Class swarmauri_standard.llms.FalAIVisionModel.FalAIVisionModel

swarmauri_standard.llms.FalAIVisionModel.FalAIVisionModel

FalAIVisionModel(**data)

Bases: LLMBase

A model for processing images and answering questions using FalAI's vision models. This model allows synchronous and asynchronous requests for image processing and question answering based on an input image and text prompt.

ATTRIBUTE	DESCRIPTION
allowed_models	List of allowed vision models. TYPE: List[str]
api_key	The API key for authentication. TYPE: str
name	The model name to use for image processing. TYPE: str
type	The type identifier for the model. TYPE: Literal
max_retries	Maximum number of retries for status polling. TYPE: int
retry_delay	Delay in seconds between retries. TYPE: float

Link to API KEY: https://fal.ai/dashboard/keys Link to Allowed Models: https://fal.ai/models?categories=vision

Initialize the FalOCR with API key, HTTP clients, and model name validation.

RAISES	DESCRIPTION
ValueError	If the provided name is not in allowed_models.

Source code in swarmauri_standard/llms/FalAIVisionModel.py

def __init__(self, **data):
    """
    Initialize the FalOCR with API key, HTTP clients, and model name validation.

    Raises:
        ValueError: If the provided name is not in allowed_models.
    """
    super().__init__(**data)
    self._headers = {
        "Content-Type": "application/json",
        "Authorization": f"Key {self.api_key.get_secret_value()}",
    }
    self._client = httpx.Client(headers=self._headers, timeout=30)

allowed_models class-attribute instance-attribute

allowed_models = [
    "fal-ai/got-ocr/v2",
    "fal-ai/any-llm/vision",
    "fal-ai/llavav15-13b",
    "fal-ai/llava-next",
    "fal-ai/imageutils/nsfw",
    "fal-ai/moondream/batched",
    "fal-ai/florence-2-large/caption",
    "fal-ai/florence-2-large/detailed-caption",
    "fal-ai/florence-2-large/more-detailed-caption",
    "fal-ai/florence-2-large/region-to-category",
    "fal-ai/florence-2-large/ocr",
    "fal-ai/sa2va/8b/image",
    "fal-ai/sa2va/8b/video",
    "fal-ai/sa2va/4b/video",
    "fal-ai/sa2va/4b/image",
    "fal-ai/mini-cpm",
    "fal-ai/moondream-next",
    "fal-ai/moondream-next/batch",
]

api_key class-attribute instance-attribute

api_key = Field(default_factory=lambda: get('FAL_KEY'))

name class-attribute instance-attribute

name = Field(default='fal-ai/got-ocr/v2')

timeout class-attribute instance-attribute

timeout = 600.0

type class-attribute instance-attribute

type = 'FalAIVisionModel'

max_retries class-attribute instance-attribute

max_retries = Field(default=60)

retry_delay class-attribute instance-attribute

retry_delay = Field(default=1.0)

model_config class-attribute instance-attribute

model_config = ConfigDict(
    extra="allow", 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=LLM.value, frozen=True)

version class-attribute instance-attribute

version = '0.1.0'

include_usage class-attribute instance-attribute

include_usage = True

BASE_URL class-attribute instance-attribute

BASE_URL = None

predict

predict(image_url, prompt, **kwargs)

Process an image and answer a question based on the prompt.

PARAMETER	DESCRIPTION
image_url	The URL of the image to process. TYPE: str
prompt	The question or instruction to apply to the image. TYPE: str
**kwargs	Additional parameters for the API request. DEFAULT: {}

RETURNS	DESCRIPTION
str	The answer or result of the image processing. TYPE: str

Source code in swarmauri_standard/llms/FalAIVisionModel.py

def predict(self, image_url: str, prompt: str, **kwargs) -> str:
    """
    Process an image and answer a question based on the prompt.

    Args:
        image_url (str): The URL of the image to process.
        prompt (str): The question or instruction to apply to the image.
        **kwargs: Additional parameters for the API request.

    Returns:
        str: The answer or result of the image processing.
    """
    response_data = self._send_request(image_url, prompt, **kwargs)
    return response_data.get("output", "")

apredict async

apredict(image_url, prompt, **kwargs)

Asynchronously process an image and answer a question based on the prompt.

PARAMETER	DESCRIPTION
image_url	The URL of the image to process. TYPE: str
prompt	The question or instruction to apply to the image. TYPE: str
**kwargs	Additional parameters for the API request. DEFAULT: {}

RETURNS	DESCRIPTION
str	The answer or result of the image processing. TYPE: str

Source code in swarmauri_standard/llms/FalAIVisionModel.py

async def apredict(self, image_url: str, prompt: str, **kwargs) -> str:
    """
    Asynchronously process an image and answer a question based on the prompt.

    Args:
        image_url (str): The URL of the image to process.
        prompt (str): The question or instruction to apply to the image.
        **kwargs: Additional parameters for the API request.

    Returns:
        str: The answer or result of the image processing.
    """
    response_data = await self._async_send_request(image_url, prompt, **kwargs)
    return response_data.get("output", "")

batch

batch(image_urls, prompts, **kwargs)

Process a batch of images and answer questions for each image synchronously.

PARAMETER	DESCRIPTION
image_urls	A list of image URLs to process. TYPE: List[str]
prompts	A list of prompts corresponding to each image. TYPE: List[str]
**kwargs	Additional parameters for the API requests. DEFAULT: {}

RETURNS	DESCRIPTION
List[str]	List[str]: A list of answers or results for each image.

Source code in swarmauri_standard/llms/FalAIVisionModel.py

def batch(self, image_urls: List[str], prompts: List[str], **kwargs) -> List[str]:
    """
    Process a batch of images and answer questions for each image synchronously.

    Args:
        image_urls (List[str]): A list of image URLs to process.
        prompts (List[str]): A list of prompts corresponding to each image.
        **kwargs: Additional parameters for the API requests.

    Returns:
        List[str]: A list of answers or results for each image.
    """
    return [
        self.predict_vision(image_url, prompt, **kwargs)
        for image_url, prompt in zip(image_urls, prompts)
    ]

abatch async

abatch(image_urls, prompts, **kwargs)

Asynchronously process a batch of images and answer questions for each image.

PARAMETER	DESCRIPTION
image_urls	A list of image URLs to process. TYPE: List[str]
prompts	A list of prompts corresponding to each image. TYPE: List[str]
**kwargs	Additional parameters for the API requests. DEFAULT: {}

RETURNS	DESCRIPTION
List[str]	List[str]: A list of answers or results for each image.

RAISES	DESCRIPTION
TimeoutError	If one or more requests do not complete within the timeout period.

Source code in swarmauri_standard/llms/FalAIVisionModel.py

async def abatch(
    self, image_urls: List[str], prompts: List[str], **kwargs
) -> List[str]:
    """
    Asynchronously process a batch of images and answer questions for each image.

    Args:
        image_urls (List[str]): A list of image URLs to process.
        prompts (List[str]): A list of prompts corresponding to each image.
        **kwargs: Additional parameters for the API requests.

    Returns:
        List[str]: A list of answers or results for each image.

    Raises:
        TimeoutError: If one or more requests do not complete within the timeout period.
    """
    tasks = [
        self.apredict_vision(image_url, prompt, **kwargs)
        for image_url, prompt in zip(image_urls, prompts)
    ]
    return await asyncio.gather(*tasks)

stream

stream(image_url, prompt, **kwargs)

summary

PARAMETER	DESCRIPTION
image_url	description TYPE: str
prompt	description TYPE: str

RETURNS	DESCRIPTION
Any	description TYPE: Any

Source code in swarmauri_standard/llms/FalAIVisionModel.py

def stream(self, image_url: str, prompt: str, **kwargs) -> Any:
    """_summary_

    Args:
        image_url (str): _description_
        prompt (str): _description_

    Returns:
        Any: _description_
    """
    raise NotImplementedError("Stream is not supported for FalAIVisionModel")

astream async

astream(image_url, prompt, **kwargs)

summary

PARAMETER	DESCRIPTION
image_url	description TYPE: str
prompt	description TYPE: str

RETURNS	DESCRIPTION
Any	description TYPE: Any

Source code in swarmauri_standard/llms/FalAIVisionModel.py

async def astream(self, image_url: str, prompt: str, **kwargs) -> Any:
    """_summary_

    Args:
        image_url (str): _description_
        prompt (str): _description_

    Returns:
        Any: _description_
    """
    raise NotImplementedError(
        "Asynchronous Stream is not supported for FalAIVisionModel"
    )

get_allowed_models

get_allowed_models()

Query the LLMProvider API endpoint to get the list of allowed models.

RETURNS	DESCRIPTION
List[str]	List[str]: The list of allowed models from the API.

Source code in swarmauri_standard/llms/FalAIVisionModel.py

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

    Returns:
        List[str]: The list of allowed models from the API.
    """
    url = "https://fal.ai/models?categories=vision"
    response = self._client.get(url)
    response.raise_for_status()
    models_data = response.json()
    return models_data.get("models", [])

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/llms/LLMBase.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/llms/LLMBase.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)