sarvamai 0.1.6__py3-none-any.whl → 0.1.7a0__py3-none-any.whl

sarvamai/__init__.py

@@ -5,6 +5,9 @@
 from .types import (
     AudioData,
     AudioMessage,
+    BaseJobParameters,
+    BulkJobCallback,
+    BulkJobInitResponseV1,
     ChatCompletionRequestAssistantMessage,
     ChatCompletionRequestMessage,
     ChatCompletionRequestMessage_Assistant,
@@ -24,8 +27,14 @@ from .types import (
     ErrorDetails,
     ErrorMessage,
     EventsData,
+    FileSignedUrlDetails,
+    FilesDownloadResponse,
+    FilesRequest,
+    FilesUploadResponse,
     FinishReason,
     Format,
+    JobState,
+    JobStatusV1,
     LanguageIdentificationResponse,
     NumeralsFormat,
     ReasoningEffort,
@@ -33,6 +42,7 @@ from .types import (
     Role,
     SarvamModelIds,
     SpeechSampleRate,
+    SpeechToTextJobParameters,
     SpeechToTextLanguage,
     SpeechToTextModel,
     SpeechToTextResponse,
@@ -47,6 +57,10 @@ from .types import (
     SpeechToTextTranslateTranscriptionData,
     SpokenFormNumeralsFormat,
     StopConfiguration,
+    StorageContainerType,
+    TaskDetailV1,
+    TaskFileDetails,
+    TaskState,
     TextToSpeechLanguage,
     TextToSpeechModel,
     TextToSpeechResponse,
@@ -72,12 +86,23 @@ from .errors import (
     TooManyRequestsError,
     UnprocessableEntityError,
 )
-from . import chat, speech_to_text, speech_to_text_streaming, speech_to_text_translate_streaming, text, text_to_speech
+from . import (
+    chat,
+    speech_to_text,
+    speech_to_text_job,
+    speech_to_text_streaming,
+    speech_to_text_translate_streaming,
+    text,
+    text_to_speech,
+)
 from .client import AsyncSarvamAI, SarvamAI
 from .environment import SarvamAIEnvironment
 from .requests import (
     AudioDataParams,
     AudioMessageParams,
+    BaseJobParametersParams,
+    BulkJobCallbackParams,
+    BulkJobInitResponseV1Params,
     ChatCompletionRequestAssistantMessageParams,
     ChatCompletionRequestMessageParams,
     ChatCompletionRequestMessage_AssistantParams,
@@ -96,7 +121,13 @@ from .requests import (
     ErrorDetailsParams,
     ErrorMessageParams,
     EventsDataParams,
+    FileSignedUrlDetailsParams,
+    FilesDownloadResponseParams,
+    FilesRequestParams,
+    FilesUploadResponseParams,
+    JobStatusV1Params,
     LanguageIdentificationResponseParams,
+    SpeechToTextJobParametersParams,
     SpeechToTextResponseDataParams,
     SpeechToTextResponseParams,
     SpeechToTextStreamingResponseParams,
@@ -106,6 +137,8 @@ from .requests import (
     SpeechToTextTranslateStreamingResponseParams,
     SpeechToTextTranslateTranscriptionDataParams,
     StopConfigurationParams,
+    TaskDetailV1Params,
+    TaskFileDetailsParams,
     TextToSpeechResponseParams,
     TimestampsModelParams,
     TranscriptionMetricsParams,
@@ -132,6 +165,12 @@ __all__ = [
     "AudioMessage",
     "AudioMessageParams",
     "BadRequestError",
+    "BaseJobParameters",
+    "BaseJobParametersParams",
+    "BulkJobCallback",
+    "BulkJobCallbackParams",
+    "BulkJobInitResponseV1",
+    "BulkJobInitResponseV1Params",
     "ChatCompletionRequestAssistantMessage",
     "ChatCompletionRequestAssistantMessageParams",
     "ChatCompletionRequestMessage",
@@ -169,10 +208,21 @@ __all__ = [
     "ErrorMessageParams",
     "EventsData",
     "EventsDataParams",
+    "FileSignedUrlDetails",
+    "FileSignedUrlDetailsParams",
+    "FilesDownloadResponse",
+    "FilesDownloadResponseParams",
+    "FilesRequest",
+    "FilesRequestParams",
+    "FilesUploadResponse",
+    "FilesUploadResponseParams",
     "FinishReason",
     "ForbiddenError",
     "Format",
     "InternalServerError",
+    "JobState",
+    "JobStatusV1",
+    "JobStatusV1Params",
     "LanguageIdentificationResponse",
     "LanguageIdentificationResponseParams",
     "NumeralsFormat",
@@ -184,6 +234,8 @@ __all__ = [
     "SarvamModelIds",
     "ServiceUnavailableError",
     "SpeechSampleRate",
+    "SpeechToTextJobParameters",
+    "SpeechToTextJobParametersParams",
     "SpeechToTextLanguage",
     "SpeechToTextModel",
     "SpeechToTextResponse",
@@ -214,6 +266,12 @@ __all__ = [
     "SpokenFormNumeralsFormat",
     "StopConfiguration",
     "StopConfigurationParams",
+    "StorageContainerType",
+    "TaskDetailV1",
+    "TaskDetailV1Params",
+    "TaskFileDetails",
+    "TaskFileDetailsParams",
+    "TaskState",
     "TextToSpeechLanguage",
     "TextToSpeechModel",
     "TextToSpeechResponse",
@@ -240,6 +298,7 @@ __all__ = [
     "__version__",
     "chat",
     "speech_to_text",
+    "speech_to_text_job",
     "speech_to_text_streaming",
     "speech_to_text_translate_streaming",
     "text",

sarvamai/client.py

@@ -9,6 +9,7 @@ from .core.api_error import ApiError
 from .core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
 from .environment import SarvamAIEnvironment
 from .speech_to_text.client import AsyncSpeechToTextClient, SpeechToTextClient
+from .speech_to_text_job.client import AsyncSpeechToTextJobClient, SpeechToTextJobClient
 from .speech_to_text_streaming.client import AsyncSpeechToTextStreamingClient, SpeechToTextStreamingClient
 from .speech_to_text_translate_streaming.client import (
     AsyncSpeechToTextTranslateStreamingClient,
@@ -82,6 +83,7 @@ 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_job = SpeechToTextJobClient(client_wrapper=self._client_wrapper)
         self.speech_to_text_streaming = SpeechToTextStreamingClient(client_wrapper=self._client_wrapper)
         self.speech_to_text_translate_streaming = SpeechToTextTranslateStreamingClient(
             client_wrapper=self._client_wrapper
@@ -152,6 +154,7 @@ 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)
+        self.speech_to_text_job = AsyncSpeechToTextJobClient(client_wrapper=self._client_wrapper)
         self.speech_to_text_streaming = AsyncSpeechToTextStreamingClient(client_wrapper=self._client_wrapper)
         self.speech_to_text_translate_streaming = AsyncSpeechToTextTranslateStreamingClient(
             client_wrapper=self._client_wrapper

sarvamai/core/client_wrapper.py

@@ -17,10 +17,10 @@ class BaseClientWrapper:
 
     def get_headers(self) -> typing.Dict[str, str]:
         headers: typing.Dict[str, str] = {
-            "User-Agent": "sarvamai/0.1.6",
+            "User-Agent": "sarvamai/0.1.7a0",
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "sarvamai",
-            "X-Fern-SDK-Version": "0.1.6",
+            "X-Fern-SDK-Version": "0.1.7a0",
         }
         headers["api-subscription-key"] = self.api_subscription_key
         return headers

sarvamai/errors/service_unavailable_error.py

@@ -3,9 +3,8 @@
 import typing
 
 from ..core.api_error import ApiError
-from ..types.error_message import ErrorMessage
 
 
 class ServiceUnavailableError(ApiError):
-    def __init__(self, body: ErrorMessage, headers: typing.Optional[typing.Dict[str, str]] = None):
+    def __init__(self, body: typing.Optional[typing.Any], headers: typing.Optional[typing.Dict[str, str]] = None):
         super().__init__(status_code=503, headers=headers, body=body)

sarvamai/requests/__init__.py

@@ -4,6 +4,9 @@
 
 from .audio_data import AudioDataParams
 from .audio_message import AudioMessageParams
+from .base_job_parameters import BaseJobParametersParams
+from .bulk_job_callback import BulkJobCallbackParams
+from .bulk_job_init_response_v_1 import BulkJobInitResponseV1Params
 from .chat_completion_request_assistant_message import ChatCompletionRequestAssistantMessageParams
 from .chat_completion_request_message import (
     ChatCompletionRequestMessageParams,
@@ -24,7 +27,13 @@ from .error_data import ErrorDataParams
 from .error_details import ErrorDetailsParams
 from .error_message import ErrorMessageParams
 from .events_data import EventsDataParams
+from .file_signed_url_details import FileSignedUrlDetailsParams
+from .files_download_response import FilesDownloadResponseParams
+from .files_request import FilesRequestParams
+from .files_upload_response import FilesUploadResponseParams
+from .job_status_v_1 import JobStatusV1Params
 from .language_identification_response import LanguageIdentificationResponseParams
+from .speech_to_text_job_parameters import SpeechToTextJobParametersParams
 from .speech_to_text_response import SpeechToTextResponseParams
 from .speech_to_text_response_data import SpeechToTextResponseDataParams
 from .speech_to_text_streaming_response import SpeechToTextStreamingResponseParams
@@ -34,6 +43,8 @@ from .speech_to_text_translate_response_data import SpeechToTextTranslateRespons
 from .speech_to_text_translate_streaming_response import SpeechToTextTranslateStreamingResponseParams
 from .speech_to_text_translate_transcription_data import SpeechToTextTranslateTranscriptionDataParams
 from .stop_configuration import StopConfigurationParams
+from .task_detail_v_1 import TaskDetailV1Params
+from .task_file_details import TaskFileDetailsParams
 from .text_to_speech_response import TextToSpeechResponseParams
 from .timestamps_model import TimestampsModelParams
 from .transcription_metrics import TranscriptionMetricsParams
@@ -43,6 +54,9 @@ from .transliteration_response import TransliterationResponseParams
 __all__ = [
     "AudioDataParams",
     "AudioMessageParams",
+    "BaseJobParametersParams",
+    "BulkJobCallbackParams",
+    "BulkJobInitResponseV1Params",
     "ChatCompletionRequestAssistantMessageParams",
     "ChatCompletionRequestMessageParams",
     "ChatCompletionRequestMessage_AssistantParams",
@@ -61,7 +75,13 @@ __all__ = [
     "ErrorDetailsParams",
     "ErrorMessageParams",
     "EventsDataParams",
+    "FileSignedUrlDetailsParams",
+    "FilesDownloadResponseParams",
+    "FilesRequestParams",
+    "FilesUploadResponseParams",
+    "JobStatusV1Params",
     "LanguageIdentificationResponseParams",
+    "SpeechToTextJobParametersParams",
     "SpeechToTextResponseDataParams",
     "SpeechToTextResponseParams",
     "SpeechToTextStreamingResponseParams",
@@ -71,6 +91,8 @@ __all__ = [
     "SpeechToTextTranslateStreamingResponseParams",
     "SpeechToTextTranslateTranscriptionDataParams",
     "StopConfigurationParams",
+    "TaskDetailV1Params",
+    "TaskFileDetailsParams",
     "TextToSpeechResponseParams",
     "TimestampsModelParams",
     "TranscriptionMetricsParams",

sarvamai/requests/base_job_parameters.py

@@ -0,0 +1,7 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+
+
+class BaseJobParametersParams(typing_extensions.TypedDict):
+    pass

sarvamai/requests/bulk_job_callback.py

@@ -0,0 +1,15 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+
+
+class BulkJobCallbackParams(typing_extensions.TypedDict):
+    url: str
+    """
+    Webhook url to call upon job completion
+    """
+
+    auth_token: typing_extensions.NotRequired[str]
+    """
+    Authorization token required for the callback Url
+    """

sarvamai/requests/bulk_job_init_response_v_1.py

@@ -0,0 +1,27 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+from ..types.job_state import JobState
+from ..types.storage_container_type import StorageContainerType
+from .base_job_parameters import BaseJobParametersParams
+from .bulk_job_callback import BulkJobCallbackParams
+
+
+class BulkJobInitResponseV1Params(typing_extensions.TypedDict):
+    job_id: str
+    """
+    Job UUID.
+    """
+
+    storage_container_type: StorageContainerType
+    """
+    Storage Container Type
+    """
+
+    job_parameters: BaseJobParametersParams
+    job_state: JobState
+    owner_id: str
+    callback: typing_extensions.NotRequired[BulkJobCallbackParams]
+    """
+    Parameters for callback URL
+    """

sarvamai/requests/file_signed_url_details.py

@@ -0,0 +1,10 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+
+
+class FileSignedUrlDetailsParams(typing_extensions.TypedDict):
+    file_url: str
+    file_metadata: typing_extensions.NotRequired[typing.Dict[str, typing.Optional[typing.Any]]]

sarvamai/requests/files_download_response.py

@@ -0,0 +1,15 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+from ..types.job_state import JobState
+from ..types.storage_container_type import StorageContainerType
+from .file_signed_url_details import FileSignedUrlDetailsParams
+
+
+class FilesDownloadResponseParams(typing_extensions.TypedDict):
+    job_id: str
+    job_state: JobState
+    download_urls: typing.Dict[str, FileSignedUrlDetailsParams]
+    storage_container_type: StorageContainerType

sarvamai/requests/files_request.py

@@ -0,0 +1,10 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+
+
+class FilesRequestParams(typing_extensions.TypedDict):
+    job_id: str
+    files: typing.Sequence[str]

sarvamai/requests/files_upload_response.py

@@ -0,0 +1,15 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+from ..types.job_state import JobState
+from ..types.storage_container_type import StorageContainerType
+from .file_signed_url_details import FileSignedUrlDetailsParams
+
+
+class FilesUploadResponseParams(typing_extensions.TypedDict):
+    job_id: str
+    job_state: JobState
+    upload_urls: typing.Dict[str, FileSignedUrlDetailsParams]
+    storage_container_type: StorageContainerType

sarvamai/requests/job_status_v_1.py

@@ -0,0 +1,70 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+from ..types.job_state import JobState
+from ..types.storage_container_type import StorageContainerType
+from .task_detail_v_1 import TaskDetailV1Params
+
+
+class JobStatusV1Params(typing_extensions.TypedDict):
+    job_state: JobState
+    """
+    Job State
+    """
+
+    created_at: str
+    """
+    Created At
+    """
+
+    updated_at: str
+    """
+    Updated At
+    """
+
+    job_id: str
+    """
+    Job Id
+    """
+
+    total_files: typing_extensions.NotRequired[int]
+    """
+    Total Files
+    """
+
+    successful_files_count: typing_extensions.NotRequired[int]
+    """
+    Success Count
+    """
+
+    failed_files_count: typing_extensions.NotRequired[int]
+    """
+    Failed Count
+    """
+
+    owner_id: str
+    """
+    Owner of the job
+    """
+
+    storage_container_type: StorageContainerType
+    """
+    Storage Container Type
+    """
+
+    error_message: typing_extensions.NotRequired[str]
+    """
+    Error Message
+    """
+
+    job_details: typing_extensions.NotRequired[typing.Sequence[TaskDetailV1Params]]
+    """
+    Job details at file level.
+    """
+
+    num_internal_retries: typing_extensions.NotRequired[int]
+    """
+    Number of internal retries
+    """

sarvamai/requests/speech_to_text_job_parameters.py

@@ -0,0 +1,32 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+from ..types.speech_to_text_model import SpeechToTextModel
+from ..types.speech_to_text_translate_language import SpeechToTextTranslateLanguage
+
+
+class SpeechToTextJobParametersParams(typing_extensions.TypedDict):
+    language_code: typing_extensions.NotRequired[SpeechToTextTranslateLanguage]
+    """
+    Language code
+    """
+
+    model: typing_extensions.NotRequired[SpeechToTextModel]
+    """
+    Model to be used for speech to text
+    """
+
+    with_timestamps: typing_extensions.NotRequired[bool]
+    """
+    Whether to include timestamps in the response
+    """
+
+    with_diarization: typing_extensions.NotRequired[bool]
+    """
+    Enables speaker diarization, which identifies and separates different speakers in the audio. In beta mode
+    """
+
+    num_speakers: typing_extensions.NotRequired[int]
+    """
+    Number of speakers to be detected in the audio. This is used when with_diarization is true.
+    """

sarvamai/requests/task_detail_v_1.py

@@ -0,0 +1,15 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+from ..types.task_state import TaskState
+from .task_file_details import TaskFileDetailsParams
+
+
+class TaskDetailV1Params(typing_extensions.TypedDict):
+    inputs: typing_extensions.NotRequired[typing.Sequence[TaskFileDetailsParams]]
+    outputs: typing_extensions.NotRequired[typing.Sequence[TaskFileDetailsParams]]
+    state: typing_extensions.NotRequired[TaskState]
+    error_message: typing_extensions.NotRequired[str]
+    exception_name: typing_extensions.NotRequired[str]

sarvamai/requests/task_file_details.py

@@ -0,0 +1,8 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+
+
+class TaskFileDetailsParams(typing_extensions.TypedDict):
+    file_name: str
+    file_id: str

sarvamai/speech_to_text/raw_client.py

@@ -15,7 +15,6 @@ from ..errors.internal_server_error import InternalServerError
 from ..errors.service_unavailable_error import ServiceUnavailableError
 from ..errors.too_many_requests_error import TooManyRequestsError
 from ..errors.unprocessable_entity_error import UnprocessableEntityError
-from ..types.error_message import ErrorMessage
 from ..types.speech_to_text_language import SpeechToTextLanguage
 from ..types.speech_to_text_model import SpeechToTextModel
 from ..types.speech_to_text_response import SpeechToTextResponse
@@ -161,9 +160,9 @@ class RawSpeechToTextClient:
                 raise ServiceUnavailableError(
                     headers=dict(_response.headers),
                     body=typing.cast(
-                        ErrorMessage,
+                        typing.Optional[typing.Any],
                         parse_obj_as(
-                            type_=ErrorMessage,  # type: ignore
+                            type_=typing.Optional[typing.Any],  # type: ignore
                             object_=_response.json(),
                         ),
                     ),
@@ -299,9 +298,9 @@ class RawSpeechToTextClient:
                 raise ServiceUnavailableError(
                     headers=dict(_response.headers),
                     body=typing.cast(
-                        ErrorMessage,
+                        typing.Optional[typing.Any],
                         parse_obj_as(
-                            type_=ErrorMessage,  # type: ignore
+                            type_=typing.Optional[typing.Any],  # type: ignore
                             object_=_response.json(),
                         ),
                     ),
@@ -447,9 +446,9 @@ class AsyncRawSpeechToTextClient:
                 raise ServiceUnavailableError(
                     headers=dict(_response.headers),
                     body=typing.cast(
-                        ErrorMessage,
+                        typing.Optional[typing.Any],
                         parse_obj_as(
-                            type_=ErrorMessage,  # type: ignore
+                            type_=typing.Optional[typing.Any],  # type: ignore
                             object_=_response.json(),
                         ),
                     ),
@@ -585,9 +584,9 @@ class AsyncRawSpeechToTextClient:
                 raise ServiceUnavailableError(
                     headers=dict(_response.headers),
                     body=typing.cast(
-                        ErrorMessage,
+                        typing.Optional[typing.Any],
                         parse_obj_as(
-                            type_=ErrorMessage,  # type: ignore
+                            type_=typing.Optional[typing.Any],  # type: ignore
                             object_=_response.json(),
                         ),
                     ),

sarvamai/speech_to_text_job/__init__.py

@@ -0,0 +1,4 @@
+# This file was auto-generated by Fern from our API Definition.
+
+# isort: skip_file
+