Prebuilt index for an Annoy search. More...

#include <knncolle_annoy.hpp>

Inheritance diagram for knncolle_annoy::AnnoyPrebuilt< Distance_, Dim_, Index_, Float_, InternalIndex_, InternalData_ >:

Public Member Functions
Dim_	num_dimensions () const

Index_	num_observations () const

std::unique_ptr< knncolle::Searcher< Index_, Float_ > >	initialize () const

Friends
class	AnnoySearcher< Distance_, Dim_, Index_, Float_, InternalIndex_, InternalData_ >

Detailed Description

template<class Distance_, typename Dim_, typename Index_, typename Float_, typename InternalIndex_, typename InternalData_>
class knncolle_annoy::AnnoyPrebuilt< Distance_, Dim_, Index_, Float_, InternalIndex_, InternalData_ >

Prebuilt index for an Annoy search.

Instances of this class are usually constructed using AnnoyBuilder::build_raw().

Template Parameters

Distance_	An Annoy class to compute the distance between vectors, e.g., `Annoy::Euclidean`.
Dim_	Integer type for the number of dimensions. For the output of `AnnoyBuilder::build_raw()`, this is set to `Matrix_::dimension_type`.
Index_	Integer type for the indices. For the output of `AnnoyBuilder::build_raw()`, this is set to `Matrix_::index_type`.
Float_	Floating point type for the query data and output distances.
InternalIndex_	Integer type for the internal indices in Annoy.
InternalData_	Floating point type for the internal data in Annoy.

Member Function Documentation

◆ initialize()

template<class Distance_ , typename Dim_ , typename Index_ , typename Float_ , typename InternalIndex_ , typename InternalData_ >

std::unique_ptr< knncolle::Searcher< Index_, Float_ > > knncolle_annoy::AnnoyPrebuilt< Distance_, Dim_, Index_, Float_, InternalIndex_, InternalData_ >::initialize ( ) const