stream[ChatCompletionChunk]:
+        """
+        Creates a model response for the given chat conversation.
+
+        Args:
+          messages: A list of messages comprising the conversation so far.
+
+          model: ID of the model to use. For details on which models are compatible with the Chat
+              API, see available [models](https://console.groq.com/docs/models)
+
+          exclude_domains: Deprecated: Use search_settings.exclude_domains instead. A list of domains to
+              exclude from the search results when the model uses a web search tool.
+
+          frequency_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on their
+              existing frequency in the text so far, decreasing the model's likelihood to
+              repeat the same line verbatim.
+
+          function_call: Deprecated in favor of `tool_choice`.
+
+              Controls which (if any) function is called by the model. `none` means the model
+              will not call a function and instead generates a message. `auto` means the model
+              can pick between generating a message or calling a function. Specifying a
+              particular function via `{"name": "my_function"}` forces the model to call that
+              function.
+
+              `none` is the default when no functions are present. `auto` is the default if
+              functions are present.
+
+          functions: Deprecated in favor of `tools`.
+
+              A list of functions the model may generate JSON inputs for.
+
+          include_domains: Deprecated: Use search_settings.include_domains instead. A list of domains to
+              include in the search results when the model uses a web search tool.
+
+          logit_bias: This is not yet supported by any of our models. Modify the likelihood of
+              specified tokens appearing in the completion.
+
+          logprobs: This is not yet supported by any of our models. Whether to return log
+              probabilities of the output tokens or not. If true, returns the log
+              probabilities of each output token returned in the `content` of `message`.
+
+          max_completion_tokens: The maximum number of tokens that can be generated in the chat completion. The
+              total length of input tokens and generated tokens is limited by the model's
+              context length.
+
+          max_tokens: Deprecated in favor of `max_completion_tokens`. The maximum number of tokens
+              that can be generated in the chat completion. The total length of input tokens
+              and generated tokens is limited by the model's context length.
+
+          metadata: This parameter is not currently supported.
+
+          n: How many chat completion choices to generate for each input message. Note that
+              the current moment, only n=1 is supported. Other values will result in a 400
+              response.
+
+          parallel_tool_calls: Whether to enable parallel function calling during tool use.
+
+          presence_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on
+              whether they appear in the text so far, increasing the model's likelihood to
+              talk about new topics.
+
+          reasoning_effort: this field is only available for qwen3 models. Set to 'none' to disable
+              reasoning. Set to 'default' or null to let Qwen reason.
+
+          reasoning_format: Specifies how to output reasoning tokens
+
+          response_format: An object specifying the format that the model must output. Setting to
+              `{ "type": "json_schema", "json_schema": {...} }` enables Structured Outputs
+              which ensures the model will match your supplied JSON schema. json_schema
+              response format is only supported on llama 4 models. Setting to
+              `{ "type": "json_object" }` enables the older JSON mode, which ensures the
+              message the model generates is valid JSON. Using `json_schema` is preferred for
+              models that support it.
+
+          search_settings: Settings for web search functionality when the model uses a web search tool.
+
+          seed: If specified, our system will make a best effort to sample deterministically,
+              such that repeated requests with the same `seed` and parameters should return
+              the same result. Determinism is not guaranteed, and you should refer to the
+              `system_fingerprint` response parameter to monitor changes in the backend.
+
+          service_tier: The service tier to use for the request. Defaults to `on_demand`.
+
+              - `auto` will automatically select the highest tier available within the rate
+                limits of your organization.
+              - `flex` uses the flex tier, which will succeed or fail quickly.
+
+          stop: Up to 4 sequences where the API will stop generating further tokens. The
+              returned text will not contain the stop sequence.
+
+          store: This parameter is not currently supported.
+
+          stream: If set, partial message deltas will be sent. Tokens will be sent as data-only
+              [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format)
+              as they become available, with the stream terminated by a `data: [DONE]`
+              message. [Example code](/docs/text-chat#streaming-a-chat-completion).
+
+          temperature: What sampling temperature to use, between 0 and 2. Higher values like 0.8 will
+              make the output more random, while lower values like 0.2 will make it more
+              focused and deterministic. We generally recommend altering this or top_p but not
+              both.
+
+          tool_choice: Controls which (if any) tool is called by the model. `none` means the model will
+              not call any tool and instead generates a message. `auto` means the model can
+              pick between generating a message or calling one or more tools. `required` means
+              the model must call one or more tools. Specifying a particular tool via
+              `{"type": "function", "function": {"name": "my_function"}}` forces the model to
+              call that tool.
+
+              `none` is the default when no tools are present. `auto` is the default if tools
+              are present.
+
+          tools: A list of tools the model may call. Currently, only functions are supported as a
+              tool. Use this to provide a list of functions the model may generate JSON inputs
+              for. A max of 128 functions are supported.
+
+          top_logprobs: This is not yet supported by any of our models. An integer between 0 and 20
+              specifying the number of most likely tokens to return at each token position,
+              each with an associated log probability. `logprobs` must be set to `true` if
+              this parameter is used.
+
+          top_p: An alternative to sampling with temperature, called nucleus sampling, where the
+              model considers the results of the tokens with top_p probability mass. So 0.1
+              means only the tokens comprising the top 10% probability mass are considered. We
+              generally recommend altering this or temperature but not both.
+
+          user: A unique identifier representing your end-user, which can help us monitor and
+              detect abuse.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        return self._post(
+            "/openai/v1/chat/completions",
+            body=maybe_transform(
+                {
+                    "messages": messages,
+                    "model": model,
+                    "exclude_domains": exclude_domains,
+                    "frequency_penalty": frequency_penalty,
+                    "function_call": function_call,
+                    "functions": functions,
+                    "include_domains": include_domains,
+                    "logit_bias": logit_bias,
+                    "logprobs": logprobs,
+                    "max_completion_tokens": max_completion_tokens,
+                    "max_tokens": max_tokens,
+                    "metadata": metadata,
+                    "n": n,
+                    "parallel_tool_calls": parallel_tool_calls,
+                    "presence_penalty": presence_penalty,
+                    "reasoning_effort": reasoning_effort,
+                    "reasoning_format": reasoning_format,
+                    "response_format": response_format,
+                    "search_settings": search_settings,
+                    "seed": seed,
+                    "service_tier": service_tier,
+                    "stop": stop,
+                    "store": store,
+                    "stream": stream,
+                    "temperature": temperature,
+                    "tool_choice": tool_choice,
+                    "tools": tools,
+                    "top_logprobs": top_logprobs,
+                    "top_p": top_p,
+                    "user": user,
+                },
+                completion_create_params.CompletionCreateParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=ChatCompletion,
+            stream=stream or False,
+            stream_cls=Stream[ChatCompletionChunk],
+        )
+
+
+class AsyncCompletions(AsyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> AsyncCompletionsWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/groq/groq-python#accessing-raw-response-data-eg-headers
+        """
+        return AsyncCompletionsWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AsyncCompletionsWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/groq/groq-python#with_streaming_response
+        """
+        return AsyncCompletionsWithStreamingResponse(self)
+
+    @overload
+    async def create(
+        self,
+        *,
+        messages: Iterable[ChatCompletionMessageParam],
+        model: str,
+        exclude_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
+        frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
+        function_call: Optional[completion_create_params.FunctionCall] | NotGiven = NOT_GIVEN,
+        functions: Optional[Iterable[completion_create_params.Function]] | NotGiven = NOT_GIVEN,
+        include_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
+        logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
+        logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
+        max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
+        metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN,
+        n: Optional[int] | NotGiven = NOT_GIVEN,
+        parallel_tool_calls: Optional[bool] | NotGiven = NOT_GIVEN,
+        presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["none", "default"]] | NotGiven = NOT_GIVEN,
+        reasoning_format: Optional[Literal["hidden", "raw", "parsed"]] | NotGiven = NOT_GIVEN,
+        response_format: Optional[completion_create_params.ResponseFormat] | NotGiven = NOT_GIVEN,
+        search_settings: Optional[completion_create_params.SearchSettings] | NotGiven = NOT_GIVEN,
+        seed: Optional[int] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "on_demand", "flex", "performance"]] | NotGiven = NOT_GIVEN,
+        stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
+        store: Optional[bool] | NotGiven = NOT_GIVEN,
+        stream: Optional[Literal[False]] | NotGiven = NOT_GIVEN,
+        temperature: Optional[float] | NotGiven = NOT_GIVEN,
+        tool_choice: Optional[ChatCompletionToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
+        tools: Optional[Iterable[ChatCompletionToolParam]] | NotGiven = NOT_GIVEN,
+        top_logprobs: Optional[int] | NotGiven = NOT_GIVEN,
+        top_p: Optional[float] | NotGiven = NOT_GIVEN,
+        user: Optional[str] | NotGiven = NOT_GIVEN,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> ChatCompletion:
+        ...
+
+    @overload
+    async def create(
+        self,
+        *,
+        messages: Iterable[ChatCompletionMessageParam],
+        model: str,
+        exclude_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
+        frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
+        function_call: Optional[completion_create_params.FunctionCall] | NotGiven = NOT_GIVEN,
+        functions: Optional[Iterable[completion_create_params.Function]] | NotGiven = NOT_GIVEN,
+        include_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
+        logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
+        logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
+        max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
+        metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN,
+        n: Optional[int] | NotGiven = NOT_GIVEN,
+        parallel_tool_calls: Optional[bool] | NotGiven = NOT_GIVEN,
+        presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["none", "default"]] | NotGiven = NOT_GIVEN,
+        reasoning_format: Optional[Literal["hidden", "raw", "parsed"]] | NotGiven = NOT_GIVEN,
+        response_format: Optional[completion_create_params.ResponseFormat] | NotGiven = NOT_GIVEN,
+        search_settings: Optional[completion_create_params.SearchSettings] | NotGiven = NOT_GIVEN,
+        seed: Optional[int] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "on_demand", "flex", "performance"]] | NotGiven = NOT_GIVEN,
+        stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
+        store: Optional[bool] | NotGiven = NOT_GIVEN,
+        stream: Literal[True],
+        temperature: Optional[float] | NotGiven = NOT_GIVEN,
+        tool_choice: Optional[ChatCompletionToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
+        tools: Optional[Iterable[ChatCompletionToolParam]] | NotGiven = NOT_GIVEN,
+        top_logprobs: Optional[int] | NotGiven = NOT_GIVEN,
+        top_p: Optional[float] | NotGiven = NOT_GIVEN,
+        user: Optional[str] | NotGiven = NOT_GIVEN,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> AsyncStream[ChatCompletionChunk]:
+        ...
+
+    @overload
+    async def create(
+        self,
+        *,
+        messages: Iterable[ChatCompletionMessageParam],
+        model: str,
+        exclude_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
+        frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
+        function_call: Optional[completion_create_params.FunctionCall] | NotGiven = NOT_GIVEN,
+        functions: Optional[Iterable[completion_create_params.Function]] | NotGiven = NOT_GIVEN,
+        include_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
+        logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
+        logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
+        max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
+        metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN,
+        n: Optional[int] | NotGiven = NOT_GIVEN,
+        parallel_tool_calls: Optional[bool] | NotGiven = NOT_GIVEN,
+        presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["none", "default"]] | NotGiven = NOT_GIVEN,
+        reasoning_format: Optional[Literal["hidden", "raw", "parsed"]] | NotGiven = NOT_GIVEN,
+        response_format: Optional[completion_create_params.ResponseFormat] | NotGiven = NOT_GIVEN,
+        search_settings: Optional[completion_create_params.SearchSettings] | NotGiven = NOT_GIVEN,
+        seed: Optional[int] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "on_demand", "flex", "performance"]] | NotGiven = NOT_GIVEN,
+        stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
+        store: Optional[bool] | NotGiven = NOT_GIVEN,
+        stream: bool,
+        temperature: Optional[float] | NotGiven = NOT_GIVEN,
+        tool_choice: Optional[ChatCompletionToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
+        tools: Optional[Iterable[ChatCompletionToolParam]] | NotGiven = NOT_GIVEN,
+        top_logprobs: Optional[int] | NotGiven = NOT_GIVEN,
+        top_p: Optional[float] | NotGiven = NOT_GIVEN,
+        user: Optional[str] | NotGiven = NOT_GIVEN,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> ChatCompletion | AsyncStream[ChatCompletionChunk]:
+        ...
+
+    async def create(
+        self,
+        *,
+        messages: Iterable[ChatCompletionMessageParam],
+        model: Union[
+            str,
+            Literal[
+                "gemma2-9b-it",
+                "llama-3.3-70b-versatile",
+                "llama-3.1-8b-instant",
+                "llama-guard-3-8b",
+                "llama3-70b-8192",
+                "llama3-8b-8192",
+            ],
+        ],
+        exclude_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
+        frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
+        function_call: Optional[completion_create_params.FunctionCall] | NotGiven = NOT_GIVEN,
+        functions: Optional[Iterable[completion_create_params.Function]] | NotGiven = NOT_GIVEN,
+        include_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
+        logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
+        logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
+        max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
+        max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
+        metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN,
+        n: Optional[int] | NotGiven = NOT_GIVEN,
+        parallel_tool_calls: Optional[bool] | NotGiven = NOT_GIVEN,
+        presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["none", "default"]] | NotGiven = NOT_GIVEN,
+        reasoning_format: Optional[Literal["hidden", "raw", "parsed"]] | NotGiven = NOT_GIVEN,
+        response_format: Optional[completion_create_params.ResponseFormat] | NotGiven = NOT_GIVEN,
+        search_settings: Optional[completion_create_params.SearchSettings] | NotGiven = NOT_GIVEN,
+        seed: Optional[int] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "on_demand", "flex", "performance"]] | NotGiven = NOT_GIVEN,
+        stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
+        store: Optional[bool] | NotGiven = NOT_GIVEN,
+        stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN,
+        temperature: Optional[float] | NotGiven = NOT_GIVEN,
+        tool_choice: Optional[ChatCompletionToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
+        tools: Optional[Iterable[ChatCompletionToolParam]] | NotGiven = NOT_GIVEN,
+        top_logprobs: Optional[int] | NotGiven = NOT_GIVEN,
+        top_p: Optional[float] | NotGiven = NOT_GIVEN,
+        user: Optional[str] | NotGiven = NOT_GIVEN,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> ChatCompletion | AsyncStream[ChatCompletionChunk]:
+        """
+        Creates a model response for the given chat conversation.
+
+        Args:
+          messages: A list of messages comprising the conversation so far.
+
+          model: ID of the model to use. For details on which models are compatible with the Chat
+              API, see available [models](https://console.groq.com/docs/models)
+
+          exclude_domains: Deprecated: Use search_settings.exclude_domains instead. A list of domains to
+              exclude from the search results when the model uses a web search tool.
+
+          frequency_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on their
+              existing frequency in the text so far, decreasing the model's likelihood to
+              repeat the same line verbatim.
+
+          function_call: Deprecated in favor of `tool_choice`.
+
+              Controls which (if any) function is called by the model. `none` means the model
+              will not call a function and instead generates a message. `auto` means the model
+              can pick between generating a message or calling a function. Specifying a
+              particular function via `{"name": "my_function"}` forces the model to call that
+              function.
+
+              `none` is the default when no functions are present. `auto` is the default if
+              functions are present.
+
+          functions: Deprecated in favor of `tools`.
+
+              A list of functions the model may generate JSON inputs for.
+
+          include_domains: Deprecated: Use search_settings.include_domains instead. A list of domains to
+              include in the search results when the model uses a web search tool.
+
+          logit_bias: This is not yet supported by any of our models. Modify the likelihood of
+              specified tokens appearing in the completion.
+
+          logprobs: This is not yet supported by any of our models. Whether to return log
+              probabilities of the output tokens or not. If true, returns the log
+              probabilities of each output token returned in the `content` of `message`.
+
+          max_completion_tokens: The maximum number of tokens that can be generated in the chat completion. The
+              total length of input tokens and generated tokens is limited by the model's
+              context length.
+
+          max_tokens: Deprecated in favor of `max_completion_tokens`. The maximum number of tokens
+              that can be generated in the chat completion. The total length of input tokens
+              and generated tokens is limited by the model's context length.
+
+          metadata: This parameter is not currently supported.
+
+          n: How many chat completion choices to generate for each input message. Note that
+              the current moment, only n=1 is supported. Other values will result in a 400
+              response.
+
+          parallel_tool_calls: Whether to enable parallel function calling during tool use.
+
+          presence_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on
+              whether they appear in the text so far, increasing the model's likelihood to
+              talk about new topics.
+
+          reasoning_effort: this field is only available for qwen3 models. Set to 'none' to disable
+              reasoning. Set to 'default' or null to let Qwen reason.
+
+          reasoning_format: Specifies how to output reasoning tokens
+
+          response_format: An object specifying the format that the model must output. Setting to
+              `{ "type": "json_schema", "json_schema": {...} }` enables Structured Outputs
+              which ensures the model will match your supplied JSON schema. json_schema
+              response format is only supported on llama 4 models. Setting to
+              `{ "type": "json_object" }` enables the older JSON mode, which ensures the
+              message the model generates is valid JSON. Using `json_schema` is preferred for
+              models that support it.
+
+          search_settings: Settings for web search functionality when the model uses a web search tool.
+
+          seed: If specified, our system will make a best effort to sample deterministically,
+              such that repeated requests with the same `seed` and parameters should return
+              the same result. Determinism is not guaranteed, and you should refer to the
+              `system_fingerprint` response parameter to monitor changes in the backend.
+
+          service_tier: The service tier to use for the request. Defaults to `on_demand`.
+
+              - `auto` will automatically select the highest tier available within the rate
+                limits of your organization.
+              - `flex` uses the flex tier, which will succeed or fail quickly.
+
+          stop: Up to 4 sequences where the API will stop generating further tokens. The
+              returned text will not contain the stop sequence.
+
+          store: This parameter is not currently supported.
+
+          stream: If set, partial message deltas will be sent. Tokens will be sent as data-only
+              [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format)
+              as they become available, with the stream terminated by a `data: [DONE]`
+              message. [Example code](/docs/text-chat#streaming-a-chat-completion).
+
+          temperature: What sampling temperature to use, between 0 and 2. Higher values like 0.8 will
+              make the output more random, while lower values like 0.2 will make it more
+              focused and deterministic. We generally recommend altering this or top_p but not
+              both.
+
+          tool_choice: Controls which (if any) tool is called by the model. `none` means the model will
+              not call any tool and instead generates a message. `auto` means the model can
+              pick between generating a message or calling one or more tools. `required` means
+              the model must call one or more tools. Specifying a particular tool via
+              `{"type": "function", "function": {"name": "my_function"}}` forces the model to
+              call that tool.
+
+              `none` is the default when no tools are present. `auto` is the default if tools
+              are present.
+
+          tools: A list of tools the model may call. Currently, only functions are supported as a
+              tool. Use this to provide a list of functions the model may generate JSON inputs
+              for. A max of 128 functions are supported.
+
+          top_logprobs: This is not yet supported by any of our models. An integer between 0 and 20
+              specifying the number of most likely tokens to return at each token position,
+              each with an associated log probability. `logprobs` must be set to `true` if
+              this parameter is used.
+
+          top_p: An alternative to sampling with temperature, called nucleus sampling, where the
+              model considers the results of the tokens with top_p probability mass. So 0.1
+              means only the tokens comprising the top 10% probability mass are considered. We
+              generally recommend altering this or temperature but not both.
+
+          user: A unique identifier representing your end-user, which can help us monitor and
+              detect abuse.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        return await self._post(
+            "/openai/v1/chat/completions",
+            body=await async_maybe_transform(
+                {
+                    "messages": messages,
+                    "model": model,
+                    "exclude_domains": exclude_domains,
+                    "frequency_penalty": frequency_penalty,
+                    "function_call": function_call,
+                    "functions": functions,
+                    "include_domains": include_domains,
+                    "logit_bias": logit_bias,
+                    "logprobs": logprobs,
+                    "max_completion_tokens": max_completion_tokens,
+                    "max_tokens": max_tokens,
+                    "metadata": metadata,
+                    "n": n,
+                    "parallel_tool_calls": parallel_tool_calls,
+                    "presence_penalty": presence_penalty,
+                    "reasoning_effort": reasoning_effort,
+                    "reasoning_format": reasoning_format,
+                    "response_format": response_format,
+                    "search_settings": search_settings,
+                    "seed": seed,
+                    "service_tier": service_tier,
+                    "stop": stop,
+                    "store": store,
+                    "stream": stream,
+                    "temperature": temperature,
+                    "tool_choice": tool_choice,
+                    "tools": tools,
+                    "top_logprobs": top_logprobs,
+                    "top_p": top_p,
+                    "user": user,
+                },
+                completion_create_params.CompletionCreateParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=ChatCompletion,
+            stream=stream or False,
+            stream_cls=AsyncStream[ChatCompletionChunk],
+        )
+
+
+class CompletionsWithRawResponse:
+    def __init__(self, completions: Completions) -> None:
+        self._completions = completions
+
+        self.create = to_raw_response_wrapper(
+            completions.create,
+        )
+
+
+class AsyncCompletionsWithRawResponse:
+    def __init__(self, completions: AsyncCompletions) -> None:
+        self._completions = completions
+
+        self.create = async_to_raw_response_wrapper(
+            completions.create,
+        )
+
+
+class CompletionsWithStreamingResponse:
+    def __init__(self, completions: Completions) -> None:
+        self._completions = completions
+
+        self.create = to_streamed_response_wrapper(
+            completions.create,
+        )
+
+
+class AsyncCompletionsWithStreamingResponse:
+    def __init__(self, completions: AsyncCompletions) -> None:
+        self._completions = completions
+
+        self.create = async_to_streamed_response_wrapper(
+            completions.create,
+        )

venv/lib/python3.11/site-packages/groq/resources/embeddings.py

@@ -0,0 +1,212 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import List, Union, Optional
+from typing_extensions import Literal
+
+import httpx
+
+from ..types import embedding_create_params
+from .._types import NOT_GIVEN, Body, Query, Headers, NotGiven
+from .._utils import maybe_transform, async_maybe_transform
+from .._compat import cached_property
+from .._resource import SyncAPIResource, AsyncAPIResource
+from .._response import (
+    to_raw_response_wrapper,
+    to_streamed_response_wrapper,
+    async_to_raw_response_wrapper,
+    async_to_streamed_response_wrapper,
+)
+from .._base_client import make_request_options
+from ..types.create_embedding_response import CreateEmbeddingResponse
+
+__all__ = ["Embeddings", "AsyncEmbeddings"]
+
+
+class Embeddings(SyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> EmbeddingsWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/groq/groq-python#accessing-raw-response-data-eg-headers
+        """
+        return EmbeddingsWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> EmbeddingsWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/groq/groq-python#with_streaming_response
+        """
+        return EmbeddingsWithStreamingResponse(self)
+
+    def create(
+        self,
+        *,
+        input: Union[str, List[str]],
+        model: Union[str, Literal["nomic-embed-text-v1_5"]],
+        encoding_format: Literal["float", "base64"] | NotGiven = NOT_GIVEN,
+        user: Optional[str] | NotGiven = NOT_GIVEN,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> CreateEmbeddingResponse:
+        """
+        Creates an embedding vector representing the input text.
+
+        Args:
+          input: Input text to embed, encoded as a string or array of tokens. To embed multiple
+              inputs in a single request, pass an array of strings or array of token arrays.
+              The input must not exceed the max input tokens for the model, cannot be an empty
+              string, and any array must be 2048 dimensions or less.
+
+          model: ID of the model to use.
+
+          encoding_format: The format to return the embeddings in. Can only be `float` or `base64`.
+
+          user: A unique identifier representing your end-user, which can help us monitor and
+              detect abuse.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        return self._post(
+            "/openai/v1/embeddings",
+            body=maybe_transform(
+                {
+                    "input": input,
+                    "model": model,
+                    "encoding_format": encoding_format,
+                    "user": user,
+                },
+                embedding_create_params.EmbeddingCreateParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=CreateEmbeddingResponse,
+        )
+
+
+class AsyncEmbeddings(AsyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> AsyncEmbeddingsWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/groq/groq-python#accessing-raw-response-data-eg-headers
+        """
+        return AsyncEmbeddingsWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AsyncEmbeddingsWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/groq/groq-python#with_streaming_response
+        """
+        return AsyncEmbeddingsWithStreamingResponse(self)
+
+    async def create(
+        self,
+        *,
+        input: Union[str, List[str]],
+        model: Union[str, Literal["nomic-embed-text-v1_5"]],
+        encoding_format: Literal["float", "base64"] | NotGiven = NOT_GIVEN,
+        user: Optional[str] | NotGiven = NOT_GIVEN,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> CreateEmbeddingResponse:
+        """
+        Creates an embedding vector representing the input text.
+
+        Args:
+          input: Input text to embed, encoded as a string or array of tokens. To embed multiple
+              inputs in a single request, pass an array of strings or array of token arrays.
+              The input must not exceed the max input tokens for the model, cannot be an empty
+              string, and any array must be 2048 dimensions or less.
+
+          model: ID of the model to use.
+
+          encoding_format: The format to return the embeddings in. Can only be `float` or `base64`.
+
+          user: A unique identifier representing your end-user, which can help us monitor and
+              detect abuse.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        return await self._post(
+            "/openai/v1/embeddings",
+            body=await async_maybe_transform(
+                {
+                    "input": input,
+                    "model": model,
+                    "encoding_format": encoding_format,
+                    "user": user,
+                },
+                embedding_create_params.EmbeddingCreateParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=CreateEmbeddingResponse,
+        )
+
+
+class EmbeddingsWithRawResponse:
+    def __init__(self, embeddings: Embeddings) -> None:
+        self._embeddings = embeddings
+
+        self.create = to_raw_response_wrapper(
+            embeddings.create,
+        )
+
+
+class AsyncEmbeddingsWithRawResponse:
+    def __init__(self, embeddings: AsyncEmbeddings) -> None:
+        self._embeddings = embeddings
+
+        self.create = async_to_raw_response_wrapper(
+            embeddings.create,
+        )
+
+
+class EmbeddingsWithStreamingResponse:
+    def __init__(self, embeddings: Embeddings) -> None:
+        self._embeddings = embeddings
+
+        self.create = to_streamed_response_wrapper(
+            embeddings.create,
+        )
+
+
+class AsyncEmbeddingsWithStreamingResponse:
+    def __init__(self, embeddings: AsyncEmbeddings) -> None:
+        self._embeddings = embeddings
+
+        self.create = async_to_streamed_response_wrapper(
+            embeddings.create,
+        )

venv/lib/python3.11/site-packages/groq/resources/files.py

@@ -0,0 +1,513 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Mapping, cast
+from typing_extensions import Literal
+
+import httpx
+
+from ..types import file_create_params
+from .._types import NOT_GIVEN, Body, Query, Headers, NotGiven, FileTypes
+from .._utils import extract_files, maybe_transform, deepcopy_minimal, async_maybe_transform
+from .._compat import cached_property
+from .._resource import SyncAPIResource, AsyncAPIResource
+from .._response import (
+    BinaryAPIResponse,
+    AsyncBinaryAPIResponse,
+    StreamedBinaryAPIResponse,
+    AsyncStreamedBinaryAPIResponse,
+    to_raw_response_wrapper,
+    to_streamed_response_wrapper,
+    async_to_raw_response_wrapper,
+    to_custom_raw_response_wrapper,
+    async_to_streamed_response_wrapper,
+    to_custom_streamed_response_wrapper,
+    async_to_custom_raw_response_wrapper,
+    async_to_custom_streamed_response_wrapper,
+)
+from .._base_client import make_request_options
+from ..types.file_info_response import FileInfoResponse
+from ..types.file_list_response import FileListResponse
+from ..types.file_create_response import FileCreateResponse
+from ..types.file_delete_response import FileDeleteResponse
+
+__all__ = ["Files", "AsyncFiles"]
+
+
+class Files(SyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> FilesWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/groq/groq-python#accessing-raw-response-data-eg-headers
+        """
+        return FilesWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> FilesWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/groq/groq-python#with_streaming_response
+        """
+        return FilesWithStreamingResponse(self)
+
+    def create(
+        self,
+        *,
+        file: FileTypes,
+        purpose: Literal["batch"],
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> FileCreateResponse:
+        """
+        Upload a file that can be used across various endpoints.
+
+        The Batch API only supports `.jsonl` files up to 100 MB in size. The input also
+        has a specific required [format](/docs/batch).
+
+        Please contact us if you need to increase these storage limits.
+
+        Args:
+          file: The File object (not file name) to be uploaded.
+
+          purpose: The intended purpose of the uploaded file. Use "batch" for
+              [Batch API](/docs/api-reference#batches).
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        body = deepcopy_minimal(
+            {
+                "file": file,
+                "purpose": purpose,
+            }
+        )
+        files = extract_files(cast(Mapping[str, object], body), paths=[["file"]])
+        # It should be noted that the actual Content-Type header that will be
+        # sent to the server will contain a `boundary` parameter, e.g.
+        # multipart/form-data; boundary=---abc--
+        extra_headers = {"Content-Type": "multipart/form-data", **(extra_headers or {})}
+        return self._post(
+            "/openai/v1/files",
+            body=maybe_transform(body, file_create_params.FileCreateParams),
+            files=files,
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=FileCreateResponse,
+        )
+
+    def list(
+        self,
+        *,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> FileListResponse:
+        """Returns a list of files."""
+        return self._get(
+            "/openai/v1/files",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=FileListResponse,
+        )
+
+    def delete(
+        self,
+        file_id: str,
+        *,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> FileDeleteResponse:
+        """
+        Delete a file.
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not file_id:
+            raise ValueError(f"Expected a non-empty value for `file_id` but received {file_id!r}")
+        return self._delete(
+            f"/openai/v1/files/{file_id}",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=FileDeleteResponse,
+        )
+
+    def content(
+        self,
+        file_id: str,
+        *,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> BinaryAPIResponse:
+        """
+        Returns the contents of the specified file.
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not file_id:
+            raise ValueError(f"Expected a non-empty value for `file_id` but received {file_id!r}")
+        extra_headers = {"Accept": "application/octet-stream", **(extra_headers or {})}
+        return self._get(
+            f"/openai/v1/files/{file_id}/content",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=BinaryAPIResponse,
+        )
+
+    def info(
+        self,
+        file_id: str,
+        *,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> FileInfoResponse:
+        """
+        Returns information about a file.
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not file_id:
+            raise ValueError(f"Expected a non-empty value for `file_id` but received {file_id!r}")
+        return self._get(
+            f"/openai/v1/files/{file_id}",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=FileInfoResponse,
+        )
+
+
+class AsyncFiles(AsyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> AsyncFilesWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/groq/groq-python#accessing-raw-response-data-eg-headers
+        """
+        return AsyncFilesWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AsyncFilesWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/groq/groq-python#with_streaming_response
+        """
+        return AsyncFilesWithStreamingResponse(self)
+
+    async def create(
+        self,
+        *,
+        file: FileTypes,
+        purpose: Literal["batch"],
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> FileCreateResponse:
+        """
+        Upload a file that can be used across various endpoints.
+
+        The Batch API only supports `.jsonl` files up to 100 MB in size. The input also
+        has a specific required [format](/docs/batch).
+
+        Please contact us if you need to increase these storage limits.
+
+        Args:
+          file: The File object (not file name) to be uploaded.
+
+          purpose: The intended purpose of the uploaded file. Use "batch" for
+              [Batch API](/docs/api-reference#batches).
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        body = deepcopy_minimal(
+            {
+                "file": file,
+                "purpose": purpose,
+            }
+        )
+        files = extract_files(cast(Mapping[str, object], body), paths=[["file"]])
+        # It should be noted that the actual Content-Type header that will be
+        # sent to the server will contain a `boundary` parameter, e.g.
+        # multipart/form-data; boundary=---abc--
+        extra_headers = {"Content-Type": "multipart/form-data", **(extra_headers or {})}
+        return await self._post(
+            "/openai/v1/files",
+            body=await async_maybe_transform(body, file_create_params.FileCreateParams),
+            files=files,
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=FileCreateResponse,
+        )
+
+    async def list(
+        self,
+        *,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> FileListResponse:
+        """Returns a list of files."""
+        return await self._get(
+            "/openai/v1/files",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=FileListResponse,
+        )
+
+    async def delete(
+        self,
+        file_id: str,
+        *,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> FileDeleteResponse:
+        """
+        Delete a file.
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not file_id:
+            raise ValueError(f"Expected a non-empty value for `file_id` but received {file_id!r}")
+        return await self._delete(
+            f"/openai/v1/files/{file_id}",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=FileDeleteResponse,
+        )
+
+    async def content(
+        self,
+        file_id: str,
+        *,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> AsyncBinaryAPIResponse:
+        """
+        Returns the contents of the specified file.
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not file_id:
+            raise ValueError(f"Expected a non-empty value for `file_id` but received {file_id!r}")
+        extra_headers = {"Accept": "application/octet-stream", **(extra_headers or {})}
+        return await self._get(
+            f"/openai/v1/files/{file_id}/content",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=AsyncBinaryAPIResponse,
+        )
+
+    async def info(
+        self,
+        file_id: str,
+        *,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> FileInfoResponse:
+        """
+        Returns information about a file.
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not file_id:
+            raise ValueError(f"Expected a non-empty value for `file_id` but received {file_id!r}")
+        return await self._get(
+            f"/openai/v1/files/{file_id}",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=FileInfoResponse,
+        )
+
+
+class FilesWithRawResponse:
+    def __init__(self, files: Files) -> None:
+        self._files = files
+
+        self.create = to_raw_response_wrapper(
+            files.create,
+        )
+        self.list = to_raw_response_wrapper(
+            files.list,
+        )
+        self.delete = to_raw_response_wrapper(
+            files.delete,
+        )
+        self.content = to_custom_raw_response_wrapper(
+            files.content,
+            BinaryAPIResponse,
+        )
+        self.info = to_raw_response_wrapper(
+            files.info,
+        )
+
+
+class AsyncFilesWithRawResponse:
+    def __init__(self, files: AsyncFiles) -> None:
+        self._files = files
+
+        self.create = async_to_raw_response_wrapper(
+            files.create,
+        )
+        self.list = async_to_raw_response_wrapper(
+            files.list,
+        )
+        self.delete = async_to_raw_response_wrapper(
+            files.delete,
+        )
+        self.content = async_to_custom_raw_response_wrapper(
+            files.content,
+            AsyncBinaryAPIResponse,
+        )
+        self.info = async_to_raw_response_wrapper(
+            files.info,
+        )
+
+
+class FilesWithStreamingResponse:
+    def __init__(self, files: Files) -> None:
+        self._files = files
+
+        self.create = to_streamed_response_wrapper(
+            files.create,
+        )
+        self.list = to_streamed_response_wrapper(
+            files.list,
+        )
+        self.delete = to_streamed_response_wrapper(
+            files.delete,
+        )
+        self.content = to_custom_streamed_response_wrapper(
+            files.content,
+            StreamedBinaryAPIResponse,
+        )
+        self.info = to_streamed_response_wrapper(
+            files.info,
+        )
+
+
+class AsyncFilesWithStreamingResponse:
+    def __init__(self, files: AsyncFiles) -> None:
+        self._files = files
+
+        self.create = async_to_streamed_response_wrapper(
+            files.create,
+        )
+        self.list = async_to_streamed_response_wrapper(
+            files.list,
+        )
+        self.delete = async_to_streamed_response_wrapper(
+            files.delete,
+        )
+        self.content = async_to_custom_streamed_response_wrapper(
+            files.content,
+            AsyncStreamedBinaryAPIResponse,
+        )
+        self.info = async_to_streamed_response_wrapper(
+            files.info,
+        )

venv/lib/python3.11/site-packages/groq/resources/models.py

@@ -0,0 +1,293 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+import httpx
+
+from .._types import NOT_GIVEN, Body, Query, Headers, NotGiven
+from .._compat import cached_property
+from .._resource import SyncAPIResource, AsyncAPIResource
+from .._response import (
+    to_raw_response_wrapper,
+    to_streamed_response_wrapper,
+    async_to_raw_response_wrapper,
+    async_to_streamed_response_wrapper,
+)
+from ..types.model import Model
+from .._base_client import make_request_options
+from ..types.model_deleted import ModelDeleted
+from ..types.model_list_response import ModelListResponse
+
+__all__ = ["Models", "AsyncModels"]
+
+
+class Models(SyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> ModelsWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/groq/groq-python#accessing-raw-response-data-eg-headers
+        """
+        return ModelsWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> ModelsWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/groq/groq-python#with_streaming_response
+        """
+        return ModelsWithStreamingResponse(self)
+
+    def retrieve(
+        self,
+        model: str,
+        *,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> Model:
+        """
+        Get a specific model
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not model:
+            raise ValueError(f"Expected a non-empty value for `model` but received {model!r}")
+        return self._get(
+            f"/openai/v1/models/{model}",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=Model,
+        )
+
+    def list(
+        self,
+        *,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> ModelListResponse:
+        """get all available models"""
+        return self._get(
+            "/openai/v1/models",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=ModelListResponse,
+        )
+
+    def delete(
+        self,
+        model: str,
+        *,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> ModelDeleted:
+        """
+        Delete a model
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not model:
+            raise ValueError(f"Expected a non-empty value for `model` but received {model!r}")
+        return self._delete(
+            f"/openai/v1/models/{model}",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=ModelDeleted,
+        )
+
+
+class AsyncModels(AsyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> AsyncModelsWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/groq/groq-python#accessing-raw-response-data-eg-headers
+        """
+        return AsyncModelsWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AsyncModelsWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/groq/groq-python#with_streaming_response
+        """
+        return AsyncModelsWithStreamingResponse(self)
+
+    async def retrieve(
+        self,
+        model: str,
+        *,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> Model:
+        """
+        Get a specific model
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not model:
+            raise ValueError(f"Expected a non-empty value for `model` but received {model!r}")
+        return await self._get(
+            f"/openai/v1/models/{model}",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=Model,
+        )
+
+    async def list(
+        self,
+        *,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> ModelListResponse:
+        """get all available models"""
+        return await self._get(
+            "/openai/v1/models",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=ModelListResponse,
+        )
+
+    async def delete(
+        self,
+        model: str,
+        *,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> ModelDeleted:
+        """
+        Delete a model
+
+        Args:
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not model:
+            raise ValueError(f"Expected a non-empty value for `model` but received {model!r}")
+        return await self._delete(
+            f"/openai/v1/models/{model}",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=ModelDeleted,
+        )
+
+
+class ModelsWithRawResponse:
+    def __init__(self, models: Models) -> None:
+        self._models = models
+
+        self.retrieve = to_raw_response_wrapper(
+            models.retrieve,
+        )
+        self.list = to_raw_response_wrapper(
+            models.list,
+        )
+        self.delete = to_raw_response_wrapper(
+            models.delete,
+        )
+
+
+class AsyncModelsWithRawResponse:
+    def __init__(self, models: AsyncModels) -> None:
+        self._models = models
+
+        self.retrieve = async_to_raw_response_wrapper(
+            models.retrieve,
+        )
+        self.list = async_to_raw_response_wrapper(
+            models.list,
+        )
+        self.delete = async_to_raw_response_wrapper(
+            models.delete,
+        )
+
+
+class ModelsWithStreamingResponse:
+    def __init__(self, models: Models) -> None:
+        self._models = models
+
+        self.retrieve = to_streamed_response_wrapper(
+            models.retrieve,
+        )
+        self.list = to_streamed_response_wrapper(
+            models.list,
+        )
+        self.delete = to_streamed_response_wrapper(
+            models.delete,
+        )
+
+
+class AsyncModelsWithStreamingResponse:
+    def __init__(self, models: AsyncModels) -> None:
+        self._models = models
+
+        self.retrieve = async_to_streamed_response_wrapper(
+            models.retrieve,
+        )
+        self.list = async_to_streamed_response_wrapper(
+            models.list,
+        )
+        self.delete = async_to_streamed_response_wrapper(
+            models.delete,
+        )

venv/lib/python3.11/site-packages/groq/types/__init__.py

@@ -0,0 +1,26 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from .model import Model as Model
+from .shared import (
+    ErrorObject as ErrorObject,
+    FunctionDefinition as FunctionDefinition,
+    FunctionParameters as FunctionParameters,
+)
+from .embedding import Embedding as Embedding
+from .model_deleted import ModelDeleted as ModelDeleted
+from .completion_usage import CompletionUsage as CompletionUsage
+from .file_create_params import FileCreateParams as FileCreateParams
+from .file_info_response import FileInfoResponse as FileInfoResponse
+from .file_list_response import FileListResponse as FileListResponse
+from .batch_create_params import BatchCreateParams as BatchCreateParams
+from .batch_list_response import BatchListResponse as BatchListResponse
+from .model_list_response import ModelListResponse as ModelListResponse
+from .file_create_response import FileCreateResponse as FileCreateResponse
+from .file_delete_response import FileDeleteResponse as FileDeleteResponse
+from .batch_cancel_response import BatchCancelResponse as BatchCancelResponse
+from .batch_create_response import BatchCreateResponse as BatchCreateResponse
+from .batch_retrieve_response import BatchRetrieveResponse as BatchRetrieveResponse
+from .embedding_create_params import EmbeddingCreateParams as EmbeddingCreateParams
+from .create_embedding_response import CreateEmbeddingResponse as CreateEmbeddingResponse

venv/lib/python3.11/site-packages/groq/types/audio/__init__.py

@@ -0,0 +1,9 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from .translation import Translation as Translation
+from .transcription import Transcription as Transcription
+from .speech_create_params import SpeechCreateParams as SpeechCreateParams
+from .translation_create_params import TranslationCreateParams as TranslationCreateParams
+from .transcription_create_params import TranscriptionCreateParams as TranscriptionCreateParams