Class swarmauri_standard.stt.OpenaiSTT.OpenaiSTT

swarmauri_standard.stt.OpenaiSTT.OpenaiSTT

OpenaiSTT(**data)

Bases: STTBase

OpenaiSTT is a class that provides transcription and translation capabilities using OpenAI's audio models. It supports both synchronous and asynchronous methods for processing audio files.

ATTRIBUTE	DESCRIPTION
api_key	API key for authentication. TYPE: str
allowed_models	List of supported model names. TYPE: List[str]
name	The default model name to be used for predictions. TYPE: str
type	The type identifier for the class. TYPE: Literal['OpenaiSTT']

Provider Resources: https://platform.openai.com/docs/api-reference/audio/createTranscription

Initialize the OpenaiSTT class with the provided data.

PARAMETER	DESCRIPTION
**data	Arbitrary keyword arguments containing initialization data. TYPE: Dict[str, Any] DEFAULT: {}

Source code in swarmauri_standard/stt/OpenaiSTT.py

def __init__(self, **data: Dict[str, Any]):
    """
    Initialize the OpenaiSTT class with the provided data.

    Args:
        **data (Dict[str, Any]): Arbitrary keyword arguments containing initialization data.
    """
    super().__init__(**data)
    self._client = httpx.Client(
        headers={"Authorization": f"Bearer {self.api_key.get_secret_value()}"},
        base_url=self._BASE_URL,
    )
    self._async_client = httpx.AsyncClient(
        headers={"Authorization": f"Bearer {self.api_key.get_secret_value()}"},
        base_url=self._BASE_URL,
    )

api_key instance-attribute

api_key

allowed_models class-attribute instance-attribute

allowed_models = [
    "whisper-1",
    "gpt-4o-transcribe",
    "gpt-4o-mini-transcribe",
]

name class-attribute instance-attribute

name = 'whisper-1'

type class-attribute instance-attribute

type = 'OpenaiSTT'

model_config class-attribute instance-attribute

model_config = ConfigDict(
    extra="forbid", arbitrary_types_allowed=True
)

id class-attribute instance-attribute

id = Field(default_factory=generate_id)

members class-attribute instance-attribute

members = None

owners class-attribute instance-attribute

owners = None

host class-attribute instance-attribute

host = None

default_logger class-attribute

default_logger = None

logger class-attribute instance-attribute

logger = None

resource class-attribute instance-attribute

resource = Field(default=STT.value, frozen=True)

version class-attribute instance-attribute

version = '0.1.0'

predict

predict(audio_path, task='transcription')

Perform synchronous transcription or translation on the provided audio file.

PARAMETER	DESCRIPTION
audio_path	Path to the audio file. TYPE: str
task	Task type. Defaults to "transcription". TYPE: Literal['transcription', 'translation'] DEFAULT: 'transcription'

RETURNS	DESCRIPTION
str	The resulting transcription or translation text. TYPE: str

RAISES	DESCRIPTION
ValueError	If the specified task is not supported.
HTTPStatusError	If the API request fails.

Source code in swarmauri_standard/stt/OpenaiSTT.py

@retry_on_status_codes((429, 529), max_retries=1)
def predict(
    self,
    audio_path: str,
    task: Literal["transcription", "translation"] = "transcription",
) -> str:
    """
    Perform synchronous transcription or translation on the provided audio file.

    Args:
        audio_path (str): Path to the audio file.
        task (Literal["transcription", "translation"]): Task type. Defaults to "transcription".

    Returns:
        str: The resulting transcription or translation text.

    Raises:
        ValueError: If the specified task is not supported.
        httpx.HTTPStatusError: If the API request fails.
    """
    kwargs = {
        "model": self.name,
    }

    with open(audio_path, "rb") as audio_file:
        actions = {
            "transcription": self._client.post(
                "transcriptions", files={"file": audio_file}, data=kwargs
            ),
            "translation": self._client.post(
                "translations", files={"file": audio_file}, data=kwargs
            ),
        }

        if task not in actions:
            raise ValueError(
                f"Task {task} not supported. Choose from {list(actions)}"
            )

    response = actions[task]
    response.raise_for_status()

    response_data = response.json()

    return response_data["text"]

apredict async

apredict(audio_path, task='transcription')

Perform asynchronous transcription or translation on the provided audio file.

PARAMETER	DESCRIPTION
audio_path	Path to the audio file. TYPE: str
task	Task type. Defaults to "transcription". TYPE: Literal['transcription', 'translation'] DEFAULT: 'transcription'

RETURNS	DESCRIPTION
str	The resulting transcription or translation text. TYPE: str

RAISES	DESCRIPTION
ValueError	If the specified task is not supported.
HTTPStatusError	If the API request fails.

Source code in swarmauri_standard/stt/OpenaiSTT.py

@retry_on_status_codes((429, 529), max_retries=1)
async def apredict(
    self,
    audio_path: str,
    task: Literal["transcription", "translation"] = "transcription",
) -> str:
    """
    Perform asynchronous transcription or translation on the provided audio file.

    Args:
        audio_path (str): Path to the audio file.
        task (Literal["transcription", "translation"]): Task type. Defaults to "transcription".

    Returns:
        str: The resulting transcription or translation text.

    Raises:
        ValueError: If the specified task is not supported.
        httpx.HTTPStatusError: If the API request fails.
    """
    kwargs = {
        "model": self.name,
    }

    async with aiofiles.open(audio_path, "rb") as audio_file:
        file_content = await audio_file.read()
        file_name = audio_path.split("/")[-1]
        actions = {
            "transcription": await self._async_client.post(
                "transcriptions",
                files={"file": (file_name, file_content, "audio/wav")},
                data=kwargs,
            ),
            "translation": await self._async_client.post(
                "translations",
                files={"file": (file_name, file_content, "audio/wav")},
                data=kwargs,
            ),
        }
        if task not in actions:
            raise ValueError(
                f"Task {task} not supported. Choose from {list(actions)}"
            )

        response = actions[task]
        response.raise_for_status()

        response_data = response.json()
        return response_data["text"]

batch

batch(path_task_dict)

Synchronously process multiple audio files for transcription or translation.

PARAMETER	DESCRIPTION
path_task_dict	A dictionary where the keys are paths to audio files and the values are the tasks. TYPE: Dict[str, Literal['transcription', 'translation']]

RETURNS	DESCRIPTION
List	A list of resulting texts from each audio file. TYPE: List

Source code in swarmauri_standard/stt/OpenaiSTT.py

def batch(
    self,
    path_task_dict: Dict[str, Literal["transcription", "translation"]],
) -> List:
    """
    Synchronously process multiple audio files for transcription or translation.

    Args:
        path_task_dict (Dict[str, Literal["transcription", "translation"]]): A dictionary where
            the keys are paths to audio files and the values are the tasks.

    Returns:
        List: A list of resulting texts from each audio file.
    """
    return [
        self.predict(audio_path=path, task=task)
        for path, task in path_task_dict.items()
    ]

abatch async

abatch(path_task_dict, max_concurrent=5)

Asynchronously process multiple audio files for transcription or translation with controlled concurrency.

PARAMETER	DESCRIPTION
path_task_dict	A dictionary where the keys are paths to audio files and the values are the tasks. TYPE: Dict[str, Literal['transcription', 'translation']]
max_concurrent	Maximum number of concurrent tasks. Defaults to 5. TYPE: int DEFAULT: 5

RETURNS	DESCRIPTION
List	A list of resulting texts from each audio file. TYPE: List

Source code in swarmauri_standard/stt/OpenaiSTT.py

async def abatch(
    self,
    path_task_dict: Dict[str, Literal["transcription", "translation"]],
    max_concurrent=5,
) -> List:
    """
    Asynchronously process multiple audio files for transcription or translation
    with controlled concurrency.

    Args:
        path_task_dict (Dict[str, Literal["transcription", "translation"]]): A dictionary where
            the keys are paths to audio files and the values are the tasks.
        max_concurrent (int): Maximum number of concurrent tasks. Defaults to 5.

    Returns:
        List: A list of resulting texts from each audio file.
    """
    semaphore = asyncio.Semaphore(max_concurrent)

    async def process_conversation(path, task) -> str:
        async with semaphore:
            return await self.apredict(audio_path=path, task=task)

    tasks = [
        process_conversation(path, task) for path, task in path_task_dict.items()
    ]
    return await asyncio.gather(*tasks)

get_allowed_models

get_allowed_models()

Queries the LLMProvider API endpoint to retrieve the list of allowed models.

RETURNS	DESCRIPTION
List[str]	List[str]: List of allowed model names.

Source code in swarmauri_standard/stt/OpenaiSTT.py

def get_allowed_models(self) -> List[str]:
    """
    Queries the LLMProvider API endpoint to retrieve the list of allowed models.

    Returns:
        List[str]: List of allowed model names.
    """
    models_data = ["whisper-1"]
    return models_data

stream

stream(audio_path, task='transcription')

Source code in swarmauri_standard/stt/OpenaiSTT.py

def stream(
    self,
    audio_path: str,
    task: Literal["transcription", "translation"] = "transcription",
) -> str:
    raise NotImplementedError("Stream method is not implemented for OpenaiSTT")

astream async

astream(audio_path, task='transcription')

Source code in swarmauri_standard/stt/OpenaiSTT.py

async def astream(
    self,
    audio_path: str,
    task: Literal["transcription", "translation"] = "transcription",
) -> str:
    raise NotImplementedError(
        "Asynchrous Stream method is not implemented for OpenaiSTT"
    )

register_model classmethod

register_model()

Decorator to register a base model in the unified registry.

RETURNS	DESCRIPTION
Callable	A decorator function that registers the model class. TYPE: Callable[[Type[BaseModel]], Type[BaseModel]]

Source code in swarmauri_base/DynamicBase.py

@classmethod
def register_model(cls) -> Callable[[Type[BaseModel]], Type[BaseModel]]:
    """
    Decorator to register a base model in the unified registry.

    Returns:
        Callable: A decorator function that registers the model class.
    """

    def decorator(model_cls: Type[BaseModel]):
        """Register ``model_cls`` as a base model."""
        model_name = model_cls.__name__
        if model_name in cls._registry:
            glogger.warning(
                "Model '%s' is already registered; skipping duplicate.", model_name
            )
            return model_cls

        cls._registry[model_name] = {"model_cls": model_cls, "subtypes": {}}
        glogger.debug("Registered base model '%s'.", model_name)
        DynamicBase._recreate_models()
        return model_cls

    return decorator

register_type classmethod

register_type(resource_type=None, type_name=None)

Decorator to register a subtype under one or more base models in the unified registry.

PARAMETER	DESCRIPTION
resource_type	The base model(s) under which to register the subtype. If None, all direct base classes (except DynamicBase) are used. TYPE: Optional[Union[Type[T], List[Type[T]]]] DEFAULT: None
type_name	An optional custom type name for the subtype. TYPE: Optional[str] DEFAULT: None

RETURNS	DESCRIPTION
Callable	A decorator function that registers the subtype. TYPE: Callable[[Type[DynamicBase]], Type[DynamicBase]]

Source code in swarmauri_base/DynamicBase.py

@classmethod
def register_type(
    cls,
    resource_type: Optional[Union[Type[T], List[Type[T]]]] = None,
    type_name: Optional[str] = None,
) -> Callable[[Type["DynamicBase"]], Type["DynamicBase"]]:
    """
    Decorator to register a subtype under one or more base models in the unified registry.

    Parameters:
        resource_type (Optional[Union[Type[T], List[Type[T]]]]):
            The base model(s) under which to register the subtype. If None, all direct base classes (except DynamicBase)
            are used.
        type_name (Optional[str]): An optional custom type name for the subtype.

    Returns:
        Callable: A decorator function that registers the subtype.
    """

    def decorator(subclass: Type["DynamicBase"]):
        """Register ``subclass`` as a subtype."""
        if resource_type is None:
            resource_types = [
                base for base in subclass.__bases__ if base is not cls
            ]
        elif not isinstance(resource_type, list):
            resource_types = [resource_type]
        else:
            resource_types = resource_type

        for rt in resource_types:
            if not issubclass(subclass, rt):
                raise TypeError(
                    f"'{subclass.__name__}' must be a subclass of '{rt.__name__}'."
                )
            final_type_name = type_name or getattr(
                subclass, "_type", subclass.__name__
            )
            base_model_name = rt.__name__

            if base_model_name not in cls._registry:
                cls._registry[base_model_name] = {"model_cls": rt, "subtypes": {}}
                glogger.debug(
                    "Created new registry entry for base model '%s'.",
                    base_model_name,
                )

            subtypes_dict = cls._registry[base_model_name]["subtypes"]
            if final_type_name in subtypes_dict:
                glogger.warning(
                    "Type '%s' already exists under '%s'; skipping duplicate.",
                    final_type_name,
                    base_model_name,
                )
                continue

            subtypes_dict[final_type_name] = subclass
            glogger.debug(
                "Registered '%s' as '%s' under '%s'.",
                subclass.__name__,
                final_type_name,
                base_model_name,
            )

        DynamicBase._recreate_models()
        return subclass

    return decorator

model_validate_toml classmethod

model_validate_toml(toml_data)

Validate a model from a TOML string.

Source code in swarmauri_base/TomlMixin.py

@classmethod
def model_validate_toml(cls, toml_data: str):
    """Validate a model from a TOML string."""
    try:
        # Parse TOML into a Python dictionary
        toml_content = tomllib.loads(toml_data)

        # Convert the dictionary to JSON and validate using Pydantic
        return cls.model_validate_json(json.dumps(toml_content))
    except tomllib.TOMLDecodeError as e:
        raise ValueError(f"Invalid TOML data: {e}")
    except ValidationError as e:
        raise ValueError(f"Validation failed: {e}")

model_dump_toml

model_dump_toml(
    fields_to_exclude=None, api_key_placeholder=None
)

Return a TOML representation of the model.

Source code in swarmauri_base/TomlMixin.py

def model_dump_toml(self, fields_to_exclude=None, api_key_placeholder=None):
    """Return a TOML representation of the model."""
    if fields_to_exclude is None:
        fields_to_exclude = []

    # Load the JSON string into a Python dictionary
    json_data = json.loads(self.model_dump_json())

    # Function to recursively remove specific keys and handle api_key placeholders
    def process_fields(data, fields_to_exclude):
        """Recursively filter fields and apply placeholders."""
        if isinstance(data, dict):
            return {
                key: (
                    api_key_placeholder
                    if key == "api_key" and api_key_placeholder is not None
                    else process_fields(value, fields_to_exclude)
                )
                for key, value in data.items()
                if key not in fields_to_exclude
            }
        elif isinstance(data, list):
            return [process_fields(item, fields_to_exclude) for item in data]
        else:
            return data

    # Filter the JSON data
    filtered_data = process_fields(json_data, fields_to_exclude)

    # Convert the filtered data into TOML
    return toml.dumps(filtered_data)

model_validate_yaml classmethod

model_validate_yaml(yaml_data)

Validate a model from a YAML string.

Source code in swarmauri_base/YamlMixin.py

@classmethod
def model_validate_yaml(cls, yaml_data: str):
    """Validate a model from a YAML string."""
    try:
        # Parse YAML into a Python dictionary
        yaml_content = yaml.safe_load(yaml_data)

        # Convert the dictionary to JSON and validate using Pydantic
        return cls.model_validate_json(json.dumps(yaml_content))
    except yaml.YAMLError as e:
        raise ValueError(f"Invalid YAML data: {e}")
    except ValidationError as e:
        raise ValueError(f"Validation failed: {e}")

model_dump_yaml

model_dump_yaml(
    fields_to_exclude=None, api_key_placeholder=None
)

Return a YAML representation of the model.

Source code in swarmauri_base/YamlMixin.py

def model_dump_yaml(self, fields_to_exclude=None, api_key_placeholder=None):
    """Return a YAML representation of the model."""
    if fields_to_exclude is None:
        fields_to_exclude = []

    # Load the JSON string into a Python dictionary
    json_data = json.loads(self.model_dump_json())

    # Function to recursively remove specific keys and handle api_key placeholders
    def process_fields(data, fields_to_exclude):
        """Recursively filter fields and apply placeholders."""
        if isinstance(data, dict):
            return {
                key: (
                    api_key_placeholder
                    if key == "api_key" and api_key_placeholder is not None
                    else process_fields(value, fields_to_exclude)
                )
                for key, value in data.items()
                if key not in fields_to_exclude
            }
        elif isinstance(data, list):
            return [process_fields(item, fields_to_exclude) for item in data]
        else:
            return data

    # Filter the JSON data
    filtered_data = process_fields(json_data, fields_to_exclude)

    # Convert the filtered data into YAML using safe mode
    return yaml.safe_dump(filtered_data, default_flow_style=False)

model_post_init

model_post_init(logger=None)

Assign a logger instance after model initialization.

Source code in swarmauri_base/LoggerMixin.py

def model_post_init(self, logger: Optional[FullUnion[LoggerBase]] = None) -> None:
    """Assign a logger instance after model initialization."""

    # Directly assign the provided FullUnion[LoggerBase] or fallback to the
    # class-level default.
    self.logger = self.logger or logger or self.default_logger

add_allowed_model

add_allowed_model(model)

Add a new model to the list of allowed models.

RAISES	DESCRIPTION
ValueError	If the model is already in the allowed models list.

Source code in swarmauri_base/stt/STTBase.py

def add_allowed_model(self, model: str) -> None:
    """
    Add a new model to the list of allowed models.

    Raises:
        ValueError: If the model is already in the allowed models list.
    """
    if model in self.allowed_models:
        raise ValueError(f"Model '{model}' is already allowed.")
    self.allowed_models.append(model)

remove_allowed_model

remove_allowed_model(model)

Remove a model from the list of allowed models.

RAISES	DESCRIPTION
ValueError	If the model is not in the allowed models list.

Source code in swarmauri_base/stt/STTBase.py

def remove_allowed_model(self, model: str) -> None:
    """
    Remove a model from the list of allowed models.

    Raises:
        ValueError: If the model is not in the allowed models list.
    """
    if model not in self.allowed_models:
        raise ValueError(f"Model '{model}' is not in the allowed models list.")
    self.allowed_models.remove(model)