sarvamai 0.1.5a4__py3-none-any.whl → 0.1.5a5__py3-none-any.whl

sarvamai/__init__.py

@@ -1,6 +1,11 @@
 # This file was auto-generated by Fern from our API Definition.
 
+# isort: skip_file
+
 from .types import (
+    AudioData,
+    AudioDataEncoding,
+    AudioMessage,
     ChatCompletionRequestAssistantMessage,
     ChatCompletionRequestMessage,
     ChatCompletionRequestMessage_Assistant,
@@ -15,9 +20,12 @@ from .types import (
     DiarizedEntry,
     DiarizedTranscript,
     ErrorCode,
+    ErrorData,
     ErrorDetails,
     ErrorMessage,
+    EventsData,
     FinishReason,
+    Format,
     LanguageIdentificationResponse,
     NumeralsFormat,
     ReasoningEffort,
@@ -27,6 +35,9 @@ from .types import (
     SpeechToTextLanguage,
     SpeechToTextModel,
     SpeechToTextResponse,
+    SpeechToTextStreamingResponse,
+    SpeechToTextStreamingResponseData,
+    SpeechToTextStreamingResponseType,
     SpeechToTextTranslateLanguage,
     SpeechToTextTranslateModel,
     SpeechToTextTranslateResponse,
@@ -37,6 +48,8 @@ from .types import (
     TextToSpeechResponse,
     TextToSpeechSpeaker,
     TimestampsModel,
+    TranscriptionData,
+    TranscriptionMetrics,
     TranslateMode,
     TranslateModel,
     TranslateSourceLanguage,
@@ -56,10 +69,12 @@ from .errors import (
     TooManyRequestsError,
     UnprocessableEntityError,
 )
-from . import chat, speech_to_text, text, text_to_speech
+from . import chat, speech_to_text, speech_to_text_streaming, text, text_to_speech
 from .client import AsyncSarvamAI, SarvamAI
 from .environment import SarvamAIEnvironment
 from .requests import (
+    AudioDataParams,
+    AudioMessageParams,
     ChatCompletionRequestAssistantMessageParams,
     ChatCompletionRequestMessageParams,
     ChatCompletionRequestMessage_AssistantParams,
@@ -73,21 +88,33 @@ from .requests import (
     CreateChatCompletionResponseParams,
     DiarizedEntryParams,
     DiarizedTranscriptParams,
+    ErrorDataParams,
     ErrorDetailsParams,
     ErrorMessageParams,
+    EventsDataParams,
     LanguageIdentificationResponseParams,
     SpeechToTextResponseParams,
+    SpeechToTextStreamingResponseDataParams,
+    SpeechToTextStreamingResponseParams,
     SpeechToTextTranslateResponseParams,
     StopConfigurationParams,
     TextToSpeechResponseParams,
     TimestampsModelParams,
+    TranscriptionDataParams,
+    TranscriptionMetricsParams,
     TranslationResponseParams,
     TransliterationResponseParams,
 )
+from .speech_to_text_streaming import SpeechToTextStreamingLanguageCode, SpeechToTextStreamingModel
 from .version import __version__
 
 __all__ = [
     "AsyncSarvamAI",
+    "AudioData",
+    "AudioDataEncoding",
+    "AudioDataParams",
+    "AudioMessage",
+    "AudioMessageParams",
     "BadRequestError",
     "ChatCompletionRequestAssistantMessage",
     "ChatCompletionRequestAssistantMessageParams",
@@ -116,12 +143,17 @@ __all__ = [
     "DiarizedTranscript",
     "DiarizedTranscriptParams",
     "ErrorCode",
+    "ErrorData",
+    "ErrorDataParams",
     "ErrorDetails",
     "ErrorDetailsParams",
     "ErrorMessage",
     "ErrorMessageParams",
+    "EventsData",
+    "EventsDataParams",
     "FinishReason",
     "ForbiddenError",
+    "Format",
     "InternalServerError",
     "LanguageIdentificationResponse",
     "LanguageIdentificationResponseParams",
@@ -137,6 +169,13 @@ __all__ = [
     "SpeechToTextModel",
     "SpeechToTextResponse",
     "SpeechToTextResponseParams",
+    "SpeechToTextStreamingLanguageCode",
+    "SpeechToTextStreamingModel",
+    "SpeechToTextStreamingResponse",
+    "SpeechToTextStreamingResponseData",
+    "SpeechToTextStreamingResponseDataParams",
+    "SpeechToTextStreamingResponseParams",
+    "SpeechToTextStreamingResponseType",
     "SpeechToTextTranslateLanguage",
     "SpeechToTextTranslateModel",
     "SpeechToTextTranslateResponse",
@@ -152,6 +191,10 @@ __all__ = [
     "TimestampsModel",
     "TimestampsModelParams",
     "TooManyRequestsError",
+    "TranscriptionData",
+    "TranscriptionDataParams",
+    "TranscriptionMetrics",
+    "TranscriptionMetricsParams",
     "TranslateMode",
     "TranslateModel",
     "TranslateSourceLanguage",
@@ -168,6 +211,7 @@ __all__ = [
     "__version__",
     "chat",
     "speech_to_text",
+    "speech_to_text_streaming",
     "text",
     "text_to_speech",
 ]

sarvamai/chat/__init__.py

@@ -1,2 +1,4 @@
 # This file was auto-generated by Fern from our API Definition.
 
+# isort: skip_file
+

sarvamai/chat/client.py

@@ -1,15 +1,14 @@
 # This file was auto-generated by Fern from our API Definition.
 
 import typing
-from ..core.client_wrapper import SyncClientWrapper
-from .raw_client import RawChatClient
+
+from ..core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
+from ..core.request_options import RequestOptions
 from ..requests.chat_completion_request_message import ChatCompletionRequestMessageParams
-from ..types.reasoning_effort import ReasoningEffort
 from ..requests.stop_configuration import StopConfigurationParams
-from ..core.request_options import RequestOptions
 from ..types.create_chat_completion_response import CreateChatCompletionResponse
-from ..core.client_wrapper import AsyncClientWrapper
-from .raw_client import AsyncRawChatClient
+from ..types.reasoning_effort import ReasoningEffort
+from .raw_client import AsyncRawChatClient, RawChatClient
 
 # this is used as the default value for optional parameters
 OMIT = typing.cast(typing.Any, ...)
@@ -84,7 +83,6 @@ class ChatClient:
         seed : typing.Optional[int]
             This feature is in Beta.
             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.
 
         frequency_penalty : typing.Optional[float]
             Number between -2.0 and 2.0. Positive values penalize new tokens based on
@@ -118,7 +116,7 @@ class ChatClient:
             messages=[{"content": "content", "role": "assistant"}],
         )
         """
-        response = self._raw_client.completions(
+        _response = self._raw_client.completions(
             messages=messages,
             temperature=temperature,
             top_p=top_p,
@@ -133,7 +131,7 @@ class ChatClient:
             wiki_grounding=wiki_grounding,
             request_options=request_options,
         )
-        return response.data
+        return _response.data
 
 
 class AsyncChatClient:
@@ -205,7 +203,6 @@ class AsyncChatClient:
         seed : typing.Optional[int]
             This feature is in Beta.
             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.
 
         frequency_penalty : typing.Optional[float]
             Number between -2.0 and 2.0. Positive values penalize new tokens based on
@@ -247,7 +244,7 @@ class AsyncChatClient:
 
         asyncio.run(main())
         """
-        response = await self._raw_client.completions(
+        _response = await self._raw_client.completions(
             messages=messages,
             temperature=temperature,
             top_p=top_p,
@@ -262,4 +259,4 @@ class AsyncChatClient:
             wiki_grounding=wiki_grounding,
             request_options=request_options,
         )
-        return response.data
+        return _response.data

sarvamai/chat/raw_client.py

@@ -1,24 +1,23 @@
 # This file was auto-generated by Fern from our API Definition.
 
 import typing
-from ..core.client_wrapper import SyncClientWrapper
-from ..requests.chat_completion_request_message import ChatCompletionRequestMessageParams
-from ..types.reasoning_effort import ReasoningEffort
-from ..requests.stop_configuration import StopConfigurationParams
+from json.decoder import JSONDecodeError
+
+from ..core.api_error import ApiError
+from ..core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
+from ..core.http_response import AsyncHttpResponse, HttpResponse
+from ..core.pydantic_utilities import parse_obj_as
 from ..core.request_options import RequestOptions
-from ..core.http_response import HttpResponse
-from ..types.create_chat_completion_response import CreateChatCompletionResponse
 from ..core.serialization import convert_and_respect_annotation_metadata
-from ..core.pydantic_utilities import parse_obj_as
 from ..errors.bad_request_error import BadRequestError
 from ..errors.forbidden_error import ForbiddenError
-from ..errors.unprocessable_entity_error import UnprocessableEntityError
-from ..errors.too_many_requests_error import TooManyRequestsError
 from ..errors.internal_server_error import InternalServerError
-from json.decoder import JSONDecodeError
-from ..core.api_error import ApiError
-from ..core.client_wrapper import AsyncClientWrapper
-from ..core.http_response import AsyncHttpResponse
+from ..errors.too_many_requests_error import TooManyRequestsError
+from ..errors.unprocessable_entity_error import UnprocessableEntityError
+from ..requests.chat_completion_request_message import ChatCompletionRequestMessageParams
+from ..requests.stop_configuration import StopConfigurationParams
+from ..types.create_chat_completion_response import CreateChatCompletionResponse
+from ..types.reasoning_effort import ReasoningEffort
 
 # this is used as the default value for optional parameters
 OMIT = typing.cast(typing.Any, ...)
@@ -82,7 +81,6 @@ class RawChatClient:
         seed : typing.Optional[int]
             This feature is in Beta.
             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.
 
         frequency_penalty : typing.Optional[float]
             Number between -2.0 and 2.0. Positive values penalize new tokens based on
@@ -107,6 +105,7 @@ class RawChatClient:
         """
         _response = self._client_wrapper.httpx_client.request(
             "v1/chat/completions",
+            base_url=self._client_wrapper.get_environment().base,
             method="POST",
             json={
                 "messages": convert_and_respect_annotation_metadata(
@@ -145,58 +144,63 @@ class RawChatClient:
                 return HttpResponse(response=_response, data=_data)
             if _response.status_code == 400:
                 raise BadRequestError(
-                    typing.cast(
+                    headers=dict(_response.headers),
+                    body=typing.cast(
                         typing.Optional[typing.Any],
                         parse_obj_as(
                             type_=typing.Optional[typing.Any],  # type: ignore
                             object_=_response.json(),
                         ),
-                    )
+                    ),
                 )
             if _response.status_code == 403:
                 raise ForbiddenError(
-                    typing.cast(
+                    headers=dict(_response.headers),
+                    body=typing.cast(
                         typing.Optional[typing.Any],
                         parse_obj_as(
                             type_=typing.Optional[typing.Any],  # type: ignore
                             object_=_response.json(),
                         ),
-                    )
+                    ),
                 )
             if _response.status_code == 422:
                 raise UnprocessableEntityError(
-                    typing.cast(
+                    headers=dict(_response.headers),
+                    body=typing.cast(
                         typing.Optional[typing.Any],
                         parse_obj_as(
                             type_=typing.Optional[typing.Any],  # type: ignore
                             object_=_response.json(),
                         ),
-                    )
+                    ),
                 )
             if _response.status_code == 429:
                 raise TooManyRequestsError(
-                    typing.cast(
+                    headers=dict(_response.headers),
+                    body=typing.cast(
                         typing.Optional[typing.Any],
                         parse_obj_as(
                             type_=typing.Optional[typing.Any],  # type: ignore
                             object_=_response.json(),
                         ),
-                    )
+                    ),
                 )
             if _response.status_code == 500:
                 raise InternalServerError(
-                    typing.cast(
+                    headers=dict(_response.headers),
+                    body=typing.cast(
                         typing.Optional[typing.Any],
                         parse_obj_as(
                             type_=typing.Optional[typing.Any],  # type: ignore
                             object_=_response.json(),
                         ),
-                    )
+                    ),
                 )
             _response_json = _response.json()
         except JSONDecodeError:
-            raise ApiError(status_code=_response.status_code, body=_response.text)
-        raise ApiError(status_code=_response.status_code, body=_response_json)
+            raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
 
 
 class AsyncRawChatClient:
@@ -257,7 +261,6 @@ class AsyncRawChatClient:
         seed : typing.Optional[int]
             This feature is in Beta.
             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.
 
         frequency_penalty : typing.Optional[float]
             Number between -2.0 and 2.0. Positive values penalize new tokens based on
@@ -282,6 +285,7 @@ class AsyncRawChatClient:
         """
         _response = await self._client_wrapper.httpx_client.request(
             "v1/chat/completions",
+            base_url=self._client_wrapper.get_environment().base,
             method="POST",
             json={
                 "messages": convert_and_respect_annotation_metadata(
@@ -320,55 +324,60 @@ class AsyncRawChatClient:
                 return AsyncHttpResponse(response=_response, data=_data)
             if _response.status_code == 400:
                 raise BadRequestError(
-                    typing.cast(
+                    headers=dict(_response.headers),
+                    body=typing.cast(
                         typing.Optional[typing.Any],
                         parse_obj_as(
                             type_=typing.Optional[typing.Any],  # type: ignore
                             object_=_response.json(),
                         ),
-                    )
+                    ),
                 )
             if _response.status_code == 403:
                 raise ForbiddenError(
-                    typing.cast(
+                    headers=dict(_response.headers),
+                    body=typing.cast(
                         typing.Optional[typing.Any],
                         parse_obj_as(
                             type_=typing.Optional[typing.Any],  # type: ignore
                             object_=_response.json(),
                         ),
-                    )
+                    ),
                 )
             if _response.status_code == 422:
                 raise UnprocessableEntityError(
-                    typing.cast(
+                    headers=dict(_response.headers),
+                    body=typing.cast(
                         typing.Optional[typing.Any],
                         parse_obj_as(
                             type_=typing.Optional[typing.Any],  # type: ignore
                             object_=_response.json(),
                         ),
-                    )
+                    ),
                 )
             if _response.status_code == 429:
                 raise TooManyRequestsError(
-                    typing.cast(
+                    headers=dict(_response.headers),
+                    body=typing.cast(
                         typing.Optional[typing.Any],
                         parse_obj_as(
                             type_=typing.Optional[typing.Any],  # type: ignore
                             object_=_response.json(),
                         ),
-                    )
+                    ),
                 )
             if _response.status_code == 500:
                 raise InternalServerError(
-                    typing.cast(
+                    headers=dict(_response.headers),
+                    body=typing.cast(
                         typing.Optional[typing.Any],
                         parse_obj_as(
                             type_=typing.Optional[typing.Any],  # type: ignore
                             object_=_response.json(),
                         ),
-                    )
+                    ),
                 )
             _response_json = _response.json()
         except JSONDecodeError:
-            raise ApiError(status_code=_response.status_code, body=_response.text)
-        raise ApiError(status_code=_response.status_code, body=_response_json)
+            raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)

sarvamai/client.py

@@ -1,20 +1,17 @@
 # This file was auto-generated by Fern from our API Definition.
 
-import typing
-from .environment import SarvamAIEnvironment
 import os
+import typing
+
 import httpx
+from .chat.client import AsyncChatClient, ChatClient
 from .core.api_error import ApiError
-from .core.client_wrapper import SyncClientWrapper
-from .text.client import TextClient
-from .speech_to_text.client import SpeechToTextClient
-from .text_to_speech.client import TextToSpeechClient
-from .chat.client import ChatClient
-from .core.client_wrapper import AsyncClientWrapper
-from .text.client import AsyncTextClient
-from .speech_to_text.client import AsyncSpeechToTextClient
-from .text_to_speech.client import AsyncTextToSpeechClient
-from .chat.client import AsyncChatClient
+from .core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
+from .environment import SarvamAIEnvironment
+from .speech_to_text.client import AsyncSpeechToTextClient, SpeechToTextClient
+from .speech_to_text_streaming.client import AsyncSpeechToTextStreamingClient, SpeechToTextStreamingClient
+from .text.client import AsyncTextClient, TextClient
+from .text_to_speech.client import AsyncTextToSpeechClient, TextToSpeechClient
 
 
 class SarvamAI:
@@ -23,9 +20,6 @@ class SarvamAI:
 
     Parameters
     ----------
-    base_url : typing.Optional[str]
-        The base url to use for requests from the client.
-
     environment : SarvamAIEnvironment
         The environment to use for requests from the client. from .environment import SarvamAIEnvironment
 
@@ -57,7 +51,6 @@ class SarvamAI:
     def __init__(
         self,
         *,
-        base_url: typing.Optional[str] = None,
         environment: SarvamAIEnvironment = SarvamAIEnvironment.PRODUCTION,
         api_subscription_key: typing.Optional[str] = os.getenv("SARVAM_API_KEY"),
         timeout: typing.Optional[float] = None,
@@ -72,7 +65,7 @@ class SarvamAI:
                 body="The client must be instantiated be either passing in api_subscription_key or setting SARVAM_API_KEY"
             )
         self._client_wrapper = SyncClientWrapper(
-            base_url=_get_base_url(base_url=base_url, environment=environment),
+            environment=environment,
             api_subscription_key=api_subscription_key,
             httpx_client=httpx_client
             if httpx_client is not None
@@ -85,6 +78,7 @@ class SarvamAI:
         self.speech_to_text = SpeechToTextClient(client_wrapper=self._client_wrapper)
         self.text_to_speech = TextToSpeechClient(client_wrapper=self._client_wrapper)
         self.chat = ChatClient(client_wrapper=self._client_wrapper)
+        self.speech_to_text_streaming = SpeechToTextStreamingClient(client_wrapper=self._client_wrapper)
 
 
 class AsyncSarvamAI:
@@ -93,9 +87,6 @@ class AsyncSarvamAI:
 
     Parameters
     ----------
-    base_url : typing.Optional[str]
-        The base url to use for requests from the client.
-
     environment : SarvamAIEnvironment
         The environment to use for requests from the client. from .environment import SarvamAIEnvironment
 
@@ -127,7 +118,6 @@ class AsyncSarvamAI:
     def __init__(
         self,
         *,
-        base_url: typing.Optional[str] = None,
         environment: SarvamAIEnvironment = SarvamAIEnvironment.PRODUCTION,
         api_subscription_key: typing.Optional[str] = os.getenv("SARVAM_API_KEY"),
         timeout: typing.Optional[float] = None,
@@ -142,7 +132,7 @@ class AsyncSarvamAI:
                 body="The client must be instantiated be either passing in api_subscription_key or setting SARVAM_API_KEY"
             )
         self._client_wrapper = AsyncClientWrapper(
-            base_url=_get_base_url(base_url=base_url, environment=environment),
+            environment=environment,
             api_subscription_key=api_subscription_key,
             httpx_client=httpx_client
             if httpx_client is not None
@@ -155,12 +145,4 @@ class AsyncSarvamAI:
         self.speech_to_text = AsyncSpeechToTextClient(client_wrapper=self._client_wrapper)
         self.text_to_speech = AsyncTextToSpeechClient(client_wrapper=self._client_wrapper)
         self.chat = AsyncChatClient(client_wrapper=self._client_wrapper)
-
-
-def _get_base_url(*, base_url: typing.Optional[str] = None, environment: SarvamAIEnvironment) -> str:
-    if base_url is not None:
-        return base_url
-    elif environment is not None:
-        return environment.value
-    else:
-        raise Exception("Please pass in either base_url or environment to construct the client")
+        self.speech_to_text_streaming = AsyncSpeechToTextStreamingClient(client_wrapper=self._client_wrapper)

sarvamai/core/__init__.py

@@ -1,8 +1,11 @@
 # This file was auto-generated by Fern from our API Definition.
 
+# isort: skip_file
+
 from .api_error import ApiError
 from .client_wrapper import AsyncClientWrapper, BaseClientWrapper, SyncClientWrapper
 from .datetime_utils import serialize_datetime
+from .events import EventEmitterMixin, EventType
 from .file import File, convert_file_dict_to_httpx_tuples, with_content_type
 from .http_client import AsyncHttpClient, HttpClient
 from .http_response import AsyncHttpResponse, HttpResponse
@@ -27,6 +30,8 @@ __all__ = [
     "AsyncHttpClient",
     "AsyncHttpResponse",
     "BaseClientWrapper",
+    "EventEmitterMixin",
+    "EventType",
     "FieldMetadata",
     "File",
     "HttpClient",

sarvamai/core/api_error.py

@@ -1,15 +1,23 @@
 # This file was auto-generated by Fern from our API Definition.
 
-import typing
+from typing import Any, Dict, Optional
 
 
 class ApiError(Exception):
-    status_code: typing.Optional[int]
-    body: typing.Any
+    headers: Optional[Dict[str, str]]
+    status_code: Optional[int]
+    body: Any
 
-    def __init__(self, *, status_code: typing.Optional[int] = None, body: typing.Any = None):
+    def __init__(
+        self,
+        *,
+        headers: Optional[Dict[str, str]] = None,
+        status_code: Optional[int] = None,
+        body: Any = None,
+    ) -> None:
+        self.headers = headers
         self.status_code = status_code
         self.body = body
 
     def __str__(self) -> str:
-        return f"status_code: {self.status_code}, body: {self.body}"
+        return f"headers: {self.headers}, status_code: {self.status_code}, body: {self.body}"

sarvamai/core/client_wrapper.py

@@ -1,29 +1,32 @@
 # This file was auto-generated by Fern from our API Definition.
 
 import typing
+
 import httpx
-from .http_client import HttpClient
-from .http_client import AsyncHttpClient
+from ..environment import SarvamAIEnvironment
+from .http_client import AsyncHttpClient, HttpClient
 
 
 class BaseClientWrapper:
-    def __init__(self, *, api_subscription_key: str, base_url: str, timeout: typing.Optional[float] = None):
+    def __init__(
+        self, *, api_subscription_key: str, environment: SarvamAIEnvironment, timeout: typing.Optional[float] = None
+    ):
         self.api_subscription_key = api_subscription_key
-        self._base_url = base_url
+        self._environment = environment
         self._timeout = timeout
 
     def get_headers(self) -> typing.Dict[str, str]:
         headers: typing.Dict[str, str] = {
-            "User-Agent": "sarvamai/0.1.5a4",
+            "User-Agent": "sarvamai/0.1.5a5",
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "sarvamai",
-            "X-Fern-SDK-Version": "0.1.5a4",
+            "X-Fern-SDK-Version": "0.1.5a5",
         }
         headers["api-subscription-key"] = self.api_subscription_key
         return headers
 
-    def get_base_url(self) -> str:
-        return self._base_url
+    def get_environment(self) -> SarvamAIEnvironment:
+        return self._environment
 
     def get_timeout(self) -> typing.Optional[float]:
         return self._timeout
@@ -34,16 +37,13 @@ class SyncClientWrapper(BaseClientWrapper):
         self,
         *,
         api_subscription_key: str,
-        base_url: str,
+        environment: SarvamAIEnvironment,
         timeout: typing.Optional[float] = None,
         httpx_client: httpx.Client,
     ):
-        super().__init__(api_subscription_key=api_subscription_key, base_url=base_url, timeout=timeout)
+        super().__init__(api_subscription_key=api_subscription_key, environment=environment, timeout=timeout)
         self.httpx_client = HttpClient(
-            httpx_client=httpx_client,
-            base_headers=self.get_headers,
-            base_timeout=self.get_timeout,
-            base_url=self.get_base_url,
+            httpx_client=httpx_client, base_headers=self.get_headers, base_timeout=self.get_timeout
         )
 
 
@@ -52,14 +52,11 @@ class AsyncClientWrapper(BaseClientWrapper):
         self,
         *,
         api_subscription_key: str,
-        base_url: str,
+        environment: SarvamAIEnvironment,
         timeout: typing.Optional[float] = None,
         httpx_client: httpx.AsyncClient,
     ):
-        super().__init__(api_subscription_key=api_subscription_key, base_url=base_url, timeout=timeout)
+        super().__init__(api_subscription_key=api_subscription_key, environment=environment, timeout=timeout)
         self.httpx_client = AsyncHttpClient(
-            httpx_client=httpx_client,
-            base_headers=self.get_headers,
-            base_timeout=self.get_timeout,
-            base_url=self.get_base_url,
+            httpx_client=httpx_client, base_headers=self.get_headers, base_timeout=self.get_timeout
         )