Class swarmauri_standard.embeddings.GeminiEmbedding.GeminiEmbedding

swarmauri_standard.embeddings.GeminiEmbedding.GeminiEmbedding

GeminiEmbedding(**kwargs)

Bases: EmbeddingBase

A class for generating embeddings using the Google Gemini API via REST endpoints.

This class allows users to obtain embeddings for text data using specified models from the Gemini API through direct HTTP requests.

ATTRIBUTE	DESCRIPTION
model	The model to use for generating embeddings. Defaults to 'text-embedding-004'. TYPE: str
allowed_models	List of supported Gemini embedding models. TYPE: List[str]
allowed_task_types	List of supported task types for embeddings. TYPE: List[str]
api_key	API key for authentication. Can be None for serialization. TYPE: str

RAISES	DESCRIPTION
ValueError	If an invalid model or task type is provided during initialization.

Example

gemini_embedding = GeminiEmbedding(api_key='your_api_key', model='text-embedding-004') embeddings = gemini_embedding.infer_vector(["Hello, world!", "Data science is awesome."])

Source code in swarmauri_standard/embeddings/GeminiEmbedding.py

def __init__(
    self,
    **kwargs,
):
    super().__init__(**kwargs)

    if self.model not in self.allowed_models:
        raise ValueError(
            f"Invalid model '{self.model}'. Allowed models are: {', '.join(self.allowed_models)}"
        )

    if self.task_type not in self.allowed_task_types:
        raise ValueError(
            f"Invalid task_type '{self.task_type}'. Allowed task types are: {', '.join(self.allowed_task_types)}"
        )

    if self.api_key.get_secret_value():
        self._headers = {
            "Content-Type": "application/json",
        }
        self._client = httpx.Client()

type class-attribute instance-attribute

type = 'GeminiEmbedding'

allowed_models class-attribute instance-attribute

allowed_models = ['text-embedding-004', 'embedding-001']

allowed_task_types class-attribute instance-attribute

allowed_task_types = [
    "unspecified",
    "retrieval_query",
    "retrieval_document",
    "semantic_similarity",
    "classification",
    "clustering",
    "question_answering",
    "fact_verification",
]

model class-attribute instance-attribute

model = Field(default='text-embedding-004')

api_key class-attribute instance-attribute

api_key = Field(default=None)

task_type class-attribute instance-attribute

task_type = Field(default='unspecified')

output_dimensionality class-attribute instance-attribute

output_dimensionality = Field(default=None)

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'

infer_vector

infer_vector(data)

Generate embeddings for the given list of strings.

PARAMETER	DESCRIPTION
data	A list of strings to generate embeddings for. TYPE: List[str]

RETURNS	DESCRIPTION
List[Vector]	List[Vector]: A list of Vector objects containing the generated embeddings.

RAISES	DESCRIPTION
ValueError	If an error occurs during the API request or response processing.

Source code in swarmauri_standard/embeddings/GeminiEmbedding.py

def infer_vector(self, data: List[str]) -> List[Vector]:
    """
    Generate embeddings for the given list of strings.

    Args:
        data (List[str]): A list of strings to generate embeddings for.

    Returns:
        List[Vector]: A list of Vector objects containing the generated embeddings.

    Raises:
        ValueError: If an error occurs during the API request or response processing.
    """
    if not self.api_key.get_secret_value():
        raise ValueError("API key must be provided for inference")

    if not data:
        return []

    embeddings = []
    for text in data:
        payload = {
            "model": f"models/{self.model}",
            "content": {"parts": [{"text": text}]},
        }

        if self.task_type != "unspecified":
            payload["taskType"] = self.task_type
        if self.output_dimensionality:
            payload["outputDimensionality"] = self.output_dimensionality

        try:
            url = f"{self._BASE_URL}/models/{self.model}:embedContent?key={self.api_key.get_secret_value()}"
            response = self._client.post(
                url, headers=self._headers, json=payload, timeout=30
            )
            response.raise_for_status()
            result = response.json()

            # Extract embedding from response
            embedding = result["embedding"]
            embeddings.append(Vector(value=embedding["values"]))

        except httpx.HTTPError as e:
            raise ValueError(f"Error calling Gemini AI API: {str(e)}")
        except (KeyError, ValueError) as e:
            raise ValueError(f"Error processing Gemini AI API response: {str(e)}")

    return embeddings

transform

transform(data)

Transform a list of texts into embeddings.

PARAMETER	DESCRIPTION
data	List of strings to transform into embeddings. TYPE: List[str]

RETURNS	DESCRIPTION
List[Vector]	List[Vector]: A list of vectors representing the transformed data.

Source code in swarmauri_standard/embeddings/GeminiEmbedding.py

def transform(self, data: List[str]) -> List[Vector]:
    """
    Transform a list of texts into embeddings.

    Args:
        data (List[str]): List of strings to transform into embeddings.

    Returns:
        List[Vector]: A list of vectors representing the transformed data.
    """
    return self.infer_vector(data)

save_model

save_model(path)

Source code in swarmauri_standard/embeddings/GeminiEmbedding.py

def save_model(self, path: str):
    raise NotImplementedError("save_model is not applicable for Gemini embeddings")

load_model

load_model(path)

Source code in swarmauri_standard/embeddings/GeminiEmbedding.py

def load_model(self, path: str):
    raise NotImplementedError("load_model is not applicable for Gemini embeddings")

fit

fit(documents, labels=None)

Source code in swarmauri_standard/embeddings/GeminiEmbedding.py

def fit(self, documents: List[str], labels=None):
    raise NotImplementedError("fit is not applicable for Gemini embeddings")

fit_transform

fit_transform(documents, **kwargs)

Source code in swarmauri_standard/embeddings/GeminiEmbedding.py

def fit_transform(self, documents: List[str], **kwargs):
    raise NotImplementedError(
        "fit_transform is not applicable for Gemini embeddings"
    )

extract_features

extract_features()

Source code in swarmauri_standard/embeddings/GeminiEmbedding.py

def extract_features(self):
    raise NotImplementedError(
        "extract_features is not applicable for Gemini embeddings"
    )

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