Embedding

Private Preview

This feature is currently in Private Preview.

This feature has the following limitations:

• Must be enabled by Tecton Support.
• Available for Rift-based Feature Views.

If you would like to participate in the preview, please file a support ticket.

Summary

The Embedding class describes an embedding feature that is applied to a Batch Feature View via features param.

Example

from tecton import Embedding, batch_feature_view
from tecton.types import String

@batch_feature_view(
    # ...
    features=[
        Embedding(
            input_column=Field("my_column", String),
            model="sentence-transformers/all-MiniLM-L6-v2",
            name="my_embedding_feature"
        ),
        Embedding(
            input_column=Field("my_other_column", String),
            model="sentence-transformers/all-MiniLM-L6-v2",
            name="my_other_embedding_feature",
            description="my embedding feature description",
            tags={"tag": "value"}
        )
    ],
)
def my_fv(data_source):
    return data_source

Attributes

Name	Data Type	Description
description	Optional[str]	A human-readable description of the feature
tags	Optional[Dict[str, str]]	Tags associated with the feature (key-value pairs of user-defined metadata).
input_column	Field	Describes name and type of the column that will be used in the aggregation.
model	str	The model name that is used to compute the embedding feature. Check https://docs.tecton.ai/docs/beta/defining-features/feature-views/embeddings for all supported models.
name	Optional[str]	The name of this feature. Defaults to an autogenerated name, e.g. "my_embedding_feature".

__init__(...)

Parameters

• description: Optional[str] = None A human-readable description of the feature
• tags: Optional[Dict[str, str]] = None Tags associated with the feature (key-value pairs of user-defined metadata).
• input_column: Field = None Describes name and type of the column that will be used in the aggregation.
• model: str = None The model name that is used to compute the embedding feature. Check https://docs.tecton.ai/docs/beta/defining-features/feature-views/embeddings for all supported models.
• name: Optional[str] = None The name of this feature. Defaults to an autogenerated name, e.g. "my_embedding_feature".