orq-ai-sdk 4.2.0rc28__py3-none-any.whl → 4.2.6__py3-none-any.whl

orq_ai_sdk/models/createtranscriptionop.py

@@ -0,0 +1,562 @@
+"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
+
+from __future__ import annotations
+from .publiccontact import PublicContact, PublicContactTypedDict
+from .publicidentity import PublicIdentity, PublicIdentityTypedDict
+from dataclasses import dataclass, field
+import httpx
+import io
+from orq_ai_sdk.models import OrqError
+from orq_ai_sdk.types import BaseModel, Nullable, UNSET_SENTINEL
+from orq_ai_sdk.utils import FieldMetadata, MultipartFormMetadata
+import pydantic
+from pydantic import model_serializer
+from typing import IO, List, Literal, Optional, Union
+from typing_extensions import Annotated, NotRequired, TypeAliasType, TypedDict
+
+
+CreateTranscriptionResponseFormat = Literal[
+    "json",
+    "text",
+    "srt",
+    "verbose_json",
+    "vtt",
+]
+r"""The format of the transcript output, in one of these options: json, text, srt, verbose_json, or vtt."""
+
+
+TimestampsGranularity = Literal[
+    "none",
+    "word",
+    "character",
+]
+r"""The granularity of the timestamps in the transcription. Word provides word-level timestamps and character provides character-level timestamps per word."""
+
+
+TimestampGranularities = Literal[
+    "word",
+    "segment",
+]
+
+
+class CreateTranscriptionFallbacksTypedDict(TypedDict):
+    model: str
+    r"""Fallback model identifier"""
+
+
+class CreateTranscriptionFallbacks(BaseModel):
+    model: str
+    r"""Fallback model identifier"""
+
+
+class CreateTranscriptionRetryTypedDict(TypedDict):
+    r"""Retry configuration for the request"""
+
+    count: NotRequired[float]
+    r"""Number of retry attempts (1-5)"""
+    on_codes: NotRequired[List[float]]
+    r"""HTTP status codes that trigger retry logic"""
+
+
+class CreateTranscriptionRetry(BaseModel):
+    r"""Retry configuration for the request"""
+
+    count: Optional[float] = 3
+    r"""Number of retry attempts (1-5)"""
+
+    on_codes: Optional[List[float]] = None
+    r"""HTTP status codes that trigger retry logic"""
+
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = set(["count", "on_codes"])
+        serialized = handler(self)
+        m = {}
+
+        for n, f in type(self).model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+
+            if val != UNSET_SENTINEL:
+                if val is not None or k not in optional_fields:
+                    m[k] = val
+
+        return m
+
+
+CreateTranscriptionLoadBalancerType = Literal["weight_based",]
+
+
+class CreateTranscriptionLoadBalancerModelsTypedDict(TypedDict):
+    model: str
+    r"""Model identifier for load balancing"""
+    weight: NotRequired[float]
+    r"""Weight assigned to this model for load balancing"""
+
+
+class CreateTranscriptionLoadBalancerModels(BaseModel):
+    model: str
+    r"""Model identifier for load balancing"""
+
+    weight: Optional[float] = 0.5
+    r"""Weight assigned to this model for load balancing"""
+
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = set(["weight"])
+        serialized = handler(self)
+        m = {}
+
+        for n, f in type(self).model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+
+            if val != UNSET_SENTINEL:
+                if val is not None or k not in optional_fields:
+                    m[k] = val
+
+        return m
+
+
+class CreateTranscriptionLoadBalancer1TypedDict(TypedDict):
+    type: CreateTranscriptionLoadBalancerType
+    models: List[CreateTranscriptionLoadBalancerModelsTypedDict]
+
+
+class CreateTranscriptionLoadBalancer1(BaseModel):
+    type: CreateTranscriptionLoadBalancerType
+
+    models: List[CreateTranscriptionLoadBalancerModels]
+
+
+CreateTranscriptionLoadBalancerTypedDict = CreateTranscriptionLoadBalancer1TypedDict
+r"""Array of models with weights for load balancing requests"""
+
+
+CreateTranscriptionLoadBalancer = CreateTranscriptionLoadBalancer1
+r"""Array of models with weights for load balancing requests"""
+
+
+class CreateTranscriptionTimeoutTypedDict(TypedDict):
+    r"""Timeout configuration to apply to the request. If the request exceeds the timeout, it will be retried or fallback to the next model if configured."""
+
+    call_timeout: float
+    r"""Timeout value in milliseconds"""
+
+
+class CreateTranscriptionTimeout(BaseModel):
+    r"""Timeout configuration to apply to the request. If the request exceeds the timeout, it will be retried or fallback to the next model if configured."""
+
+    call_timeout: float
+    r"""Timeout value in milliseconds"""
+
+
+class CreateTranscriptionOrqTypedDict(TypedDict):
+    name: NotRequired[str]
+    r"""The name to display on the trace. If not specified, the default system name will be used."""
+    fallbacks: NotRequired[List[CreateTranscriptionFallbacksTypedDict]]
+    r"""Array of fallback models to use if primary model fails"""
+    retry: NotRequired[CreateTranscriptionRetryTypedDict]
+    r"""Retry configuration for the request"""
+    identity: NotRequired[PublicIdentityTypedDict]
+    r"""Information about the identity making the request. If the identity does not exist, it will be created automatically."""
+    contact: NotRequired[PublicContactTypedDict]
+    r"""@deprecated Use identity instead. Information about the contact making the request."""
+    load_balancer: NotRequired[CreateTranscriptionLoadBalancerTypedDict]
+    r"""Array of models with weights for load balancing requests"""
+    timeout: NotRequired[CreateTranscriptionTimeoutTypedDict]
+    r"""Timeout configuration to apply to the request. If the request exceeds the timeout, it will be retried or fallback to the next model if configured."""
+
+
+class CreateTranscriptionOrq(BaseModel):
+    name: Optional[str] = None
+    r"""The name to display on the trace. If not specified, the default system name will be used."""
+
+    fallbacks: Optional[List[CreateTranscriptionFallbacks]] = None
+    r"""Array of fallback models to use if primary model fails"""
+
+    retry: Optional[CreateTranscriptionRetry] = None
+    r"""Retry configuration for the request"""
+
+    identity: Optional[PublicIdentity] = None
+    r"""Information about the identity making the request. If the identity does not exist, it will be created automatically."""
+
+    contact: Annotated[
+        Optional[PublicContact],
+        pydantic.Field(
+            deprecated="warning: ** DEPRECATED ** - This will be removed in a future release, please migrate away from it as soon as possible."
+        ),
+    ] = None
+    r"""@deprecated Use identity instead. Information about the contact making the request."""
+
+    load_balancer: Optional[CreateTranscriptionLoadBalancer] = None
+    r"""Array of models with weights for load balancing requests"""
+
+    timeout: Optional[CreateTranscriptionTimeout] = None
+    r"""Timeout configuration to apply to the request. If the request exceeds the timeout, it will be retried or fallback to the next model if configured."""
+
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = set(
+            [
+                "name",
+                "fallbacks",
+                "retry",
+                "identity",
+                "contact",
+                "load_balancer",
+                "timeout",
+            ]
+        )
+        serialized = handler(self)
+        m = {}
+
+        for n, f in type(self).model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+
+            if val != UNSET_SENTINEL:
+                if val is not None or k not in optional_fields:
+                    m[k] = val
+
+        return m
+
+
+class CreateTranscriptionFileTypedDict(TypedDict):
+    file_name: str
+    content: Union[bytes, IO[bytes], io.BufferedReader]
+    content_type: NotRequired[str]
+
+
+class CreateTranscriptionFile(BaseModel):
+    file_name: Annotated[
+        str, pydantic.Field(alias="fileName"), FieldMetadata(multipart=True)
+    ]
+
+    content: Annotated[
+        Union[bytes, IO[bytes], io.BufferedReader],
+        pydantic.Field(alias=""),
+        FieldMetadata(multipart=MultipartFormMetadata(content=True)),
+    ]
+
+    content_type: Annotated[
+        Optional[str],
+        pydantic.Field(alias="Content-Type"),
+        FieldMetadata(multipart=True),
+    ] = None
+
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = set(["contentType"])
+        serialized = handler(self)
+        m = {}
+
+        for n, f in type(self).model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+
+            if val != UNSET_SENTINEL:
+                if val is not None or k not in optional_fields:
+                    m[k] = val
+
+        return m
+
+
+class CreateTranscriptionRequestBodyTypedDict(TypedDict):
+    r"""Transcribes audio into the input language."""
+
+    model: str
+    r"""ID of the model to use"""
+    prompt: NotRequired[str]
+    r"""An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language."""
+    enable_logging: NotRequired[bool]
+    r"""When enable_logging is set to false, zero retention mode is used. This disables history features like request stitching and is only available to enterprise customers."""
+    diarize: NotRequired[bool]
+    r"""Whether to annotate which speaker is currently talking in the uploaded file."""
+    response_format: NotRequired[CreateTranscriptionResponseFormat]
+    r"""The format of the transcript output, in one of these options: json, text, srt, verbose_json, or vtt."""
+    tag_audio_events: NotRequired[bool]
+    r"""Whether to tag audio events like (laughter), (footsteps), etc. in the transcription."""
+    num_speakers: NotRequired[float]
+    r"""The maximum amount of speakers talking in the uploaded file. Helps with predicting who speaks when, the maximum is 32."""
+    timestamps_granularity: NotRequired[TimestampsGranularity]
+    r"""The granularity of the timestamps in the transcription. Word provides word-level timestamps and character provides character-level timestamps per word."""
+    temperature: NotRequired[float]
+    r"""The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit."""
+    language: NotRequired[str]
+    r"""The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency."""
+    timestamp_granularities: NotRequired[List[TimestampGranularities]]
+    r"""The timestamp granularities to populate for this transcription. response_format must be set to verbose_json to use timestamp granularities. Either or both of these options are supported: \"word\" or \"segment\". Note: There is no additional latency for segment timestamps, but generating word timestamps incurs additional latency."""
+    orq: NotRequired[CreateTranscriptionOrqTypedDict]
+    file: NotRequired[CreateTranscriptionFileTypedDict]
+    r"""The audio file object (not file name) to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm."""
+
+
+class CreateTranscriptionRequestBody(BaseModel):
+    r"""Transcribes audio into the input language."""
+
+    model: Annotated[str, FieldMetadata(multipart=True)]
+    r"""ID of the model to use"""
+
+    prompt: Annotated[Optional[str], FieldMetadata(multipart=True)] = None
+    r"""An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language."""
+
+    enable_logging: Annotated[Optional[bool], FieldMetadata(multipart=True)] = True
+    r"""When enable_logging is set to false, zero retention mode is used. This disables history features like request stitching and is only available to enterprise customers."""
+
+    diarize: Annotated[Optional[bool], FieldMetadata(multipart=True)] = False
+    r"""Whether to annotate which speaker is currently talking in the uploaded file."""
+
+    response_format: Annotated[
+        Optional[CreateTranscriptionResponseFormat], FieldMetadata(multipart=True)
+    ] = None
+    r"""The format of the transcript output, in one of these options: json, text, srt, verbose_json, or vtt."""
+
+    tag_audio_events: Annotated[Optional[bool], FieldMetadata(multipart=True)] = True
+    r"""Whether to tag audio events like (laughter), (footsteps), etc. in the transcription."""
+
+    num_speakers: Annotated[Optional[float], FieldMetadata(multipart=True)] = None
+    r"""The maximum amount of speakers talking in the uploaded file. Helps with predicting who speaks when, the maximum is 32."""
+
+    timestamps_granularity: Annotated[
+        Optional[TimestampsGranularity], FieldMetadata(multipart=True)
+    ] = "word"
+    r"""The granularity of the timestamps in the transcription. Word provides word-level timestamps and character provides character-level timestamps per word."""
+
+    temperature: Annotated[Optional[float], FieldMetadata(multipart=True)] = None
+    r"""The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit."""
+
+    language: Annotated[Optional[str], FieldMetadata(multipart=True)] = None
+    r"""The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency."""
+
+    timestamp_granularities: Annotated[
+        Optional[List[TimestampGranularities]], FieldMetadata(multipart=True)
+    ] = None
+    r"""The timestamp granularities to populate for this transcription. response_format must be set to verbose_json to use timestamp granularities. Either or both of these options are supported: \"word\" or \"segment\". Note: There is no additional latency for segment timestamps, but generating word timestamps incurs additional latency."""
+
+    orq: Annotated[
+        Optional[CreateTranscriptionOrq],
+        FieldMetadata(multipart=MultipartFormMetadata(json=True)),
+    ] = None
+
+    file: Annotated[
+        Optional[CreateTranscriptionFile],
+        FieldMetadata(multipart=MultipartFormMetadata(file=True)),
+    ] = None
+    r"""The audio file object (not file name) to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm."""
+
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = set(
+            [
+                "prompt",
+                "enable_logging",
+                "diarize",
+                "response_format",
+                "tag_audio_events",
+                "num_speakers",
+                "timestamps_granularity",
+                "temperature",
+                "language",
+                "timestamp_granularities",
+                "orq",
+                "file",
+            ]
+        )
+        serialized = handler(self)
+        m = {}
+
+        for n, f in type(self).model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+
+            if val != UNSET_SENTINEL:
+                if val is not None or k not in optional_fields:
+                    m[k] = val
+
+        return m
+
+
+class CreateTranscriptionErrorTypedDict(TypedDict):
+    message: str
+    type: str
+    param: Nullable[str]
+    code: str
+
+
+class CreateTranscriptionError(BaseModel):
+    message: str
+
+    type: str
+
+    param: Nullable[str]
+
+    code: str
+
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        serialized = handler(self)
+        m = {}
+
+        for n, f in type(self).model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+
+            if val != UNSET_SENTINEL:
+                m[k] = val
+
+        return m
+
+
+class CreateTranscriptionRouterAudioTranscriptionsResponseBodyData(BaseModel):
+    error: CreateTranscriptionError
+
+
+@dataclass(unsafe_hash=True)
+class CreateTranscriptionRouterAudioTranscriptionsResponseBody(OrqError):
+    r"""Returns validation error"""
+
+    data: CreateTranscriptionRouterAudioTranscriptionsResponseBodyData = field(
+        hash=False
+    )
+
+    def __init__(
+        self,
+        data: CreateTranscriptionRouterAudioTranscriptionsResponseBodyData,
+        raw_response: httpx.Response,
+        body: Optional[str] = None,
+    ):
+        fallback = body or raw_response.text
+        message = str(data.error.message) or fallback
+        super().__init__(message, raw_response, body)
+        object.__setattr__(self, "data", data)
+
+
+class WordsTypedDict(TypedDict):
+    word: NotRequired[str]
+    start: NotRequired[float]
+    end: NotRequired[float]
+
+
+class Words(BaseModel):
+    word: Optional[str] = None
+
+    start: Optional[float] = None
+
+    end: Optional[float] = None
+
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = set(["word", "start", "end"])
+        serialized = handler(self)
+        m = {}
+
+        for n, f in type(self).model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+
+            if val != UNSET_SENTINEL:
+                if val is not None or k not in optional_fields:
+                    m[k] = val
+
+        return m
+
+
+class SegmentsTypedDict(TypedDict):
+    id: float
+    seek: float
+    start: float
+    end: float
+    text: str
+    tokens: List[float]
+    temperature: float
+    avg_logprob: float
+    compression_ratio: float
+    no_speech_prob: float
+
+
+class Segments(BaseModel):
+    id: float
+
+    seek: float
+
+    start: float
+
+    end: float
+
+    text: str
+
+    tokens: List[float]
+
+    temperature: float
+
+    avg_logprob: float
+
+    compression_ratio: float
+
+    no_speech_prob: float
+
+
+class CreateTranscriptionResponseBody2TypedDict(TypedDict):
+    text: str
+    task: NotRequired[str]
+    language: NotRequired[str]
+    duration: NotRequired[float]
+    words: NotRequired[List[WordsTypedDict]]
+    segments: NotRequired[List[SegmentsTypedDict]]
+
+
+class CreateTranscriptionResponseBody2(BaseModel):
+    text: str
+
+    task: Optional[str] = None
+
+    language: Optional[str] = None
+
+    duration: Optional[float] = None
+
+    words: Optional[List[Words]] = None
+
+    segments: Optional[List[Segments]] = None
+
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = set(["task", "language", "duration", "words", "segments"])
+        serialized = handler(self)
+        m = {}
+
+        for n, f in type(self).model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+
+            if val != UNSET_SENTINEL:
+                if val is not None or k not in optional_fields:
+                    m[k] = val
+
+        return m
+
+
+class CreateTranscriptionResponseBody1TypedDict(TypedDict):
+    text: str
+
+
+class CreateTranscriptionResponseBody1(BaseModel):
+    text: str
+
+
+CreateTranscriptionResponseBodyTypedDict = TypeAliasType(
+    "CreateTranscriptionResponseBodyTypedDict",
+    Union[
+        CreateTranscriptionResponseBody1TypedDict,
+        CreateTranscriptionResponseBody2TypedDict,
+        str,
+    ],
+)
+r"""Returns the transcription or verbose transcription"""
+
+
+CreateTranscriptionResponseBody = TypeAliasType(
+    "CreateTranscriptionResponseBody",
+    Union[CreateTranscriptionResponseBody1, CreateTranscriptionResponseBody2, str],
+)
+r"""Returns the transcription or verbose transcription"""