tfrs.layers.factorized_top_k.Streaming

View source on GitHub

Retrieves K highest scoring items and their ids from a large dataset.

Inherits From: TopK

tfrs.layers.factorized_top_k.Streaming(
    query_model: Optional[tf.keras.Model] = None,
    k: int = 10,
    handle_incomplete_batches: bool = True,
    num_parallel_calls: int = tf.data.AUTOTUNE,
    sorted_order: bool = True
) -> None

Used to efficiently retrieve top K query-candidate scores from a dataset, along with the top scoring candidates' identifiers.

Args
query_model	Optional Keras model for representing queries. If provided, will be used to transform raw features into query embeddings when querying the layer. If not provided, the layer will expect to be given query embeddings as inputs.
k	Number of top scores to retrieve.
handle_incomplete_batches	When True, candidate batches smaller than k will be correctly handled at the price of some performance. As an alternative, consider using the drop_remainer option when batching the candidate dataset.
num_parallel_calls	Degree of parallelism when computing scores. Defaults to autotuning.
sorted_order	If the resulting scores should be returned in sorted order. setting this to False may result in a small increase in performance.

Raises
ValueError if candidate elements are not tuples.

Methods

call

View source

call(
    queries: Union[tf.Tensor, Dict[Text, tf.Tensor]], k: Optional[int] = None
) -> Tuple[tf.Tensor, tf.Tensor]

Query the index.

Args
queries	Query features. If query_model was provided in the constructor, these can be raw query features that will be processed by the query model before performing retrieval. If query_model was not provided, these should be pre-computed query embeddings.
k	The number of candidates to retrieve. If not supplied, defaults to the k value supplied in the constructor.

Returns
Tuple of (top candidate scores, top candidate identifiers).

Raises
ValueError if index has not been called.

index

View source

index(
    candidates: tf.data.Dataset, identifiers: Optional[tf.data.Dataset] = None
) -> 'Streaming'

Not implemented. Please call index_from_dataset instead.

index_from_dataset

View source

index_from_dataset(
    candidates: tf.data.Dataset
) -> 'TopK'

Builds the retrieval index.

When called multiple times the existing index will be dropped and a new one created.

Args
candidates	Dataset of candidate embeddings or (candidate identifier, candidate embedding) pairs. If the dataset returns tuples, the identifiers will be used as identifiers of top candidates returned when performing searches. If not given, indices into the candidates dataset will be given instead.

Returns
Self.

Raises
ValueError if the dataset does not have the correct structure.

is_exact

View source

is_exact() -> bool

Indicates whether the results returned by the layer are exact.

Some layers may return approximate scores: for example, the ScaNN layer may return approximate results.

Returns
True if the layer returns exact results, and False otherwise.

query_with_exclusions

View source

@tf.function
query_with_exclusions(
    queries: Union[tf.Tensor, Dict[Text, tf.Tensor]],
    exclusions: tf.Tensor,
    k: Optional[int] = None
) -> Tuple[tf.Tensor, tf.Tensor]

Query the index.

Args
queries	Query features. If query_model was provided in the constructor, these can be raw query features that will be processed by the query model before performing retrieval. If query_model was not provided, these should be pre-computed query embeddings.
exclusions	[query_batch_size, num_to_exclude] tensor of identifiers to be excluded from the top-k calculation. This is most commonly used to exclude previously seen candidates from retrieval. For example, if a user has already seen items with ids "42" and "43", you could set exclude to [["42", "43"]].
k	The number of candidates to retrieve. Defaults to constructor k parameter if not supplied.

Returns
Tuple of (top candidate scores, top candidate identifiers).

Raises
ValueError if index has not been called. ValueError if queries is not a tensor (after being passed through the query model).