Skip to content

Class swarmauri_standard.embeddings.TfidfEmbedding.TfidfEmbedding

swarmauri_standard.embeddings.TfidfEmbedding.TfidfEmbedding

TfidfEmbedding(**kwargs)

Bases: EmbeddingBase

Source code in swarmauri_standard/embeddings/TfidfEmbedding.py
21
22
23
24
25
26
def __init__(self, **kwargs):
    super().__init__(**kwargs)
    # Initialize our internal attributes.
    self._features = []  # This will hold our vocabulary.
    self._idf = {}  # This will hold the computed idf for each token.
    self._fit_matrix = []  # This will hold the TF-IDF vectors.

type class-attribute instance-attribute

type = 'TfidfEmbedding'

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=EMBEDDING.value, frozen=True)

version class-attribute instance-attribute

version = '0.1.0'

extract_features

extract_features()

Returns the list of features (vocabulary terms) that were extracted during fitting.

Source code in swarmauri_standard/embeddings/TfidfEmbedding.py
28
29
30
31
32
def extract_features(self) -> List[str]:
    """
    Returns the list of features (vocabulary terms) that were extracted during fitting.
    """
    return self._features

fit

fit(documents)

Fits the TF-IDF model on the provided documents. It computes the vocabulary, document frequencies, idf values, and the TF-IDF vectors for each document.

Source code in swarmauri_standard/embeddings/TfidfEmbedding.py
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
def fit(self, documents: List[str]) -> None:
    """
    Fits the TF-IDF model on the provided documents.
    It computes the vocabulary, document frequencies, idf values, and the TF-IDF
    vectors for each document.
    """
    N = len(documents)
    df = defaultdict(int)
    tokenized_docs = []

    # Tokenize documents and compute document frequency for each token.
    for doc in documents:
        # Simple tokenization: lowercasing and splitting on whitespace.
        tokens = doc.lower().split()
        tokenized_docs.append(tokens)
        for token in set(tokens):  # use set() to count each token once per doc
            df[token] += 1

    # Build a sorted vocabulary for consistent vector ordering.
    self._features = sorted(list(df.keys()))

    # Compute idf for each term using the formula: log(N / df)
    self._idf = {token: math.log(N / df[token]) for token in self._features}

    # Now compute the TF-IDF vector for each document.
    self._fit_matrix = []
    for tokens in tokenized_docs:
        tf = Counter(tokens)
        doc_len = len(tokens)
        vector = []
        for token in self._features:
            # Compute term frequency (TF) for the token in this document.
            tf_value = tf[token] / doc_len if doc_len > 0 else 0.0
            # Multiply by idf to get the TF-IDF weight.
            tfidf_value = tf_value * self._idf[token]
            vector.append(tfidf_value)
        self._fit_matrix.append(vector)

fit_transform

fit_transform(documents)

Fits the model on the provided documents and returns the TF-IDF vectors as a list of Vector instances.

Source code in swarmauri_standard/embeddings/TfidfEmbedding.py
72
73
74
75
76
77
78
def fit_transform(self, documents: List[str]) -> List[Vector]:
    """
    Fits the model on the provided documents and returns the TF-IDF vectors as a list
    of Vector instances.
    """
    self.fit(documents)
    return [Vector(value=vec) for vec in self._fit_matrix]

transform

transform(documents)

Transforms new documents into TF-IDF vectors using the vocabulary and idf values computed during fitting. Any term not in the vocabulary is ignored.

Source code in swarmauri_standard/embeddings/TfidfEmbedding.py
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
def transform(self, documents: List[str]) -> List[Vector]:
    """
    Transforms new documents into TF-IDF vectors using the vocabulary and idf values
    computed during fitting. Any term not in the vocabulary is ignored.
    """
    if not self._features or not self._idf:
        raise ValueError(
            "The model has not been fitted yet. Please call fit first."
        )

    transformed_vectors = []
    for doc in documents:
        tokens = doc.lower().split()
        tf = Counter(tokens)
        doc_len = len(tokens)
        vector = []
        for token in self._features:
            tf_value = tf[token] / doc_len if doc_len > 0 else 0.0
            # If the token is not in the fitted vocabulary, its idf defaults to 0.
            idf_value = self._idf.get(token, 0.0)
            vector.append(tf_value * idf_value)
        transformed_vectors.append(Vector(value=vector))
    return transformed_vectors

infer_vector

infer_vector(data, documents)

Infers a TF-IDF vector for a new document. In this implementation, we append the new document to the provided corpus, re-fit the model, and return the vector for the new document. (Note: This re-fits the model which might be inefficient for production but mirrors the original logic.)

Source code in swarmauri_standard/embeddings/TfidfEmbedding.py
104
105
106
107
108
109
110
111
112
113
def infer_vector(self, data: str, documents: List[str]) -> Vector:
    """
    Infers a TF-IDF vector for a new document. In this implementation, we append the
    new document to the provided corpus, re-fit the model, and return the vector for
    the new document. (Note: This re-fits the model which might be inefficient for
    production but mirrors the original logic.)
    """
    documents.append(data)
    vectors = self.fit_transform(documents)
    return vectors[-1]

save_model

save_model(path)

Saves the TF-IDF model (i.e. the vocabulary and idf values) to the specified path using joblib.

Source code in swarmauri_standard/embeddings/TfidfEmbedding.py
115
116
117
118
119
120
121
122
123
124
def save_model(self, path: str) -> None:
    """
    Saves the TF-IDF model (i.e. the vocabulary and idf values) to the specified path
    using joblib.
    """
    model_data = {
        "features": self._features,
        "idf": self._idf,
    }
    joblib.dump(model_data, path)

load_model

load_model(path)

Loads a TF-IDF model (i.e. the vocabulary and idf values) from the specified path using joblib.

Source code in swarmauri_standard/embeddings/TfidfEmbedding.py
126
127
128
129
130
131
132
133
def load_model(self, path: str) -> None:
    """
    Loads a TF-IDF model (i.e. the vocabulary and idf values) from the specified path
    using joblib.
    """
    model_data = joblib.load(path)
    self._features = model_data.get("features", [])
    self._idf = model_data.get("idf", {})

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
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
@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
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
@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
12
13
14
15
16
17
18
19
20
21
22
23
24
@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
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
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
11
12
13
14
15
16
17
18
19
20
21
22
23
@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
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
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
23
24
25
26
27
28
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