sarvamai 0.1.22a3__py3-none-any.whl → 0.1.23a1__py3-none-any.whl

sarvamai/types/__init__.py

@@ -2,110 +2,231 @@
 
 # isort: skip_file
 
-from .audio_data import AudioData
-from .audio_data_input_audio_codec import AudioDataInputAudioCodec
-from .audio_message import AudioMessage
-from .audio_output import AudioOutput
-from .audio_output_data import AudioOutputData
-from .base_job_parameters import BaseJobParameters
-from .bulk_job_callback import BulkJobCallback
-from .bulk_job_init_response_v_1 import BulkJobInitResponseV1
-from .chat_completion_request_assistant_message import ChatCompletionRequestAssistantMessage
-from .chat_completion_request_message import (
-    ChatCompletionRequestMessage,
-    ChatCompletionRequestMessage_Assistant,
-    ChatCompletionRequestMessage_System,
-    ChatCompletionRequestMessage_User,
-)
-from .chat_completion_request_system_message import ChatCompletionRequestSystemMessage
-from .chat_completion_request_user_message import ChatCompletionRequestUserMessage
-from .chat_completion_response_message import ChatCompletionResponseMessage
-from .choice import Choice
-from .completion_event_flag import CompletionEventFlag
-from .completion_usage import CompletionUsage
-from .config_message import ConfigMessage
-from .configure_connection import ConfigureConnection
-from .configure_connection_data import ConfigureConnectionData
-from .configure_connection_data_output_audio_bitrate import ConfigureConnectionDataOutputAudioBitrate
-from .configure_connection_data_output_audio_codec import ConfigureConnectionDataOutputAudioCodec
-from .configure_connection_data_speaker import ConfigureConnectionDataSpeaker
-from .configure_connection_data_target_language_code import ConfigureConnectionDataTargetLanguageCode
-from .connection_sample_rate import ConnectionSampleRate
-from .create_chat_completion_response import CreateChatCompletionResponse
-from .diarized_entry import DiarizedEntry
-from .diarized_transcript import DiarizedTranscript
-from .error_code import ErrorCode
-from .error_data import ErrorData
-from .error_details import ErrorDetails
-from .error_message import ErrorMessage
-from .error_response import ErrorResponse
-from .error_response_data import ErrorResponseData
-from .event_response import EventResponse
-from .event_response_data import EventResponseData
-from .events_data import EventsData
-from .events_data_signal_type import EventsDataSignalType
-from .file_signed_url_details import FileSignedUrlDetails
-from .files_download_response import FilesDownloadResponse
-from .files_request import FilesRequest
-from .files_upload_response import FilesUploadResponse
-from .finish_reason import FinishReason
-from .flush_signal import FlushSignal
-from .input_audio_codec import InputAudioCodec
-from .job_state import JobState
-from .job_status_v_1_response import JobStatusV1Response
-from .language_identification_response import LanguageIdentificationResponse
-from .numerals_format import NumeralsFormat
-from .ping_signal import PingSignal
-from .reasoning_effort import ReasoningEffort
-from .response_speech_state import ResponseSpeechState
-from .response_type import ResponseType
-from .role import Role
-from .sarvam_model_ids import SarvamModelIds
-from .send_text import SendText
-from .send_text_data import SendTextData
-from .speech_sample_rate import SpeechSampleRate
-from .speech_to_text_job_parameters import SpeechToTextJobParameters
-from .speech_to_text_language import SpeechToTextLanguage
-from .speech_to_text_model import SpeechToTextModel
-from .speech_to_text_response import SpeechToTextResponse
-from .speech_to_text_response_data import SpeechToTextResponseData
-from .speech_to_text_streaming_response import SpeechToTextStreamingResponse
-from .speech_to_text_transcription_data import SpeechToTextTranscriptionData
-from .speech_to_text_translate_job_parameters import SpeechToTextTranslateJobParameters
-from .speech_to_text_translate_language import SpeechToTextTranslateLanguage
-from .speech_to_text_translate_model import SpeechToTextTranslateModel
-from .speech_to_text_translate_response import SpeechToTextTranslateResponse
-from .speech_to_text_translate_response_data import SpeechToTextTranslateResponseData
-from .speech_to_text_translate_streaming_response import SpeechToTextTranslateStreamingResponse
-from .speech_to_text_translate_transcription_data import SpeechToTextTranslateTranscriptionData
-from .spoken_form_numerals_format import SpokenFormNumeralsFormat
-from .stop_configuration import StopConfiguration
-from .storage_container_type import StorageContainerType
-from .stt_flush_signal import SttFlushSignal
-from .task_detail_v_1 import TaskDetailV1
-from .task_file_details import TaskFileDetails
-from .task_state import TaskState
-from .text_to_speech_language import TextToSpeechLanguage
-from .text_to_speech_model import TextToSpeechModel
-from .text_to_speech_output_audio_codec import TextToSpeechOutputAudioCodec
-from .text_to_speech_response import TextToSpeechResponse
-from .text_to_speech_speaker import TextToSpeechSpeaker
-from .timestamps_model import TimestampsModel
-from .transcription_metrics import TranscriptionMetrics
-from .translate_mode import TranslateMode
-from .translate_model import TranslateModel
-from .translate_source_language import TranslateSourceLanguage
-from .translate_speaker_gender import TranslateSpeakerGender
-from .translate_target_language import TranslateTargetLanguage
-from .translation_response import TranslationResponse
-from .translatiterate_target_language import TranslatiterateTargetLanguage
-from .transliterate_mode import TransliterateMode
-from .transliterate_source_language import TransliterateSourceLanguage
-from .transliteration_response import TransliterationResponse
+import typing
+from importlib import import_module
+
+if typing.TYPE_CHECKING:
+    from .audio_data import AudioData
+    from .audio_message import AudioMessage
+    from .audio_output import AudioOutput
+    from .audio_output_data import AudioOutputData
+    from .base_job_parameters import BaseJobParameters
+    from .bulk_job_callback import BulkJobCallback
+    from .bulk_job_init_response_v_1 import BulkJobInitResponseV1
+    from .chat_completion_request_assistant_message import ChatCompletionRequestAssistantMessage
+    from .chat_completion_request_message import (
+        ChatCompletionRequestMessage,
+        ChatCompletionRequestMessage_Assistant,
+        ChatCompletionRequestMessage_System,
+        ChatCompletionRequestMessage_User,
+    )
+    from .chat_completion_request_system_message import ChatCompletionRequestSystemMessage
+    from .chat_completion_request_user_message import ChatCompletionRequestUserMessage
+    from .chat_completion_response_message import ChatCompletionResponseMessage
+    from .choice import Choice
+    from .completion_event_flag import CompletionEventFlag
+    from .completion_usage import CompletionUsage
+    from .config_message import ConfigMessage
+    from .configure_connection import ConfigureConnection
+    from .configure_connection_data import ConfigureConnectionData
+    from .configure_connection_data_output_audio_bitrate import ConfigureConnectionDataOutputAudioBitrate
+    from .configure_connection_data_output_audio_codec import ConfigureConnectionDataOutputAudioCodec
+    from .configure_connection_data_speaker import ConfigureConnectionDataSpeaker
+    from .configure_connection_data_target_language_code import ConfigureConnectionDataTargetLanguageCode
+    from .connection_sample_rate import ConnectionSampleRate
+    from .create_chat_completion_response import CreateChatCompletionResponse
+    from .diarized_entry import DiarizedEntry
+    from .diarized_transcript import DiarizedTranscript
+    from .error_code import ErrorCode
+    from .error_data import ErrorData
+    from .error_details import ErrorDetails
+    from .error_message import ErrorMessage
+    from .error_response import ErrorResponse
+    from .error_response_data import ErrorResponseData
+    from .event_response import EventResponse
+    from .event_response_data import EventResponseData
+    from .events_data import EventsData
+    from .events_data_signal_type import EventsDataSignalType
+    from .file_signed_url_details import FileSignedUrlDetails
+    from .files_download_response import FilesDownloadResponse
+    from .files_request import FilesRequest
+    from .files_upload_response import FilesUploadResponse
+    from .finish_reason import FinishReason
+    from .flush_signal import FlushSignal
+    from .input_audio_codec import InputAudioCodec
+    from .job_state import JobState
+    from .job_status_v_1_response import JobStatusV1Response
+    from .language_identification_response import LanguageIdentificationResponse
+    from .numerals_format import NumeralsFormat
+    from .ping_signal import PingSignal
+    from .reasoning_effort import ReasoningEffort
+    from .response_type import ResponseType
+    from .role import Role
+    from .sarvam_model_ids import SarvamModelIds
+    from .send_text import SendText
+    from .send_text_data import SendTextData
+    from .speech_sample_rate import SpeechSampleRate
+    from .speech_to_text_job_parameters import SpeechToTextJobParameters
+    from .speech_to_text_language import SpeechToTextLanguage
+    from .speech_to_text_model import SpeechToTextModel
+    from .speech_to_text_response import SpeechToTextResponse
+    from .speech_to_text_response_data import SpeechToTextResponseData
+    from .speech_to_text_streaming_response import SpeechToTextStreamingResponse
+    from .speech_to_text_transcription_data import SpeechToTextTranscriptionData
+    from .speech_to_text_translate_job_parameters import SpeechToTextTranslateJobParameters
+    from .speech_to_text_translate_language import SpeechToTextTranslateLanguage
+    from .speech_to_text_translate_model import SpeechToTextTranslateModel
+    from .speech_to_text_translate_response import SpeechToTextTranslateResponse
+    from .speech_to_text_translate_response_data import SpeechToTextTranslateResponseData
+    from .speech_to_text_translate_streaming_response import SpeechToTextTranslateStreamingResponse
+    from .speech_to_text_translate_transcription_data import SpeechToTextTranslateTranscriptionData
+    from .spoken_form_numerals_format import SpokenFormNumeralsFormat
+    from .stop_configuration import StopConfiguration
+    from .storage_container_type import StorageContainerType
+    from .stt_flush_signal import SttFlushSignal
+    from .task_detail_v_1 import TaskDetailV1
+    from .task_file_details import TaskFileDetails
+    from .task_state import TaskState
+    from .text_to_speech_language import TextToSpeechLanguage
+    from .text_to_speech_model import TextToSpeechModel
+    from .text_to_speech_output_audio_codec import TextToSpeechOutputAudioCodec
+    from .text_to_speech_response import TextToSpeechResponse
+    from .text_to_speech_speaker import TextToSpeechSpeaker
+    from .timestamps_model import TimestampsModel
+    from .transcription_metrics import TranscriptionMetrics
+    from .translate_mode import TranslateMode
+    from .translate_model import TranslateModel
+    from .translate_source_language import TranslateSourceLanguage
+    from .translate_speaker_gender import TranslateSpeakerGender
+    from .translate_target_language import TranslateTargetLanguage
+    from .translation_response import TranslationResponse
+    from .translatiterate_target_language import TranslatiterateTargetLanguage
+    from .transliterate_mode import TransliterateMode
+    from .transliterate_source_language import TransliterateSourceLanguage
+    from .transliteration_response import TransliterationResponse
+_dynamic_imports: typing.Dict[str, str] = {
+    "AudioData": ".audio_data",
+    "AudioMessage": ".audio_message",
+    "AudioOutput": ".audio_output",
+    "AudioOutputData": ".audio_output_data",
+    "BaseJobParameters": ".base_job_parameters",
+    "BulkJobCallback": ".bulk_job_callback",
+    "BulkJobInitResponseV1": ".bulk_job_init_response_v_1",
+    "ChatCompletionRequestAssistantMessage": ".chat_completion_request_assistant_message",
+    "ChatCompletionRequestMessage": ".chat_completion_request_message",
+    "ChatCompletionRequestMessage_Assistant": ".chat_completion_request_message",
+    "ChatCompletionRequestMessage_System": ".chat_completion_request_message",
+    "ChatCompletionRequestMessage_User": ".chat_completion_request_message",
+    "ChatCompletionRequestSystemMessage": ".chat_completion_request_system_message",
+    "ChatCompletionRequestUserMessage": ".chat_completion_request_user_message",
+    "ChatCompletionResponseMessage": ".chat_completion_response_message",
+    "Choice": ".choice",
+    "CompletionEventFlag": ".completion_event_flag",
+    "CompletionUsage": ".completion_usage",
+    "ConfigMessage": ".config_message",
+    "ConfigureConnection": ".configure_connection",
+    "ConfigureConnectionData": ".configure_connection_data",
+    "ConfigureConnectionDataOutputAudioBitrate": ".configure_connection_data_output_audio_bitrate",
+    "ConfigureConnectionDataOutputAudioCodec": ".configure_connection_data_output_audio_codec",
+    "ConfigureConnectionDataSpeaker": ".configure_connection_data_speaker",
+    "ConfigureConnectionDataTargetLanguageCode": ".configure_connection_data_target_language_code",
+    "ConnectionSampleRate": ".connection_sample_rate",
+    "CreateChatCompletionResponse": ".create_chat_completion_response",
+    "DiarizedEntry": ".diarized_entry",
+    "DiarizedTranscript": ".diarized_transcript",
+    "ErrorCode": ".error_code",
+    "ErrorData": ".error_data",
+    "ErrorDetails": ".error_details",
+    "ErrorMessage": ".error_message",
+    "ErrorResponse": ".error_response",
+    "ErrorResponseData": ".error_response_data",
+    "EventResponse": ".event_response",
+    "EventResponseData": ".event_response_data",
+    "EventsData": ".events_data",
+    "EventsDataSignalType": ".events_data_signal_type",
+    "FileSignedUrlDetails": ".file_signed_url_details",
+    "FilesDownloadResponse": ".files_download_response",
+    "FilesRequest": ".files_request",
+    "FilesUploadResponse": ".files_upload_response",
+    "FinishReason": ".finish_reason",
+    "FlushSignal": ".flush_signal",
+    "InputAudioCodec": ".input_audio_codec",
+    "JobState": ".job_state",
+    "JobStatusV1Response": ".job_status_v_1_response",
+    "LanguageIdentificationResponse": ".language_identification_response",
+    "NumeralsFormat": ".numerals_format",
+    "PingSignal": ".ping_signal",
+    "ReasoningEffort": ".reasoning_effort",
+    "ResponseType": ".response_type",
+    "Role": ".role",
+    "SarvamModelIds": ".sarvam_model_ids",
+    "SendText": ".send_text",
+    "SendTextData": ".send_text_data",
+    "SpeechSampleRate": ".speech_sample_rate",
+    "SpeechToTextJobParameters": ".speech_to_text_job_parameters",
+    "SpeechToTextLanguage": ".speech_to_text_language",
+    "SpeechToTextModel": ".speech_to_text_model",
+    "SpeechToTextResponse": ".speech_to_text_response",
+    "SpeechToTextResponseData": ".speech_to_text_response_data",
+    "SpeechToTextStreamingResponse": ".speech_to_text_streaming_response",
+    "SpeechToTextTranscriptionData": ".speech_to_text_transcription_data",
+    "SpeechToTextTranslateJobParameters": ".speech_to_text_translate_job_parameters",
+    "SpeechToTextTranslateLanguage": ".speech_to_text_translate_language",
+    "SpeechToTextTranslateModel": ".speech_to_text_translate_model",
+    "SpeechToTextTranslateResponse": ".speech_to_text_translate_response",
+    "SpeechToTextTranslateResponseData": ".speech_to_text_translate_response_data",
+    "SpeechToTextTranslateStreamingResponse": ".speech_to_text_translate_streaming_response",
+    "SpeechToTextTranslateTranscriptionData": ".speech_to_text_translate_transcription_data",
+    "SpokenFormNumeralsFormat": ".spoken_form_numerals_format",
+    "StopConfiguration": ".stop_configuration",
+    "StorageContainerType": ".storage_container_type",
+    "SttFlushSignal": ".stt_flush_signal",
+    "TaskDetailV1": ".task_detail_v_1",
+    "TaskFileDetails": ".task_file_details",
+    "TaskState": ".task_state",
+    "TextToSpeechLanguage": ".text_to_speech_language",
+    "TextToSpeechModel": ".text_to_speech_model",
+    "TextToSpeechOutputAudioCodec": ".text_to_speech_output_audio_codec",
+    "TextToSpeechResponse": ".text_to_speech_response",
+    "TextToSpeechSpeaker": ".text_to_speech_speaker",
+    "TimestampsModel": ".timestamps_model",
+    "TranscriptionMetrics": ".transcription_metrics",
+    "TranslateMode": ".translate_mode",
+    "TranslateModel": ".translate_model",
+    "TranslateSourceLanguage": ".translate_source_language",
+    "TranslateSpeakerGender": ".translate_speaker_gender",
+    "TranslateTargetLanguage": ".translate_target_language",
+    "TranslationResponse": ".translation_response",
+    "TranslatiterateTargetLanguage": ".translatiterate_target_language",
+    "TransliterateMode": ".transliterate_mode",
+    "TransliterateSourceLanguage": ".transliterate_source_language",
+    "TransliterationResponse": ".transliteration_response",
+}
+
+
+def __getattr__(attr_name: str) -> typing.Any:
+    module_name = _dynamic_imports.get(attr_name)
+    if module_name is None:
+        raise AttributeError(f"No {attr_name} found in _dynamic_imports for module name -> {__name__}")
+    try:
+        module = import_module(module_name, __package__)
+        if module_name == f".{attr_name}":
+            return module
+        else:
+            return getattr(module, attr_name)
+    except ImportError as e:
+        raise ImportError(f"Failed to import {attr_name} from {module_name}: {e}") from e
+    except AttributeError as e:
+        raise AttributeError(f"Failed to get {attr_name} from {module_name}: {e}") from e
+
+
+def __dir__():
+    lazy_attrs = list(_dynamic_imports.keys())
+    return sorted(lazy_attrs)
+
 
 __all__ = [
     "AudioData",
-    "AudioDataInputAudioCodec",
     "AudioMessage",
     "AudioOutput",
     "AudioOutputData",
@@ -157,7 +278,6 @@ __all__ = [
     "NumeralsFormat",
     "PingSignal",
     "ReasoningEffort",
-    "ResponseSpeechState",
     "ResponseType",
     "Role",
     "SarvamModelIds",

sarvamai/types/audio_data.py

@@ -4,7 +4,6 @@ import typing
 
 import pydantic
 from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
-from .audio_data_input_audio_codec import AudioDataInputAudioCodec
 
 
 class AudioData(UniversalBaseModel):
@@ -29,11 +28,6 @@ class AudioData(UniversalBaseModel):
     Audio encoding format
     """
 
-    input_audio_codec: typing.Optional[AudioDataInputAudioCodec] = pydantic.Field(default=None)
-    """
-    Audio codec/format of the input file. Our API automatically detects all codec formats, but for PCM files specifically (pcm_s16le, pcm_l16, pcm_raw), you must pass this parameter. PCM files supports sample rate 16000 and 8000.
-    """
-
     if IS_PYDANTIC_V2:
         model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
     else:

sarvamai/types/chat_completion_request_message.py

@@ -5,6 +5,7 @@ from __future__ import annotations
 import typing
 
 import pydantic
+import typing_extensions
 from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
 
 
@@ -50,6 +51,9 @@ class ChatCompletionRequestMessage_User(UniversalBaseModel):
             extra = pydantic.Extra.allow
 
 
-ChatCompletionRequestMessage = typing.Union[
-    ChatCompletionRequestMessage_Assistant, ChatCompletionRequestMessage_System, ChatCompletionRequestMessage_User
+ChatCompletionRequestMessage = typing_extensions.Annotated[
+    typing.Union[
+        ChatCompletionRequestMessage_Assistant, ChatCompletionRequestMessage_System, ChatCompletionRequestMessage_User
+    ],
+    pydantic.Field(discriminator="role"),
 ]

sarvamai/types/completion_event_flag.py

@@ -1,3 +1,5 @@
 # This file was auto-generated by Fern from our API Definition.
 
-CompletionEventFlag = bool
+import typing
+
+CompletionEventFlag = typing.Union[typing.Literal["true", "false"], typing.Any]

sarvamai/types/error_response_data.py

@@ -13,7 +13,7 @@ class ErrorResponseData(UniversalBaseModel):
     Optional error code for programmatic error handling
     """
 
-    details: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = pydantic.Field(default=None)
+    details: typing.Optional[typing.Dict[str, typing.Any]] = pydantic.Field(default=None)
     """
     Additional error details and context information
     """

sarvamai/types/file_signed_url_details.py

@@ -8,7 +8,7 @@ from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
 
 class FileSignedUrlDetails(UniversalBaseModel):
     file_url: str
-    file_metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = None
+    file_metadata: typing.Optional[typing.Dict[str, typing.Any]] = None
 
     if IS_PYDANTIC_V2:
         model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2

sarvamai/types/speech_to_text_transcription_data.py

@@ -4,7 +4,6 @@ import typing
 
 import pydantic
 from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
-from .response_speech_state import ResponseSpeechState
 from .transcription_metrics import TranscriptionMetrics
 
 
@@ -19,12 +18,12 @@ class SpeechToTextTranscriptionData(UniversalBaseModel):
     Transcript of the provided speech in original language
     """
 
-    timestamps: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = pydantic.Field(default=None)
+    timestamps: typing.Optional[typing.Dict[str, typing.Any]] = pydantic.Field(default=None)
     """
     Timestamp information (if available)
     """
 
-    diarized_transcript: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = pydantic.Field(default=None)
+    diarized_transcript: typing.Optional[typing.Dict[str, typing.Any]] = pydantic.Field(default=None)
     """
     Diarized transcript of the provided speech
     """
@@ -34,11 +33,6 @@ class SpeechToTextTranscriptionData(UniversalBaseModel):
     BCP-47 code of detected language
     """
 
-    response_speech_state: typing.Optional[ResponseSpeechState] = pydantic.Field(default=None)
-    """
-    Current state of speech detection and processing
-    """
-
     metrics: TranscriptionMetrics
 
     if IS_PYDANTIC_V2:

sarvamai/types/speech_to_text_translate_transcription_data.py

@@ -4,7 +4,6 @@ import typing
 
 import pydantic
 from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
-from .response_speech_state import ResponseSpeechState
 from .transcription_metrics import TranscriptionMetrics
 
 
@@ -24,11 +23,6 @@ class SpeechToTextTranslateTranscriptionData(UniversalBaseModel):
     BCP-47 code of detected source language (null when language detection is in progress)
     """
 
-    response_speech_state: typing.Optional[ResponseSpeechState] = pydantic.Field(default=None)
-    """
-    Current state of speech detection and processing
-    """
-
     metrics: TranscriptionMetrics
 
     if IS_PYDANTIC_V2:

{sarvamai-0.1.22a3.dist-info → sarvamai-0.1.23a1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sarvamai
-Version: 0.1.22a3
+Version: 0.1.23a1
 Summary: 
 Requires-Python: >=3.8,<4.0
 Classifier: Intended Audience :: Developers
@@ -23,6 +23,7 @@ Requires-Dist: pydantic (>=1.9.2)
 Requires-Dist: pydantic-core (>=2.18.2)
 Requires-Dist: typing_extensions (>=4.0.0)
 Requires-Dist: websockets (>=12.0)
+Project-URL: Repository, https://github.com/sarvamai/sarvam-python-sdk
 Description-Content-Type: text/markdown
 
 # Sarvam Python Library