Skip to main content
Version: Beta 🚧

Inference

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 Inference class describes a model inference feature that is applied to a Batch Feature View via features param.

Example

from tecton import Inference, batch_feature_view
from tecton.types import String, Int64
@batch_feature_view(
# ...
features=[
Inference(
input_columns=[Field("my_field1", String), Field("my_field2", Int64)],
model="my_custom_model",
name="my_inference_feature"
),
Inference(
input_columns=[Field("my_field3", String), Field("my_field4", Int64)],
model="my_custom_model",
name="my_other_inference_feature"m
description="my inference feature description",
tags={"tag": "value"}
)
],
)
def my_fv(data_source):
return data_source

Attributes​

NameData TypeDescription
descriptionOptional[str]A human-readable description of the feature
tagsOptional[Dict[str, str]]Tags associated with the feature (key-value pairs of user-defined metadata).
modelstrThe model name that is used to compute the inference feature. The model needs to be registered in advance using tecton model CLI.
input_columnsList[Field]A list of columns that are used as inputs to the model.
nameOptional[str]The name of this feature. Defaults to an autogenerated name, e.g. "my_inference_feature".

Methods​

NameDescription
__init__(...)Initialize Inference

__init__(...)​

Parameters

  • description (Optional[str]) - A human-readable description of the feature Default: None

  • tags (Optional[Dict[str, str]]) - Tags associated with the feature (key-value pairs of user-defined metadata). Default: None

  • model (str) - The model name that is used to compute the inference feature. The model needs to be registered in advance using tecton model CLI. Default: None

  • input_columns (List[Field]) - A list of columns that are used as inputs to the model. Default: None

  • name (Optional[str]) - The name of this feature. Defaults to an autogenerated name, e.g. "my_inference_feature". Default: None

Was this page helpful?