Prompt

Private Preview

Tecton managed Prompts are in Private Preview.

Summary

A Tecton Prompt.
 
The Prompt should not be instantiated directly and the tecton.prompt decorator is recommended instead.

Example

@prompt(
    sources=[offer_email_request, last_product_viewed, last_order_metrics, weekly_spend],
    description="Contextual prompt for offer generation email",
)
def offer_email_prompt(offer_email_request, last_product_viewed, last_order_metrics, weekly_spend):
    offer_email_prompt_template = """\
    Generate a personalized offer email for user {name} given the following information about them:
    last product viewed: {last_product_viewed}
    total spend over last 7 days: {last_week_spend}
    time since last order: {time_since_last_order}
    """

    return offer_email_prompt_template.format(
        name=offer_email_request["user_name"],
        last_product_viewed=last_product_viewed["product_name_last_7d_10m"],
        last_week_spend=weekly_spend["amt_sum_7d_1d"],
        time_since_last_order=last_order_metrics["time_since_last_order"],
    )

@prompt (Decorator)

Declare a Prompt

Parameters

• name (Optional[str]) - Unique, human friendly name that identifies the FeatureView. Defaults to the function name. Default: None


• description (Optional[str]) - A human-readable description. Default: None


• owner (Optional[str]) - Owner name (typically the email of the primary maintainer). Default: None


• tags (Optional[Dict[str, str]]) - Tags associated with this Tecton Object (key-value pairs of arbitrary metadata). Default: None


• prevent_destroy (bool) - If True, this Tecton object will be blocked from being deleted or re-created (i.e. a destructive update) during tecton plan/apply. To remove or update this object, prevent_destroy must be set to False via the same tecton apply or a separate tecton apply. prevent_destroy can be used to prevent accidental changes such as inadvertently deleting a Feature Service used in production or recreating a Feature View that triggers expensive re-materialization jobs. prevent_destroy also blocks changes to dependent Tecton objects that would trigger a recreation of the tagged object, e.g. if prevent_destroy is set on a Feature Service, that will also prevent deletions or re-creates of Feature Views used in that service. prevent_destroy is only enforced in live (i.e. non-dev) workspaces. Default: false


• sources (Optional[List[Union[configs.RequestSource, FeatureView, 'FeatureReference']]]) - The data source inputs to the feature view. An input can be a RequestSource, a BatchFeatureView, or a StreamFeatureView Default: None


• environment (Optional[str]) - The environment in which this feature view can run. Defaults to None, which means the feature view can run in any environment. If specified, the feature view will only run in the specified environment. Learn more about environments at On Demand Feature View Environments Default: None


• context_parameter_name (Optional[str]) - Name of the function parameter that Tecton injects Realtime Context to. This context is a RealtimeContext object for Python mode FVs and a pandas.DataFrame object for Pandas mode FVs. Default: None

Returns

An object of type Prompt.

Prompt (Class)

Attributes

Name	Data Type	Description
context_parameter_name	Optional[str]	Name of the function parameter that Tecton injects Realtime Context to.
created_at	Optional[datetime.datetime]	Returns the time that this Tecton object was created or last updated. None for locally defined objects.
defined_in	Optional[str]	The repo filename where this object was declared. None for locally defined objects.
description	Optional[str]	Returns the description of the Tecton object.
environment	Optional[str]	The environment in which this feature view runs.
feature_metadata	List[FeatureMetadata]
id	str	Returns the unique id of the Tecton object.
info
join_keys	List[str]	The join key column names.
name	str	Returns the name of the Tecton object.
online_serving_index	List[str]	The set of join keys that will be indexed and queryable during online serving.   defaults to the complete set of join keys.
owner	Optional[str]	Returns the owner of the Tecton object.
prevent_destroy	bool	If set to True, Tecton will block destructive actions taken on this Feature View or Feature Table.
sources
tags	Dict[str, str]	Returns the tags of the Tecton object.
transformations
url	str	Returns a link to the Tecton Web UI.
wildcard_join_key	Optional[set]	Returns a wildcard join key column name if it exists; Otherwise returns None.
workspace	Optional[str]	Returns the workspace that this Tecton object belongs to. None for locally defined objects.

Methods

Name	Description
get_online_prompt(...)	Returns a Prompt that's generated using an Online Transformation for the given request data and the
get_prompts_for_events(...)	Returns a Tecton TectonDataFrame of the prompts that would be generated for each set of events, plus
print_transformation_schema()	Prints the schema of the output of the transformation.
run_prompt(...)	Get the prompt using mock inputs.
summary()	Displays a human-readable summary.
transformation_schema()	Returns the schema of the output of the transformation.
with_join_key_map(...)	Rebind join keys for a Feature View or Feature Table used in a Feature Service.
with_name(...)	Rename a Feature View or Feature Table used in a Feature Service.

get_online_prompt(...)

Returns a Prompt that's generated using an Online Transformation for the given request data and the latest feature values from the Online Store for the given join keys (if using dependent Feature Views).

Parameters

• join_keys (Optional[Mapping[str, Union[int, numpy.int_, str, bytes]]]) - Join keys of any dependent Feature Views of the Prompt. Default: None


• include_join_keys_in_response (bool) - Whether to include join keys as part of the response FeatureVector. Default: false


• request_data (Optional[Mapping[str, Union[int, numpy.int_, str, bytes, float]]]) - Dictionary of Request-Time key-values that provide the data for the RequestSource of the Prompt. Default: None

Returns

FeatureVector: A tecton.FeatureVector of the results.

get_prompts_for_events(...)

Returns a Tecton TectonDataFrame of the prompts that would be generated for each set of events, plus the events that generated each prompts.

Parameters

• events (Union[pyspark_dataframe.DataFrame, pandas.DataFrame, TectonDataFrame, str]) - A dataframe of input feature values, request data keys, and timestamps that determine the prompt. The returned data frame will contain rollups for all (feature values, request data key) combinations that are required to compute a full frame from the events dataframe.


• timestamp_key (Optional[str]) - Name of the timestamp column. This method will fetch the latest features computed before the specified timestamps in this column. If there is only 1 column of type timestamp in the input events, it will be the timestamp_key by default. Default: None


• from_source (Optional[bool]) - Whether feature values should be recomputed from the original data source. If None, input feature values will be fetched from the Offline Store for Feature Views that have offline materialization enabled and otherwise computes feature values on the fly from raw data. Use from_source=True to force computing from raw data and from_source=False to error if any input Feature Views are not materialized. Defaults to None. Default: None


• compute_mode (Optional[Union[ComputeMode, str]]) - Compute mode to use to produce the data frame, one of "rift" or "spark" Default: None

Returns

TectonDataFrame: A Tecton TectonDataFrame.

print_transformation_schema(...)

Prints the schema of the output of the transformation.

Returns

None

run_prompt(...)

Get the prompt using mock inputs.

Parameters

• input_data (Optional[Dict[str, Any]]) - Required. Dict with the same expected keys as the Prompt's inputs parameters. Each value must be a Dictionary representing a single row. Default: None

Returns

str: The resulting prompt as a string.

summary()

Displays a human-readable summary.

transformation_schema(...)

Returns the schema of the output of the transformation.

Returns

List[types.Field]

with_join_key_map(...)

Rebind join keys for a Feature View or Feature Table used in a Feature Service.
 
The keys in join_key_map should be the join keys, and the values should be the feature service overrides.

Parameters

• join_key_map (Dict[str, str]) - Dictionary remapping the join key names. Dictionary keys are join keys, values are the feature service override values.

Returns

FeatureReference

Example

from tecton import FeatureService

# The join key for this feature service will be "feature_service_user_id".
feature_service = FeatureService(
    name="feature_service",
    features=[
        my_feature_view.with_join_key_map({"user_id" : "feature_service_user_id"}),
    ],
)

# Here is a more sophisticated example. The join keys for this feature service will be "transaction_id",
# "sender_id", and "recipient_id" and will contain three feature views named "transaction_features",
# "sender_features", and "recipient_features".
transaction_fraud_service = FeatureService(
    name="transaction_fraud_service",
    features=[
        # Select a subset of features from a feature view.
        transaction_features[["amount"]],

        # Rename a feature view and/or rebind its join keys. In this example, we want user features for both the
        # transaction sender and recipient, so include the feature view twice and bind it to two different feature
        # service join keys.
        user_features.with_name("sender_features").with_join_key_map({"user_id" : "sender_id"}),
        user_features.with_name("recipient_features").with_join_key_map({"user_id" : "recipient_id"}),
    ],
)

with_name(...)

Rename a Feature View or Feature Table used in a Feature Service.

Parameters

• namespace (str) - The namespace used to prefix the features joined from this FeatureView. By default, namespace is set to the FeatureView name.

Returns

FeatureReference

Examples

from tecton import FeatureService

# The feature view in this feature service will be named "new_named_feature_view" in training data dataframe
# columns and other metadata.

feature_service = FeatureService(
    name="feature_service",
    features=[
        my_feature_view.with_name("new_named_feature_view")
    ],
)

# Here is a more sophisticated example. The join keys for this feature service will be "transaction_id",
# "sender_id", and "recipient_id" and will contain three feature views named "transaction_features",
# "sender_features", and "recipient_features".
transaction_fraud_service = FeatureService(
    name="transaction_fraud_service",
    features=[
        # Select a subset of features from a feature view.
        transaction_features[["amount"]],

        # Rename a feature view and/or rebind its join keys. In this example, we want user features for both the
        # transaction sender and recipient, so include the feature view twice and bind it to two different feature
        # service join keys.
        user_features.with_name("sender_features").with_join_key_map({"user_id" : "sender_id"}),
        user_features.with_name("recipient_features").with_join_key_map({"user_id" : "recipient_id"}),
    ],
)