Index the embeddings infered by the model to allow distance based
sub-linear search
-
class CalibrationResults: Cutpoints and thresholds associated with a calibration. -
class ClassificationMatch: Abstract base class for defining the classification matching strategy. -
class ClassificationMetric: Abstract base class for computing classification metrics. -
class Distance: Note: don't forget to add your distance to the DISTANCES list -
class Evaluator: Evaluates search index performance and calibrates it. -
class F1Score: Calculates the harmonic mean of precision and recall. -
class FloatTensor: Float tensor -
class Indexer: Indexing system that allows to efficiently find nearest embeddings -
class Lookup: Metadata associated with a query match. -
class MemoryEvaluator: In memory index performance evaluation and classification. -
class MemoryStore: Efficient in-memory dataset store -
class NMSLibSearch: Efficiently find nearest embeddings by indexing known embeddings and make -
class PandasDataFrame: Symbolic pandas frame -
class Path: PurePath subclass that can make system calls. -
class RetrievalMetric: Abstract base class for computing retrieval metrics. -
class Search: Helper class that provides a standard way to create an ABC using -
class Store: Helper class that provides a standard way to create an ABC using -
class Tensor: Atf.Tensorrepresents a multidimensional array of elements. -
class defaultdict: defaultdict(default_factory[, ...]) --> dict with default factory -
class deque: deque([iterable[, maxlen]]) --> deque object -
class tqdm: Asynchronous-friendly version of tqdm (Python 3.6+).
-
distance_canonicalizer(...): Normalize user requested distance to its matching Distance object. -
make_classification_matcher(...): Convert classification matcher from str name to object if needed. -
make_classification_metric(...): Convert classification metric from str name to object if needed. -
tabulate(...): Format a fixed width table for pretty printing. -
time(...): time() -> floating point number