Class swarmauri_standard.similarities.CosineSimilarity.CosineSimilarity

swarmauri_standard.similarities.CosineSimilarity.CosineSimilarity

Bases: SimilarityBase

Cosine similarity implementation that measures the cosine of the angle between two vectors.

Cosine similarity is a measure of similarity between two non-zero vectors defined by the cosine of the angle between them. It is calculated as the dot product of the vectors divided by the product of their magnitudes. The result ranges from -1 to 1, where 1 means the vectors are identical in direction, 0 means they are orthogonal, and -1 means they are opposite.

Attributes

type : Literal["CosineSimilarity"] Type identifier for this similarity measure

type class-attribute instance-attribute

type = 'CosineSimilarity'

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 = SIMILARITY.value

version class-attribute instance-attribute

version = '0.1.0'

similarity

similarity(x, y)

Calculate the cosine similarity between two vectors.

Parameters

x : ComparableType First vector y : ComparableType Second vector

Returns

float Cosine similarity between x and y, ranging from -1 to 1

Raises

ValueError If either vector has zero magnitude or incompatible dimensions TypeError If the input types are not numeric arrays or lists

Source code in swarmauri_standard/similarities/CosineSimilarity.py

def similarity(self, x: ComparableType, y: ComparableType) -> float:
    """
    Calculate the cosine similarity between two vectors.

    Parameters
    ----------
    x : ComparableType
        First vector
    y : ComparableType
        Second vector

    Returns
    -------
    float
        Cosine similarity between x and y, ranging from -1 to 1

    Raises
    ------
    ValueError
        If either vector has zero magnitude or incompatible dimensions
    TypeError
        If the input types are not numeric arrays or lists
    """
    try:
        # Convert inputs to numpy arrays if they aren't already
        x_array = np.array(x, dtype=float)
        y_array = np.array(y, dtype=float)

        # Check for compatible dimensions
        if x_array.shape != y_array.shape:
            raise ValueError(
                f"Incompatible dimensions: {x_array.shape} vs {y_array.shape}"
            )

        # Calculate vector norms
        x_norm = np.linalg.norm(x_array)
        y_norm = np.linalg.norm(y_array)

        # Check for zero vectors
        if x_norm < 1e-10 or y_norm < 1e-10:
            raise ValueError("Cosine similarity is undefined for zero vectors")

        # Calculate dot product
        dot_product = np.dot(x_array, y_array)

        # Calculate cosine similarity
        cosine_sim = dot_product / (x_norm * y_norm)

        # Handle potential numerical errors that might push the value outside [-1, 1]
        if cosine_sim > 1.0:
            cosine_sim = 1.0
        elif cosine_sim < -1.0:
            cosine_sim = -1.0

        return float(cosine_sim)

    except Exception as e:
        logger.error(f"Error calculating cosine similarity: {str(e)}")
        raise

similarities

similarities(x, ys)

Calculate cosine similarities between one vector and multiple other vectors.

Parameters

x : ComparableType Reference vector ys : Sequence[ComparableType] Sequence of vectors to compare against the reference

Returns

List[float] List of cosine similarity scores between x and each element in ys

Raises

ValueError If any vector has zero magnitude or incompatible dimensions TypeError If any input types are not numeric arrays or lists

Source code in swarmauri_standard/similarities/CosineSimilarity.py

def similarities(
    self, x: ComparableType, ys: Sequence[ComparableType]
) -> List[float]:
    """
    Calculate cosine similarities between one vector and multiple other vectors.

    Parameters
    ----------
    x : ComparableType
        Reference vector
    ys : Sequence[ComparableType]
        Sequence of vectors to compare against the reference

    Returns
    -------
    List[float]
        List of cosine similarity scores between x and each element in ys

    Raises
    ------
    ValueError
        If any vector has zero magnitude or incompatible dimensions
    TypeError
        If any input types are not numeric arrays or lists
    """
    try:
        # Convert reference vector to numpy array
        x_array = np.array(x, dtype=float)
        x_norm = np.linalg.norm(x_array)

        if x_norm < 1e-10:
            raise ValueError("Cosine similarity is undefined for zero vectors")

        results = []
        for y in ys:
            y_array = np.array(y, dtype=float)

            # Check for compatible dimensions
            if x_array.shape != y_array.shape:
                raise ValueError(
                    f"Incompatible dimensions: {x_array.shape} vs {y_array.shape}"
                )

            y_norm = np.linalg.norm(y_array)

            if y_norm < 1e-10:
                raise ValueError("Cosine similarity is undefined for zero vectors")

            dot_product = np.dot(x_array, y_array)
            cosine_sim = dot_product / (x_norm * y_norm)

            # Handle potential numerical errors
            if cosine_sim > 1.0:
                cosine_sim = 1.0
            elif cosine_sim < -1.0:
                cosine_sim = -1.0

            results.append(float(cosine_sim))

        return results

    except Exception as e:
        logger.error(f"Error calculating multiple cosine similarities: {str(e)}")
        raise

dissimilarity

dissimilarity(x, y)

Calculate the cosine dissimilarity between two vectors.

For cosine similarity, dissimilarity is defined as 1 - similarity for the normalized range [0, 1], which corresponds to the angle-based distance.

Parameters

x : ComparableType First vector y : ComparableType Second vector

Returns

float Cosine dissimilarity between x and y, ranging from 0 to 2

Raises

ValueError If either vector has zero magnitude or incompatible dimensions TypeError If the input types are not numeric arrays or lists

Source code in swarmauri_standard/similarities/CosineSimilarity.py

def dissimilarity(self, x: ComparableType, y: ComparableType) -> float:
    """
    Calculate the cosine dissimilarity between two vectors.

    For cosine similarity, dissimilarity is defined as 1 - similarity for
    the normalized range [0, 1], which corresponds to the angle-based distance.

    Parameters
    ----------
    x : ComparableType
        First vector
    y : ComparableType
        Second vector

    Returns
    -------
    float
        Cosine dissimilarity between x and y, ranging from 0 to 2

    Raises
    ------
    ValueError
        If either vector has zero magnitude or incompatible dimensions
    TypeError
        If the input types are not numeric arrays or lists
    """
    try:
        # Cosine dissimilarity is 1 - cosine similarity for normalized values
        # This maps the range [-1, 1] to [0, 2]
        similarity_value = self.similarity(x, y)
        return 1.0 - similarity_value

    except Exception as e:
        logger.error(f"Error calculating cosine dissimilarity: {str(e)}")
        raise

check_bounded

check_bounded()

Check if the similarity measure is bounded.

Cosine similarity is bounded in the range [-1, 1].

Returns

bool True, as cosine similarity is bounded

Source code in swarmauri_standard/similarities/CosineSimilarity.py

def check_bounded(self) -> bool:
    """
    Check if the similarity measure is bounded.

    Cosine similarity is bounded in the range [-1, 1].

    Returns
    -------
    bool
        True, as cosine similarity is bounded
    """
    return True

check_symmetry

check_symmetry(x, y)

Check if the cosine similarity measure is symmetric: s(x,y) = s(y,x).

Cosine similarity is inherently symmetric due to the commutative property of the dot product.

Parameters

x : ComparableType First vector y : ComparableType Second vector

Returns

bool True, as cosine similarity is symmetric

Raises

ValueError If either vector has zero magnitude or incompatible dimensions TypeError If the input types are not numeric arrays or lists

Source code in swarmauri_standard/similarities/CosineSimilarity.py

def check_symmetry(self, x: ComparableType, y: ComparableType) -> bool:
    """
    Check if the cosine similarity measure is symmetric: s(x,y) = s(y,x).

    Cosine similarity is inherently symmetric due to the commutative property
    of the dot product.

    Parameters
    ----------
    x : ComparableType
        First vector
    y : ComparableType
        Second vector

    Returns
    -------
    bool
        True, as cosine similarity is symmetric

    Raises
    ------
    ValueError
        If either vector has zero magnitude or incompatible dimensions
    TypeError
        If the input types are not numeric arrays or lists
    """
    try:
        # Cosine similarity is symmetric by definition
        # But we'll verify with an explicit check
        similarity_xy = self.similarity(x, y)
        similarity_yx = self.similarity(y, x)
        return abs(similarity_xy - similarity_yx) < 1e-10

    except Exception as e:
        logger.error(f"Error checking symmetry: {str(e)}")
        raise

check_identity_of_discernibles

check_identity_of_discernibles(x, y)

Check if the cosine similarity measure satisfies the identity of discernibles.

For cosine similarity, this property is partially satisfied: parallel vectors with the same direction (even with different magnitudes) will have a similarity of 1.

Parameters

x : ComparableType First vector y : ComparableType Second vector

Returns

bool True if the identity of discernibles property holds, False otherwise

Raises

ValueError If either vector has zero magnitude or incompatible dimensions TypeError If the input types are not numeric arrays or lists

Source code in swarmauri_standard/similarities/CosineSimilarity.py

def check_identity_of_discernibles(
    self, x: ComparableType, y: ComparableType
) -> bool:
    """
    Check if the cosine similarity measure satisfies the identity of discernibles.

    For cosine similarity, this property is partially satisfied: parallel vectors
    with the same direction (even with different magnitudes) will have a similarity of 1.

    Parameters
    ----------
    x : ComparableType
        First vector
    y : ComparableType
        Second vector

    Returns
    -------
    bool
        True if the identity of discernibles property holds, False otherwise

    Raises
    ------
    ValueError
        If either vector has zero magnitude or incompatible dimensions
    TypeError
        If the input types are not numeric arrays or lists
    """
    try:
        # Convert inputs to numpy arrays
        x_array = np.array(x, dtype=float)
        y_array = np.array(y, dtype=float)

        # Check for zero vectors
        x_norm = np.linalg.norm(x_array)
        y_norm = np.linalg.norm(y_array)

        if x_norm < 1e-10 or y_norm < 1e-10:
            raise ValueError("Cosine similarity is undefined for zero vectors")

        # For cosine similarity, vectors are "identical" (sim=1) if they point in the same direction
        # This means they are scalar multiples of each other
        similarity_value = self.similarity(x, y)

        # Check if vectors are parallel (same direction)
        are_parallel = abs(similarity_value - 1.0) < 1e-10

        # For the identity of discernibles, we need to check if:
        # 1. If vectors are identical (same direction and magnitude), similarity should be 1
        # 2. If vectors are different in any way, similarity should be < 1

        # Check if vectors are identical (same values)
        are_identical = np.array_equal(x_array, y_array)

        # For cosine similarity, the identity of discernibles is satisfied if:
        # - Identical vectors have similarity 1 (always true for non-zero vectors)
        # - Different vectors that are not parallel have similarity < 1

        if are_identical:
            return are_parallel  # Should be True for identical non-zero vectors
        else:
            # For different vectors, we only care if the similarity correctly reflects
            # whether they're parallel or not
            if are_parallel:
                # If vectors differ but are parallel, they're scalar multiples
                # For cosine similarity, this is still considered "identical" in direction
                return True
            else:
                # If vectors are different and not parallel, similarity should be < 1
                return similarity_value < 1.0 - 1e-10

    except Exception as e:
        logger.error(f"Error checking identity of discernibles: {str(e)}")
        raise

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

dissimilarities

dissimilarities(x, ys)

Calculate dissimilarities between one object and multiple other objects.

Parameters

x : ComparableType Reference object ys : Sequence[ComparableType] Sequence of objects to compare against the reference

Returns

List[float] List of dissimilarity scores between x and each element in ys

Raises

NotImplementedError This method must be implemented by subclasses ValueError If any objects are incomparable or have incompatible dimensions TypeError If any input types are not supported

Source code in swarmauri_base/similarities/SimilarityBase.py

def dissimilarities(
    self, x: ComparableType, ys: Sequence[ComparableType]
) -> List[float]:
    """
    Calculate dissimilarities between one object and multiple other objects.

    Parameters
    ----------
    x : ComparableType
        Reference object
    ys : Sequence[ComparableType]
        Sequence of objects to compare against the reference

    Returns
    -------
    List[float]
        List of dissimilarity scores between x and each element in ys

    Raises
    ------
    NotImplementedError
        This method must be implemented by subclasses
    ValueError
        If any objects are incomparable or have incompatible dimensions
    TypeError
        If any input types are not supported
    """
    # Default implementation can be overridden for efficiency
    try:
        return [self.dissimilarity(x, y) for y in ys]
    except Exception as e:
        logger.error(f"Error calculating dissimilarities: {str(e)}")
        raise

check_reflexivity

check_reflexivity(x)

Check if the similarity measure is reflexive: s(x,x) = 1.

Parameters

x : ComparableType Object to check reflexivity with

Returns

bool True if s(x,x) = 1, False otherwise

Raises

TypeError If the input type is not supported

Source code in swarmauri_base/similarities/SimilarityBase.py

def check_reflexivity(self, x: ComparableType) -> bool:
    """
    Check if the similarity measure is reflexive: s(x,x) = 1.

    Parameters
    ----------
    x : ComparableType
        Object to check reflexivity with

    Returns
    -------
    bool
        True if s(x,x) = 1, False otherwise

    Raises
    ------
    TypeError
        If the input type is not supported
    """
    try:
        # A similarity measure is reflexive if s(x,x) = 1
        similarity_value = self.similarity(x, x)
        # Use approximate equality to handle floating-point precision issues
        return abs(similarity_value - 1.0) < 1e-10
    except Exception as e:
        logger.error(f"Error checking reflexivity: {str(e)}")
        raise