Flat Orchestrator

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

class Flat : public svs::manager::IndexManager<FlatInterface>

Type erased container for the Flat index.

Public Types

using search_parameters_type = typename IFace::search_parameters_type

Require the presence of the search_parameters_type alias in the instantiating interface.

Public Functions

inline void save(const std::filesystem::path &data_directory) const

Save the Flat index to disk.

Parameters:

data_directory – Directory where the index data will be saved.

template<typename Query>
inline double get_distance(size_t id, const Query &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

inline size_t size() const

Return the number of elements in the indexed dataset.

inline size_t dimensions() const

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

inline std::vector<svs::DataType> query_types() const

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

inline size_t get_num_threads() const

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

inline void set_threadpool(Pool threadpool)

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

ThreadPool

An acceptable thread pool should implement two methods:

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

  • void parallel_for(std::function<void(size_t)> f, size_t n). This method should execute f. Here, f(i) represents a task on the i^th partition, and n represents the number of partitions that need to be executed.

Parameters:

threadpool – An acceptable thread pool.

inline threads::ThreadPoolHandle &get_threadpool_handle()

Return the current thread pool handle.

Public Static Functions

template<manager::QueryTypeDefinition QueryTypes, typename DataLoader, typename Distance, typename ThreadPoolProto>
static inline Flat assemble(DataLoader &&data_loader, Distance distance, ThreadPoolProto threadpool_proto)

Load a Flat Index from an existing dataset.

data_loader

The data loader should be any object loadable via svs::detail::dispatch_load returning a Vamana compatible dataset. Concrete examples include:

ThreadPool

An acceptable thread pool should implement two methods:

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

  • void parallel_for(std::function<void(size_t)> f, size_t n). This method should execute f. Here, f(i) represents a task on the i^th partition, and n 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 a svs::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 using threadpool_proto as the number of threads to create.

struct AssembleTag

Internal dispatch tag.