sarvamai 0.1.23a5__py3-none-any.whl → 0.1.23a7__py3-none-any.whl

sarvamai/speech_to_text_translate_streaming/raw_client.py

@@ -14,6 +14,7 @@ from .types.speech_to_text_translate_streaming_flush_signal import SpeechToTextT
 from .types.speech_to_text_translate_streaming_high_vad_sensitivity import (
     SpeechToTextTranslateStreamingHighVadSensitivity,
 )
+from .types.speech_to_text_translate_streaming_input_audio_codec import SpeechToTextTranslateStreamingInputAudioCodec
 from .types.speech_to_text_translate_streaming_vad_signals import SpeechToTextTranslateStreamingVadSignals
 
 try:
@@ -35,6 +36,7 @@ class RawSpeechToTextTranslateStreamingClient:
         high_vad_sensitivity: typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity] = None,
         vad_signals: typing.Optional[SpeechToTextTranslateStreamingVadSignals] = None,
         flush_signal: typing.Optional[SpeechToTextTranslateStreamingFlushSignal] = None,
+        input_audio_codec: typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec] = None,
         api_subscription_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> typing.Iterator[SpeechToTextTranslateStreamingSocketClient]:
@@ -65,6 +67,10 @@ class RawSpeechToTextTranslateStreamingClient:
         flush_signal : typing.Optional[SpeechToTextTranslateStreamingFlushSignal]
             Signal to flush the audio buffer and finalize transcription and translation
 
+        input_audio_codec : typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec]
+            Audio codec/format of the input stream. Use this when sending raw PCM audio.
+            Supported values: wav, pcm_s16le, pcm_l16, pcm_raw.
+
         api_subscription_key : typing.Optional[str]
             API subscription key for authentication
 
@@ -87,6 +93,8 @@ class RawSpeechToTextTranslateStreamingClient:
             query_params = query_params.add("vad_signals", vad_signals)
         if flush_signal is not None:
             query_params = query_params.add("flush_signal", flush_signal)
+        if input_audio_codec is not None:
+            query_params = query_params.add("input_audio_codec", input_audio_codec)
         ws_url = ws_url + f"?{query_params}"
         headers = self._client_wrapper.get_headers()
         if api_subscription_key is not None:
@@ -124,6 +132,7 @@ class AsyncRawSpeechToTextTranslateStreamingClient:
         high_vad_sensitivity: typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity] = None,
         vad_signals: typing.Optional[SpeechToTextTranslateStreamingVadSignals] = None,
         flush_signal: typing.Optional[SpeechToTextTranslateStreamingFlushSignal] = None,
+        input_audio_codec: typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec] = None,
         api_subscription_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> typing.AsyncIterator[AsyncSpeechToTextTranslateStreamingSocketClient]:
@@ -154,6 +163,10 @@ class AsyncRawSpeechToTextTranslateStreamingClient:
         flush_signal : typing.Optional[SpeechToTextTranslateStreamingFlushSignal]
             Signal to flush the audio buffer and finalize transcription and translation
 
+        input_audio_codec : typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec]
+            Audio codec/format of the input stream. Use this when sending raw PCM audio.
+            Supported values: wav, pcm_s16le, pcm_l16, pcm_raw.
+
         api_subscription_key : typing.Optional[str]
             API subscription key for authentication
 
@@ -176,6 +189,8 @@ class AsyncRawSpeechToTextTranslateStreamingClient:
             query_params = query_params.add("vad_signals", vad_signals)
         if flush_signal is not None:
             query_params = query_params.add("flush_signal", flush_signal)
+        if input_audio_codec is not None:
+            query_params = query_params.add("input_audio_codec", input_audio_codec)
         ws_url = ws_url + f"?{query_params}"
         headers = self._client_wrapper.get_headers()
         if api_subscription_key is not None:

sarvamai/speech_to_text_translate_streaming/types/__init__.py

@@ -4,10 +4,12 @@
 
 from .speech_to_text_translate_streaming_flush_signal import SpeechToTextTranslateStreamingFlushSignal
 from .speech_to_text_translate_streaming_high_vad_sensitivity import SpeechToTextTranslateStreamingHighVadSensitivity
+from .speech_to_text_translate_streaming_input_audio_codec import SpeechToTextTranslateStreamingInputAudioCodec
 from .speech_to_text_translate_streaming_vad_signals import SpeechToTextTranslateStreamingVadSignals
 
 __all__ = [
     "SpeechToTextTranslateStreamingFlushSignal",
     "SpeechToTextTranslateStreamingHighVadSensitivity",
+    "SpeechToTextTranslateStreamingInputAudioCodec",
     "SpeechToTextTranslateStreamingVadSignals",
 ]

sarvamai/speech_to_text_translate_streaming/types/speech_to_text_translate_streaming_input_audio_codec.py

@@ -0,0 +1,7 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+SpeechToTextTranslateStreamingInputAudioCodec = typing.Union[
+    typing.Literal["wav", "pcm_s16le", "pcm_l16", "pcm_raw"], typing.Any
+]

sarvamai/types/__init__.py

@@ -34,6 +34,21 @@ from .connection_sample_rate import ConnectionSampleRate
 from .create_chat_completion_response import CreateChatCompletionResponse
 from .diarized_entry import DiarizedEntry
 from .diarized_transcript import DiarizedTranscript
+from .doc_digitization_create_job_response import DocDigitizationCreateJobResponse
+from .doc_digitization_download_files_response import DocDigitizationDownloadFilesResponse
+from .doc_digitization_error_code import DocDigitizationErrorCode
+from .doc_digitization_error_details import DocDigitizationErrorDetails
+from .doc_digitization_error_message import DocDigitizationErrorMessage
+from .doc_digitization_job_detail import DocDigitizationJobDetail
+from .doc_digitization_job_detail_state import DocDigitizationJobDetailState
+from .doc_digitization_job_parameters import DocDigitizationJobParameters
+from .doc_digitization_job_state import DocDigitizationJobState
+from .doc_digitization_job_status_response import DocDigitizationJobStatusResponse
+from .doc_digitization_output_format import DocDigitizationOutputFormat
+from .doc_digitization_page_error import DocDigitizationPageError
+from .doc_digitization_supported_language import DocDigitizationSupportedLanguage
+from .doc_digitization_upload_files_response import DocDigitizationUploadFilesResponse
+from .doc_digitization_webhook_callback import DocDigitizationWebhookCallback
 from .error_code import ErrorCode
 from .error_data import ErrorData
 from .error_details import ErrorDetails
@@ -134,6 +149,21 @@ __all__ = [
     "CreateChatCompletionResponse",
     "DiarizedEntry",
     "DiarizedTranscript",
+    "DocDigitizationCreateJobResponse",
+    "DocDigitizationDownloadFilesResponse",
+    "DocDigitizationErrorCode",
+    "DocDigitizationErrorDetails",
+    "DocDigitizationErrorMessage",
+    "DocDigitizationJobDetail",
+    "DocDigitizationJobDetailState",
+    "DocDigitizationJobParameters",
+    "DocDigitizationJobState",
+    "DocDigitizationJobStatusResponse",
+    "DocDigitizationOutputFormat",
+    "DocDigitizationPageError",
+    "DocDigitizationSupportedLanguage",
+    "DocDigitizationUploadFilesResponse",
+    "DocDigitizationWebhookCallback",
     "ErrorCode",
     "ErrorData",
     "ErrorDetails",

sarvamai/types/doc_digitization_create_job_response.py

@@ -0,0 +1,37 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
+from .doc_digitization_job_parameters import DocDigitizationJobParameters
+from .doc_digitization_job_state import DocDigitizationJobState
+from .storage_container_type import StorageContainerType
+
+
+class DocDigitizationCreateJobResponse(UniversalBaseModel):
+    job_id: str = pydantic.Field()
+    """
+    Unique job identifier (UUID)
+    """
+
+    storage_container_type: StorageContainerType = pydantic.Field()
+    """
+    Storage Container Type
+    """
+
+    job_parameters: DocDigitizationJobParameters = pydantic.Field()
+    """
+    Job configuration parameters
+    """
+
+    job_state: DocDigitizationJobState
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

sarvamai/types/doc_digitization_download_files_response.py

@@ -0,0 +1,47 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
+from .doc_digitization_job_state import DocDigitizationJobState
+from .file_signed_url_details import FileSignedUrlDetails
+from .storage_container_type import StorageContainerType
+
+
+class DocDigitizationDownloadFilesResponse(UniversalBaseModel):
+    """
+    Response for download-files endpoint.
+    """
+
+    job_id: str = pydantic.Field()
+    """
+    Job identifier (UUID)
+    """
+
+    job_state: DocDigitizationJobState = pydantic.Field()
+    """
+    Current job state
+    """
+
+    storage_container_type: StorageContainerType = pydantic.Field()
+    """
+    Storage backend type
+    """
+
+    download_urls: typing.Dict[str, FileSignedUrlDetails] = pydantic.Field()
+    """
+    Map of filename to presigned download URL details
+    """
+
+    error_code: typing.Optional[str] = None
+    error_message: typing.Optional[str] = None
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

sarvamai/types/doc_digitization_error_code.py

@@ -0,0 +1,15 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+DocDigitizationErrorCode = typing.Union[
+    typing.Literal[
+        "invalid_request_error",
+        "internal_server_error",
+        "insufficient_quota_error",
+        "invalid_api_key_error",
+        "rate_limit_exceeded_error",
+        "high_load_error",
+    ],
+    typing.Any,
+]

sarvamai/types/doc_digitization_error_details.py

@@ -0,0 +1,33 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
+from .doc_digitization_error_code import DocDigitizationErrorCode
+
+
+class DocDigitizationErrorDetails(UniversalBaseModel):
+    message: str = pydantic.Field()
+    """
+    Message describing the error
+    """
+
+    code: DocDigitizationErrorCode = pydantic.Field()
+    """
+    Error code for the specific error that has occurred.
+    """
+
+    request_id: typing.Optional[str] = pydantic.Field(default=None)
+    """
+    Unique identifier for the request. Format: date_UUID4
+    """
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

sarvamai/types/doc_digitization_error_message.py

@@ -0,0 +1,23 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
+from .doc_digitization_error_details import DocDigitizationErrorDetails
+
+
+class DocDigitizationErrorMessage(UniversalBaseModel):
+    error: DocDigitizationErrorDetails = pydantic.Field()
+    """
+    Error details
+    """
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

sarvamai/types/doc_digitization_job_detail.py

@@ -0,0 +1,74 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
+from .doc_digitization_job_detail_state import DocDigitizationJobDetailState
+from .doc_digitization_page_error import DocDigitizationPageError
+from .task_file_details import TaskFileDetails
+
+
+class DocDigitizationJobDetail(UniversalBaseModel):
+    """
+    Processing details for a single input file with page-level metrics.
+    """
+
+    inputs: typing.List[TaskFileDetails] = pydantic.Field()
+    """
+    Input file(s) for this task
+    """
+
+    outputs: typing.List[TaskFileDetails] = pydantic.Field()
+    """
+    Output file(s) produced
+    """
+
+    state: DocDigitizationJobDetailState = pydantic.Field()
+    """
+    Processing state for this file
+    """
+
+    total_pages: typing.Optional[int] = pydantic.Field(default=None)
+    """
+    Total pages/images in the input file
+    """
+
+    pages_processed: typing.Optional[int] = pydantic.Field(default=None)
+    """
+    Number of pages processed so far
+    """
+
+    pages_succeeded: typing.Optional[int] = pydantic.Field(default=None)
+    """
+    Number of pages successfully processed
+    """
+
+    pages_failed: typing.Optional[int] = pydantic.Field(default=None)
+    """
+    Number of pages that failed processing
+    """
+
+    error_message: typing.Optional[str] = pydantic.Field(default=None)
+    """
+    Error message if processing failed
+    """
+
+    error_code: typing.Optional[str] = pydantic.Field(default=None)
+    """
+    Standardized error code if failed
+    """
+
+    page_errors: typing.Optional[typing.List[DocDigitizationPageError]] = pydantic.Field(default=None)
+    """
+    Detailed errors for each failed page
+    """
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

sarvamai/types/doc_digitization_job_detail_state.py

@@ -0,0 +1,7 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+DocDigitizationJobDetailState = typing.Union[
+    typing.Literal["Pending", "Running", "Success", "PartialSuccess", "Failed"], typing.Any
+]

sarvamai/types/doc_digitization_job_parameters.py

@@ -0,0 +1,33 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
+from .doc_digitization_output_format import DocDigitizationOutputFormat
+from .doc_digitization_supported_language import DocDigitizationSupportedLanguage
+
+
+class DocDigitizationJobParameters(UniversalBaseModel):
+    """
+    Job parameters for document digitization.
+    """
+
+    language: typing.Optional[DocDigitizationSupportedLanguage] = pydantic.Field(default=None)
+    """
+    ISO language code for the document
+    """
+
+    output_format: typing.Optional[DocDigitizationOutputFormat] = pydantic.Field(default=None)
+    """
+    Output format: html or md
+    """
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

sarvamai/types/doc_digitization_job_state.py

@@ -0,0 +1,7 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+DocDigitizationJobState = typing.Union[
+    typing.Literal["Accepted", "Pending", "Running", "Completed", "PartiallyCompleted", "Failed"], typing.Any
+]

sarvamai/types/doc_digitization_job_status_response.py

@@ -0,0 +1,75 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
+from .doc_digitization_job_detail import DocDigitizationJobDetail
+from .doc_digitization_job_state import DocDigitizationJobState
+from .storage_container_type import StorageContainerType
+
+
+class DocDigitizationJobStatusResponse(UniversalBaseModel):
+    """
+    Response model for job status endpoint.
+    """
+
+    job_id: str = pydantic.Field()
+    """
+    Job identifier (UUID)
+    """
+
+    job_state: DocDigitizationJobState = pydantic.Field()
+    """
+    Current job state
+    """
+
+    created_at: dt.datetime = pydantic.Field()
+    """
+    Job creation timestamp (ISO 8601)
+    """
+
+    updated_at: dt.datetime = pydantic.Field()
+    """
+    Last update timestamp (ISO 8601)
+    """
+
+    storage_container_type: StorageContainerType = pydantic.Field()
+    """
+    Storage backend type
+    """
+
+    total_files: typing.Optional[int] = pydantic.Field(default=None)
+    """
+    Total input files (always 1)
+    """
+
+    successful_files_count: typing.Optional[int] = pydantic.Field(default=None)
+    """
+    Files that completed successfully
+    """
+
+    failed_files_count: typing.Optional[int] = pydantic.Field(default=None)
+    """
+    Files that failed
+    """
+
+    error_message: typing.Optional[str] = pydantic.Field(default=None)
+    """
+    Job-level error message
+    """
+
+    job_details: typing.Optional[typing.List[DocDigitizationJobDetail]] = pydantic.Field(default=None)
+    """
+    Per-file processing details with page metrics
+    """
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

sarvamai/types/doc_digitization_output_format.py

@@ -0,0 +1,5 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+DocDigitizationOutputFormat = typing.Union[typing.Literal["html", "md"], typing.Any]

sarvamai/types/doc_digitization_page_error.py

@@ -0,0 +1,36 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
+
+
+class DocDigitizationPageError(UniversalBaseModel):
+    """
+    Error details for a specific page.
+    """
+
+    page_number: int = pydantic.Field()
+    """
+    Page number that failed
+    """
+
+    error_code: str = pydantic.Field()
+    """
+    Standardized error code
+    """
+
+    error_message: str = pydantic.Field()
+    """
+    Human-readable error description
+    """
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

sarvamai/types/doc_digitization_supported_language.py

@@ -0,0 +1,32 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+DocDigitizationSupportedLanguage = typing.Union[
+    typing.Literal[
+        "hi",
+        "en",
+        "bn",
+        "gu",
+        "kn",
+        "ml",
+        "mr",
+        "or",
+        "pa",
+        "ta",
+        "te",
+        "ur",
+        "as",
+        "bodo",
+        "doi",
+        "ks",
+        "kok",
+        "mai",
+        "mni",
+        "ne",
+        "sa",
+        "sat",
+        "sd",
+    ],
+    typing.Any,
+]

sarvamai/types/doc_digitization_upload_files_response.py

@@ -0,0 +1,44 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
+from .doc_digitization_job_state import DocDigitizationJobState
+from .file_signed_url_details import FileSignedUrlDetails
+from .storage_container_type import StorageContainerType
+
+
+class DocDigitizationUploadFilesResponse(UniversalBaseModel):
+    """
+    Response with presigned upload URLs
+    """
+
+    job_id: str = pydantic.Field()
+    """
+    Job identifier
+    """
+
+    job_state: DocDigitizationJobState = pydantic.Field()
+    """
+    Current job state
+    """
+
+    upload_urls: typing.Dict[str, FileSignedUrlDetails] = pydantic.Field()
+    """
+    Map of filename to presigned upload URL details
+    """
+
+    storage_container_type: StorageContainerType = pydantic.Field()
+    """
+    Storage backend type
+    """
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

sarvamai/types/doc_digitization_webhook_callback.py

@@ -0,0 +1,31 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
+
+
+class DocDigitizationWebhookCallback(UniversalBaseModel):
+    """
+    Webhook configuration for job completion notification
+    """
+
+    url: str = pydantic.Field()
+    """
+    HTTPS webhook URL to call upon job completion (HTTP not allowed)
+    """
+
+    auth_token: typing.Optional[str] = pydantic.Field(default=None)
+    """
+    Authorization token sent as X-SARVAM-JOB-CALLBACK-TOKEN header
+    """
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

{sarvamai-0.1.23a5.dist-info → sarvamai-0.1.23a7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sarvamai
-Version: 0.1.23a5
+Version: 0.1.23a7
 Summary: 
 Requires-Python: >=3.8,<4.0
 Classifier: Intended Audience :: Developers