Class swarmauri_standard.distances.LevenshteinDistance.LevenshteinDistance

swarmauri_standard.distances.LevenshteinDistance.LevenshteinDistance

Bases: DistanceBase

Implements the IDistance interface to calculate the Levenshtein distance between two vectors. The Levenshtein distance between two strings is given by the minimum number of operations needed to transform one string into the other, where an operation is an insertion, deletion, or substitution of a single character.

type class-attribute instance-attribute

type = 'LevenshteinDistance'

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

name class-attribute instance-attribute

name = None

resource class-attribute instance-attribute

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

version class-attribute instance-attribute

version = '0.1.0'

distance

distance(vector_a, vector_b)

Compute the Levenshtein distance between two vectors.

Note: Since Levenshtein distance is typically calculated between strings, it is assumed that the vectors represent strings where each element of the vector corresponds to the ASCII value of a character in the string.

PARAMETER	DESCRIPTION
vector_a	The first vector in the comparison. TYPE: List[float]
vector_b	The second vector in the comparison. TYPE: List[float]

RETURNS	DESCRIPTION
float	The computed Levenshtein distance between vector_a and vector_b. TYPE: float

Source code in swarmauri_standard/distances/LevenshteinDistance.py

def distance(self, vector_a: Vector, vector_b: Vector) -> float:
    """
    Compute the Levenshtein distance between two vectors.

    Note: Since Levenshtein distance is typically calculated between strings,
    it is assumed that the vectors represent strings where each element of the
    vector corresponds to the ASCII value of a character in the string.

    Args:
        vector_a (List[float]): The first vector in the comparison.
        vector_b (List[float]): The second vector in the comparison.

    Returns:
       float: The computed Levenshtein distance between vector_a and vector_b.
    """
    string_a = "".join([chr(int(round(value))) for value in vector_a.value])
    string_b = "".join([chr(int(round(value))) for value in vector_b.value])

    return self.levenshtein(string_a, string_b)

levenshtein

levenshtein(seq1, seq2)

Calculate the Levenshtein distance between two strings.

PARAMETER	DESCRIPTION
seq1	The first string. TYPE: str
seq2	The second string. TYPE: str

RETURNS	DESCRIPTION
float	The Levenshtein distance between seq1 and seq2. TYPE: float

Source code in swarmauri_standard/distances/LevenshteinDistance.py

def levenshtein(self, seq1: str, seq2: str) -> float:
    """
    Calculate the Levenshtein distance between two strings.

    Args:
        seq1 (str): The first string.
        seq2 (str): The second string.

    Returns:
        float: The Levenshtein distance between seq1 and seq2.
    """
    size_x = len(seq1) + 1
    size_y = len(seq2) + 1
    matrix = np.zeros((size_x, size_y))

    for x in range(size_x):
        matrix[x, 0] = x
    for y in range(size_y):
        matrix[0, y] = y

    for x in range(1, size_x):
        for y in range(1, size_y):
            if seq1[x - 1] == seq2[y - 1]:
                matrix[x, y] = min(
                    matrix[x - 1, y] + 1, matrix[x - 1, y - 1], matrix[x, y - 1] + 1
                )
            else:
                matrix[x, y] = min(
                    matrix[x - 1, y] + 1,
                    matrix[x - 1, y - 1] + 1,
                    matrix[x, y - 1] + 1,
                )

    return matrix[size_x - 1, size_y - 1]

similarity

similarity(vector_a, vector_b)

Source code in swarmauri_standard/distances/LevenshteinDistance.py

def similarity(self, vector_a: Vector, vector_b: Vector) -> float:
    string_a = "".join([chr(int(round(value))) for value in vector_a.value])
    string_b = "".join([chr(int(round(value))) for value in vector_b.value])
    return 1 - self.levenshtein(string_a, string_b) / max(
        len(vector_a), len(vector_b)
    )

distances

distances(vector_a, vectors_b)

Source code in swarmauri_standard/distances/LevenshteinDistance.py

def distances(self, vector_a: Vector, vectors_b: List[Vector]) -> List[float]:
    distances = [self.distance(vector_a, vector_b) for vector_b in vectors_b]
    return distances

similarities

similarities(vector_a, vectors_b)

Source code in swarmauri_standard/distances/LevenshteinDistance.py

def similarities(self, vector_a: Vector, vectors_b: List[Vector]) -> List[float]:
    similarities = [self.similarity(vector_a, vector_b) for vector_b in vectors_b]
    return similarities

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