sarvamai 0.1.23a6__py3-none-any.whl → 0.1.23a8__py3-none-any.whl

sarvamai/requests/__init__.py

@@ -27,6 +27,16 @@ from .configure_connection_data import ConfigureConnectionDataParams
 from .create_chat_completion_response import CreateChatCompletionResponseParams
 from .diarized_entry import DiarizedEntryParams
 from .diarized_transcript import DiarizedTranscriptParams
+from .doc_digitization_create_job_response import DocDigitizationCreateJobResponseParams
+from .doc_digitization_download_files_response import DocDigitizationDownloadFilesResponseParams
+from .doc_digitization_error_details import DocDigitizationErrorDetailsParams
+from .doc_digitization_error_message import DocDigitizationErrorMessageParams
+from .doc_digitization_job_detail import DocDigitizationJobDetailParams
+from .doc_digitization_job_parameters import DocDigitizationJobParametersParams
+from .doc_digitization_job_status_response import DocDigitizationJobStatusResponseParams
+from .doc_digitization_page_error import DocDigitizationPageErrorParams
+from .doc_digitization_upload_files_response import DocDigitizationUploadFilesResponseParams
+from .doc_digitization_webhook_callback import DocDigitizationWebhookCallbackParams
 from .error_data import ErrorDataParams
 from .error_details import ErrorDetailsParams
 from .error_message import ErrorMessageParams
@@ -89,6 +99,16 @@ __all__ = [
     "CreateChatCompletionResponseParams",
     "DiarizedEntryParams",
     "DiarizedTranscriptParams",
+    "DocDigitizationCreateJobResponseParams",
+    "DocDigitizationDownloadFilesResponseParams",
+    "DocDigitizationErrorDetailsParams",
+    "DocDigitizationErrorMessageParams",
+    "DocDigitizationJobDetailParams",
+    "DocDigitizationJobParametersParams",
+    "DocDigitizationJobStatusResponseParams",
+    "DocDigitizationPageErrorParams",
+    "DocDigitizationUploadFilesResponseParams",
+    "DocDigitizationWebhookCallbackParams",
     "ErrorDataParams",
     "ErrorDetailsParams",
     "ErrorMessageParams",

sarvamai/requests/doc_digitization_create_job_response.py

@@ -0,0 +1,25 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+from ..types.doc_digitization_job_state import DocDigitizationJobState
+from ..types.storage_container_type import StorageContainerType
+from .doc_digitization_job_parameters import DocDigitizationJobParametersParams
+
+
+class DocDigitizationCreateJobResponseParams(typing_extensions.TypedDict):
+    job_id: str
+    """
+    Unique job identifier (UUID)
+    """
+
+    storage_container_type: StorageContainerType
+    """
+    Storage Container Type
+    """
+
+    job_parameters: DocDigitizationJobParametersParams
+    """
+    Job configuration parameters
+    """
+
+    job_state: DocDigitizationJobState

sarvamai/requests/doc_digitization_download_files_response.py

@@ -0,0 +1,37 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+from ..types.doc_digitization_job_state import DocDigitizationJobState
+from ..types.storage_container_type import StorageContainerType
+from .file_signed_url_details import FileSignedUrlDetailsParams
+
+
+class DocDigitizationDownloadFilesResponseParams(typing_extensions.TypedDict):
+    """
+    Response for download-files endpoint.
+    """
+
+    job_id: str
+    """
+    Job identifier (UUID)
+    """
+
+    job_state: DocDigitizationJobState
+    """
+    Current job state
+    """
+
+    storage_container_type: StorageContainerType
+    """
+    Storage backend type
+    """
+
+    download_urls: typing.Dict[str, FileSignedUrlDetailsParams]
+    """
+    Map of filename to presigned download URL details
+    """
+
+    error_code: typing_extensions.NotRequired[str]
+    error_message: typing_extensions.NotRequired[str]

sarvamai/requests/doc_digitization_error_details.py

@@ -0,0 +1,21 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+from ..types.doc_digitization_error_code import DocDigitizationErrorCode
+
+
+class DocDigitizationErrorDetailsParams(typing_extensions.TypedDict):
+    message: str
+    """
+    Message describing the error
+    """
+
+    code: DocDigitizationErrorCode
+    """
+    Error code for the specific error that has occurred.
+    """
+
+    request_id: typing_extensions.NotRequired[str]
+    """
+    Unique identifier for the request. Format: date_UUID4
+    """

sarvamai/requests/doc_digitization_error_message.py

@@ -0,0 +1,11 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+from .doc_digitization_error_details import DocDigitizationErrorDetailsParams
+
+
+class DocDigitizationErrorMessageParams(typing_extensions.TypedDict):
+    error: DocDigitizationErrorDetailsParams
+    """
+    Error details
+    """

sarvamai/requests/doc_digitization_job_detail.py

@@ -0,0 +1,64 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+from ..types.doc_digitization_job_detail_state import DocDigitizationJobDetailState
+from .doc_digitization_page_error import DocDigitizationPageErrorParams
+from .task_file_details import TaskFileDetailsParams
+
+
+class DocDigitizationJobDetailParams(typing_extensions.TypedDict):
+    """
+    Processing details for a single input file with page-level metrics.
+    """
+
+    inputs: typing.Sequence[TaskFileDetailsParams]
+    """
+    Input file(s) for this task
+    """
+
+    outputs: typing.Sequence[TaskFileDetailsParams]
+    """
+    Output file(s) produced
+    """
+
+    state: DocDigitizationJobDetailState
+    """
+    Processing state for this file
+    """
+
+    total_pages: typing_extensions.NotRequired[int]
+    """
+    Total pages/images in the input file
+    """
+
+    pages_processed: typing_extensions.NotRequired[int]
+    """
+    Number of pages processed so far
+    """
+
+    pages_succeeded: typing_extensions.NotRequired[int]
+    """
+    Number of pages successfully processed
+    """
+
+    pages_failed: typing_extensions.NotRequired[int]
+    """
+    Number of pages that failed processing
+    """
+
+    error_message: typing_extensions.NotRequired[str]
+    """
+    Error message if processing failed
+    """
+
+    error_code: typing_extensions.NotRequired[str]
+    """
+    Standardized error code if failed
+    """
+
+    page_errors: typing_extensions.NotRequired[typing.Sequence[DocDigitizationPageErrorParams]]
+    """
+    Detailed errors for each failed page
+    """

sarvamai/requests/doc_digitization_job_parameters.py

@@ -0,0 +1,21 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+from ..types.doc_digitization_output_format import DocDigitizationOutputFormat
+from ..types.doc_digitization_supported_language import DocDigitizationSupportedLanguage
+
+
+class DocDigitizationJobParametersParams(typing_extensions.TypedDict):
+    """
+    Job parameters for document digitization.
+    """
+
+    language: typing_extensions.NotRequired[DocDigitizationSupportedLanguage]
+    """
+    ISO language code for the document
+    """
+
+    output_format: typing_extensions.NotRequired[DocDigitizationOutputFormat]
+    """
+    Output format: html or md
+    """

sarvamai/requests/doc_digitization_job_status_response.py

@@ -0,0 +1,65 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+import typing_extensions
+from ..types.doc_digitization_job_state import DocDigitizationJobState
+from ..types.storage_container_type import StorageContainerType
+from .doc_digitization_job_detail import DocDigitizationJobDetailParams
+
+
+class DocDigitizationJobStatusResponseParams(typing_extensions.TypedDict):
+    """
+    Response model for job status endpoint.
+    """
+
+    job_id: str
+    """
+    Job identifier (UUID)
+    """
+
+    job_state: DocDigitizationJobState
+    """
+    Current job state
+    """
+
+    created_at: dt.datetime
+    """
+    Job creation timestamp (ISO 8601)
+    """
+
+    updated_at: dt.datetime
+    """
+    Last update timestamp (ISO 8601)
+    """
+
+    storage_container_type: StorageContainerType
+    """
+    Storage backend type
+    """
+
+    total_files: typing_extensions.NotRequired[int]
+    """
+    Total input files (always 1)
+    """
+
+    successful_files_count: typing_extensions.NotRequired[int]
+    """
+    Files that completed successfully
+    """
+
+    failed_files_count: typing_extensions.NotRequired[int]
+    """
+    Files that failed
+    """
+
+    error_message: typing_extensions.NotRequired[str]
+    """
+    Job-level error message
+    """
+
+    job_details: typing_extensions.NotRequired[typing.Sequence[DocDigitizationJobDetailParams]]
+    """
+    Per-file processing details with page metrics
+    """

sarvamai/requests/doc_digitization_page_error.py

@@ -0,0 +1,24 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+
+
+class DocDigitizationPageErrorParams(typing_extensions.TypedDict):
+    """
+    Error details for a specific page.
+    """
+
+    page_number: int
+    """
+    Page number that failed
+    """
+
+    error_code: str
+    """
+    Standardized error code
+    """
+
+    error_message: str
+    """
+    Human-readable error description
+    """

sarvamai/requests/doc_digitization_upload_files_response.py

@@ -0,0 +1,34 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+from ..types.doc_digitization_job_state import DocDigitizationJobState
+from ..types.storage_container_type import StorageContainerType
+from .file_signed_url_details import FileSignedUrlDetailsParams
+
+
+class DocDigitizationUploadFilesResponseParams(typing_extensions.TypedDict):
+    """
+    Response with presigned upload URLs
+    """
+
+    job_id: str
+    """
+    Job identifier
+    """
+
+    job_state: DocDigitizationJobState
+    """
+    Current job state
+    """
+
+    upload_urls: typing.Dict[str, FileSignedUrlDetailsParams]
+    """
+    Map of filename to presigned upload URL details
+    """
+
+    storage_container_type: StorageContainerType
+    """
+    Storage backend type
+    """

sarvamai/requests/doc_digitization_webhook_callback.py

@@ -0,0 +1,19 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+
+
+class DocDigitizationWebhookCallbackParams(typing_extensions.TypedDict):
+    """
+    Webhook configuration for job completion notification
+    """
+
+    url: str
+    """
+    HTTPS webhook URL to call upon job completion (HTTP not allowed)
+    """
+
+    auth_token: typing_extensions.NotRequired[str]
+    """
+    Authorization token sent as X-SARVAM-JOB-CALLBACK-TOKEN header
+    """

sarvamai/requests/speech_to_text_response.py

@@ -1,20 +1,28 @@
 # This file was auto-generated by Fern from our API Definition.
 
 import typing_extensions
+from .diarized_transcript import DiarizedTranscriptParams
+from .timestamps_model import TimestampsModelParams
 
 
 class SpeechToTextResponseParams(typing_extensions.TypedDict):
-    request_id: str
+    request_id: typing_extensions.NotRequired[str]
+    transcript: str
     """
-    Unique identifier for the request
+    The transcribed text from the provided audio file.
     """
 
-    transcript: str
+    timestamps: typing_extensions.NotRequired[TimestampsModelParams]
     """
-    The transcribed text from the provided audio file.
+    Contains timestamps for the transcribed text. This field is included only if with_timestamps is set to true
+    """
+
+    diarized_transcript: typing_extensions.NotRequired[DiarizedTranscriptParams]
+    """
+    Diarized transcript of the provided speech
     """
 
-    language_code: str
+    language_code: typing_extensions.NotRequired[str]
     """
-    The BCP-47 code of language spoken in the input (e.g., hi-IN, en-IN). If multiple languages are detected, returns the most predominant spoken language.
+    This will return the BCP-47 code of language spoken in the input. If multiple languages are detected, this will return language code of most predominant spoken language. If no language is detected, this will be null
     """

sarvamai/requests/speech_to_text_transcription_data.py

@@ -32,18 +32,4 @@ class SpeechToTextTranscriptionDataParams(typing_extensions.TypedDict):
     BCP-47 code of detected language
     """
 
-    language_probability: typing_extensions.NotRequired[float]
-    """
-    Float value (0.0 to 1.0) indicating the probability of the detected language being correct. Higher values indicate higher confidence.
-    
-    **When it returns a value:**
-    - When `language_code` is not provided in the request
-    - When `language_code` is set to `unknown`
-    
-    **When it returns null:**
-    - When a specific `language_code` is provided (language detection is skipped)
-    
-    The parameter is always present in the response.
-    """
-
     metrics: TranscriptionMetricsParams

sarvamai/requests/speech_to_text_translate_response.py

@@ -1,20 +1,23 @@
 # This file was auto-generated by Fern from our API Definition.
 
 import typing_extensions
+from ..types.speech_to_text_translate_language import SpeechToTextTranslateLanguage
+from .diarized_transcript import DiarizedTranscriptParams
 
 
 class SpeechToTextTranslateResponseParams(typing_extensions.TypedDict):
-    request_id: str
+    request_id: typing_extensions.NotRequired[str]
+    transcript: str
     """
-    Unique identifier for the request
+    Transcript of the provided speech
     """
 
-    transcript: str
+    language_code: typing_extensions.NotRequired[SpeechToTextTranslateLanguage]
     """
-    English translation of the provided speech
+    This will return the BCP-47 code of language spoken in the input. If multiple languages are detected, this will return language code of most predominant spoken language. If no language is detected, this will be null
     """
 
-    language_code: str
+    diarized_transcript: typing_extensions.NotRequired[DiarizedTranscriptParams]
     """
-    The BCP-47 code of the detected source language spoken in the input (e.g., hi-IN, kn-IN).
+    Diarized transcript of the provided speech
     """

sarvamai/requests/speech_to_text_translate_transcription_data.py

@@ -20,17 +20,4 @@ class SpeechToTextTranslateTranscriptionDataParams(typing_extensions.TypedDict):
     BCP-47 code of detected source language (null when language detection is in progress)
     """
 
-    language_probability: typing_extensions.NotRequired[float]
-    """
-    Float value (0.0 to 1.0) indicating the probability of the detected source language being correct. Higher values indicate higher confidence.
-    
-    **When it returns a value:**
-    - Always returns a value as source language is auto-detected for translation
-    
-    **When it returns null:**
-    - When language detection confidence is unavailable
-    
-    The parameter is always present in the response.
-    """
-
     metrics: TranscriptionMetricsParams

sarvamai/speech_to_text_streaming/client.py

@@ -67,7 +67,7 @@ class SpeechToTextStreamingClient:
         language_code : SpeechToTextStreamingLanguageCode
             Specifies the language of the input audio in BCP-47 format.
 
-            **Available Options (saarika:v2.5):**
+            **Available Options:**
             - `hi-IN`: Hindi
             - `bn-IN`: Bengali
             - `gu-IN`: Gujarati
@@ -80,20 +80,6 @@ class SpeechToTextStreamingClient:
             - `te-IN`: Telugu
             - `en-IN`: English
 
-            **Additional Options (saaras:v3 only):**
-            - `as-IN`: Assamese
-            - `ur-IN`: Urdu
-            - `ne-IN`: Nepali
-            - `kok-IN`: Konkani
-            - `ks-IN`: Kashmiri
-            - `sd-IN`: Sindhi
-            - `sa-IN`: Sanskrit
-            - `sat-IN`: Santali
-            - `mni-IN`: Manipuri
-            - `brx-IN`: Bodo
-            - `mai-IN`: Maithili
-            - `doi-IN`: Dogri
-
         model : typing.Optional[SpeechToTextStreamingModel]
             Specifies the model to use for speech-to-text conversion.
 
@@ -231,7 +217,7 @@ class AsyncSpeechToTextStreamingClient:
         language_code : SpeechToTextStreamingLanguageCode
             Specifies the language of the input audio in BCP-47 format.
 
-            **Available Options (saarika:v2.5):**
+            **Available Options:**
             - `hi-IN`: Hindi
             - `bn-IN`: Bengali
             - `gu-IN`: Gujarati
@@ -244,20 +230,6 @@ class AsyncSpeechToTextStreamingClient:
             - `te-IN`: Telugu
             - `en-IN`: English
 
-            **Additional Options (saaras:v3 only):**
-            - `as-IN`: Assamese
-            - `ur-IN`: Urdu
-            - `ne-IN`: Nepali
-            - `kok-IN`: Konkani
-            - `ks-IN`: Kashmiri
-            - `sd-IN`: Sindhi
-            - `sa-IN`: Sanskrit
-            - `sat-IN`: Santali
-            - `mni-IN`: Manipuri
-            - `brx-IN`: Bodo
-            - `mai-IN`: Maithili
-            - `doi-IN`: Dogri
-
         model : typing.Optional[SpeechToTextStreamingModel]
             Specifies the model to use for speech-to-text conversion.
 

sarvamai/speech_to_text_streaming/raw_client.py

@@ -55,7 +55,7 @@ class RawSpeechToTextStreamingClient:
         language_code : SpeechToTextStreamingLanguageCode
             Specifies the language of the input audio in BCP-47 format.
 
-            **Available Options (saarika:v2.5):**
+            **Available Options:**
             - `hi-IN`: Hindi
             - `bn-IN`: Bengali
             - `gu-IN`: Gujarati
@@ -68,20 +68,6 @@ class RawSpeechToTextStreamingClient:
             - `te-IN`: Telugu
             - `en-IN`: English
 
-            **Additional Options (saaras:v3 only):**
-            - `as-IN`: Assamese
-            - `ur-IN`: Urdu
-            - `ne-IN`: Nepali
-            - `kok-IN`: Konkani
-            - `ks-IN`: Kashmiri
-            - `sd-IN`: Sindhi
-            - `sa-IN`: Sanskrit
-            - `sat-IN`: Santali
-            - `mni-IN`: Manipuri
-            - `brx-IN`: Bodo
-            - `mai-IN`: Maithili
-            - `doi-IN`: Dogri
-
         model : typing.Optional[SpeechToTextStreamingModel]
             Specifies the model to use for speech-to-text conversion.
 
@@ -208,7 +194,7 @@ class AsyncRawSpeechToTextStreamingClient:
         language_code : SpeechToTextStreamingLanguageCode
             Specifies the language of the input audio in BCP-47 format.
 
-            **Available Options (saarika:v2.5):**
+            **Available Options:**
             - `hi-IN`: Hindi
             - `bn-IN`: Bengali
             - `gu-IN`: Gujarati
@@ -221,20 +207,6 @@ class AsyncRawSpeechToTextStreamingClient:
             - `te-IN`: Telugu
             - `en-IN`: English
 
-            **Additional Options (saaras:v3 only):**
-            - `as-IN`: Assamese
-            - `ur-IN`: Urdu
-            - `ne-IN`: Nepali
-            - `kok-IN`: Konkani
-            - `ks-IN`: Kashmiri
-            - `sd-IN`: Sindhi
-            - `sa-IN`: Sanskrit
-            - `sat-IN`: Santali
-            - `mni-IN`: Manipuri
-            - `brx-IN`: Bodo
-            - `mai-IN`: Maithili
-            - `doi-IN`: Dogri
-
         model : typing.Optional[SpeechToTextStreamingModel]
             Specifies the model to use for speech-to-text conversion.
 

sarvamai/speech_to_text_streaming/types/speech_to_text_streaming_language_code.py

@@ -3,30 +3,6 @@
 import typing
 
 SpeechToTextStreamingLanguageCode = typing.Union[
-    typing.Literal[
-        "en-IN",
-        "hi-IN",
-        "bn-IN",
-        "gu-IN",
-        "kn-IN",
-        "ml-IN",
-        "mr-IN",
-        "od-IN",
-        "pa-IN",
-        "ta-IN",
-        "te-IN",
-        "as-IN",
-        "ur-IN",
-        "ne-IN",
-        "kok-IN",
-        "ks-IN",
-        "sd-IN",
-        "sa-IN",
-        "sat-IN",
-        "mni-IN",
-        "brx-IN",
-        "mai-IN",
-        "doi-IN",
-    ],
+    typing.Literal["en-IN", "hi-IN", "bn-IN", "gu-IN", "kn-IN", "ml-IN", "mr-IN", "od-IN", "pa-IN", "ta-IN", "te-IN"],
     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",