Flat Orchestrator

Documentation for the type-erased version of thesvs::index::flat::FlatIndex.

classFlat:publicsvs::manager::IndexManager<FlatInterface>

Type erased container for theFlat index.

Public Types

usingsearch_parameters_type=typenameIFace::search_parameters_type

Require the presence of thesearch_parameters_type alias in the instantiating interface.

Public Functions

inlinevoidsave(conststd::filesystem::path&data_directory)const

Save theFlat index to disk.

Parameters:

data_directory – Directory where the index data will be saved.

template<typenameQuery>
inlinedoubleget_distance(size_tid,constQuery&query)const

Get the distance between a vector in the index and a query vector.

Distance

Template Parameters:

Query – The query vector type

Parameters:

  • id – The ID of the vector in the index

  • query – The query vector

inlinesize_tsize()const

Return the number of elements in the indexed dataset.

inlinesize_tdimensions()const

Return the logical number of dimensions of each vector in the indexed dataset.

inlinestd::vector<svs::DataType>query_types()const

Return query-types that this index is specialized to work with.

inlinesize_tget_num_threads()const

Return the current number of worker threads used by this index for searches.

inlinevoidset_threadpool(Poolthreadpool)

Destroy the original thread pool and set to the new one.

ThreadPool

An acceptable thread pool should implement two methods:

  • size_tsize(). This method should return the number of threads used in the thread pool.

  • voidparallel_for(std::function<void(size_t)>f,size_tn). This method should executef. Here,f(i) represents a task on thei^th partition, andn represents the number of partitions that need to be executed.

Parameters:

threadpool – An acceptable thread pool.

inlinethreads::ThreadPoolHandle&get_threadpool_handle()

Return the current thread pool handle.

Public Static Functions

template<manager::QueryTypeDefinitionQueryTypes,typenameDataLoader,typenameDistance,typenameThreadPoolProto>
staticinlineFlatassemble(DataLoader&&data_loader,Distancedistance,ThreadPoolProtothreadpool_proto)

Load aFlat Index from an existing dataset.

data_loader

The data loader should be any object loadable viasvs::detail::dispatch_load returning aVamana compatible dataset. Concrete examples include:

ThreadPool

An acceptable thread pool should implement two methods:

  • size_tsize(). This method should return the number of threads used in the thread pool.

  • voidparallel_for(std::function<void(size_t)>f,size_tn). This method should executef. Here,f(i) represents a task on thei^th partition, andn represents the number of partitions that need to be executed.

Template Parameters:

QueryType – The element type of the vectors that will be used for querying.

Parameters:

  • data_loader – A compatible class capable of load data. See expanded notes.

  • distance – A distance functor to use or asvs::DistanceType enum.

  • threadpool_proto – Precursor for the thread pool to use. Can either be an acceptable thread pool instance or an integer specifying the number of threads to use. In the latter case, a new default thread pool will be constructed usingthreadpool_proto as the number of threads to create.

structAssembleTag

Internal dispatch tag.