Prebuilt index for an Hnsw search. More...

#include <knncolle_hnsw.hpp>

Inheritance diagram for knncolle_hnsw::HnswPrebuilt< Dim_, Index_, Float_, InternalData_ >:

Public Member Functions
Dim_	num_dimensions () const

Index_	num_observations () const

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

Friends
class	HnswSearcher< Dim_, Index_, Float_, InternalData_ >

Detailed Description

template<typename Dim_, typename Index_, typename Float_, typename InternalData_>
class knncolle_hnsw::HnswPrebuilt< Dim_, Index_, Float_, InternalData_ >

Prebuilt index for an Hnsw search.

Instances of this class are usually constructed using HnswBuilder::build_raw(). The initialize() method will create an instance of the HnswSearcher class.

Template Parameters

Dim_	Integer type for the number of dimensions. For the output of `HnswBuilder::build_raw()`, this is set to `Matrix_::dimension_type`.
Index_	Integer type for the indices. For the output of `HnswBuilder::build_raw()`, this is set to `Matrix_::index_type`.
Float_	Floating point type for the query data and output distances.
InternalData_	Floating point type for the internal data in the HNSW index.