ex.Vector

A vector is a numerical representation of a Record field or attribute, usually the record's text. Vectors can be used to search for similar records via the UI or SDK. Vectors can be added to a record directly or as a dictionary with a key that the matches ex.VectorField name.

Usage Examples

To use vectors within a dataset, you must define a vector field in the dataset settings. The vector field is a list of vector fields that can be attached to a record. The following example demonstrates how to add vectors to a dataset and how to access vectors from a record object:

import extralit as ex

dataset = Dataset(
    name="dataset_with_metadata",
    settings=Settings(
        fields=[TextField(name="text")],
        questions=[LabelQuestion(name="label", labels=["positive", "negative"])],
        vectors=[
            VectorField(name="vector_name"),
        ],
    ),
)
dataset.create()

Then, you can add records to the dataset with vectors that correspond to the vector field defined in the dataset settings:

dataset.records.log(
    [
        {
            "text": "Hello World, how are you?",
            "vector_name": [0.1, 0.2, 0.3]
        }
    ]
)

Vectors can be passed using a mapping, where the key is the key in the data source and the value is the name in the dataset's setting's ex.VectorField object. For example, the following code adds a record with a vector using a mapping:

dataset.records.log(
    [
        {
            "text": "Hello World, how are you?",
            "x": [0.1, 0.2, 0.3]
        }
    ],
    mapping={"x": "vector_name"}
)

Or, vectors can be instantiated and added to a record directly, like this:

dataset.records.log(
    [
        ex.Record(
            fields={"text": "Hello World, how are you?"},
            vectors=[ex.Vector("embedding", [0.1, 0.2, 0.3])],
        )
    ]
)

---

Vector

Bases: Resource

Class for interacting with Extralit Vectors. Vectors are typically used to represent embeddings or features of records. The Vector class is used to deliver vectors to the Extralit server.

Attributes:

Name	Type	Description
name	str	The name of the vector.
values	list[float]	The values of the vector.

Source code in src/extralit/vectors.py

class Vector(Resource):
    """ Class for interacting with Extralit Vectors. Vectors are typically used to represent \
        embeddings or features of records. The `Vector` class is used to deliver vectors to the Extralit server.

    Attributes:
        name (str): The name of the vector.
        values (list[float]): The values of the vector.
    """

    _model: VectorModel

    def __init__(
        self,
        name: str,
        values: list[float],
    ) -> None:
        """Initializes a Vector with a name and values that can be used to search in the Extralit ui.

        Parameters:
            name (str): Name of the vector
            values (list[float]): List of float values

        """
        self._model = VectorModel(
            name=name,
            vector_values=values,
        )

    def __repr__(self) -> str:
        return repr(f"{self.__class__.__name__}({self._model})")

    ##############################
    # Properties
    ##############################

    @property
    def name(self) -> str:
        """Name of the vector that corresponds to the name of the vector in the dataset's `Settings`"""
        return self._model.name

    @property
    def values(self) -> list[float]:
        """List of float values that represent the vector."""
        return self._model.vector_values

    ##############################
    # Methods
    ##############################

    @classmethod
    def from_model(cls, model: VectorModel) -> "Vector":
        return cls(
            name=model.name,
            values=model.vector_values,
        )

    def serialize(self) -> dict[str, Any]:
        dumped_model = self._model.model_dump()
        name = dumped_model.pop("name")
        values = dumped_model.pop("vector_values")
        return {name: values}

name property

Name of the vector that corresponds to the name of the vector in the dataset's Settings

values property

List of float values that represent the vector.

__init__(name, values)

Initializes a Vector with a name and values that can be used to search in the Extralit ui.

Parameters:

Name	Type	Description	Default
name	str	Name of the vector	required
values	list[float]	List of float values	required

Source code in src/extralit/vectors.py

def __init__(
    self,
    name: str,
    values: list[float],
) -> None:
    """Initializes a Vector with a name and values that can be used to search in the Extralit ui.

    Parameters:
        name (str): Name of the vector
        values (list[float]): List of float values

    """
    self._model = VectorModel(
        name=name,
        vector_values=values,
    )