File MetaIndexes.h

namespace faiss

Copyright (c) Facebook, Inc. and its affiliates.

This source code is licensed under the MIT license found in the LICENSE file in the root directory of this source tree.

Throughout the library, vectors are provided as float * pointers. Most algorithms can be optimized when several vectors are processed (added/searched) together in a batch. In this case, they are passed in as a matrix. When n vectors of size d are provided as float * x, component j of vector i is

x[ i * d + j ]

where 0 <= i < n and 0 <= j < d. In other words, matrices are always compact. When specifying the size of the matrix, we call it an n*d matrix, which implies a row-major storage.

Copyright (c) Facebook, Inc. and its affiliates.

This source code is licensed under the MIT license found in the LICENSE file in the root directory of this source tree. I/O functions can read/write to a filename, a file handle or to an object that abstracts the medium.

The read functions return objects that should be deallocated with delete. All references within these objectes are owned by the object.

Copyright (c) Facebook, Inc. and its affiliates.

This source code is licensed under the MIT license found in the LICENSE file in the root directory of this source tree. Definition of inverted lists + a few common classes that implement the interface.

Copyright (c) Facebook, Inc. and its affiliates.

This source code is licensed under the MIT license found in the LICENSE file in the root directory of this source tree. Since IVF (inverted file) indexes are of so much use for large-scale use cases, we group a few functions related to them in this small library. Most functions work both on IndexIVFs and IndexIVFs embedded within an IndexPreTransform.

Copyright (c) Facebook, Inc. and its affiliates.

This source code is licensed under the MIT license found in the LICENSE file in the root directory of this source tree. In this file are the implementations of extra metrics beyond L2 and inner product

Copyright (c) Facebook, Inc. and its affiliates.

This source code is licensed under the MIT license found in the LICENSE file in the root directory of this source tree. Defines a few objects that apply transformations to a set of vectors Often these are pre-processing steps.

Typedefs

using IndexIDMap = IndexIDMapTemplate<Index>

using IndexBinaryIDMap = IndexIDMapTemplate<IndexBinary>

using IndexIDMap2 = IndexIDMap2Template<Index>

using IndexBinaryIDMap2 = IndexIDMap2Template<IndexBinary>

template<typename IndexT> struct IndexIDMap2Template : public faiss::IndexIDMapTemplate<IndexT>

#include <MetaIndexes.h>

same as IndexIDMap but also provides an efficient reconstruction implementation via a 2-way index

Public Types

using idx_t = typename IndexT::idx_t

using component_t = typename IndexT::component_t

using distance_t = typename IndexT::distance_t

Public Functions

explicit IndexIDMap2Template(IndexT *index)

void construct_rev_map(): make the rev_map from scratch

void add_with_ids(idx_t n, const component_t *x, const idx_t *xids) override

size_t remove_ids(const IDSelector &sel) override

void reconstruct(idx_t key, component_t *recons) const override

inline ~IndexIDMap2Template() override

inline IndexIDMap2Template()

void add(idx_t n, const component_t *x) override: this will fail. Use add_with_ids

void search(idx_t n, const component_t *x, idx_t k, distance_t *distances, idx_t *labels) const override

void train(idx_t n, const component_t *x) override

void reset() override

void range_search(idx_t n, const component_t *x, distance_t radius, RangeSearchResult *result) const override

Public Members

std::unordered_map<idx_t, idx_t> rev_map

IndexT *index

bool own_fields: ! the sub-index

std::vector<idx_t> id_map: ! whether pointers are deleted in destructo

template<typename IndexT> struct IndexIDMapTemplate : public IndexT 

#include <MetaIndexes.h>

Index that translates search results to ids

Subclassed by faiss::IndexIDMap2Template< IndexT >

Public Types

using idx_t = typename IndexT::idx_t

using component_t = typename IndexT::component_t

using distance_t = typename IndexT::distance_t

Public Functions

explicit IndexIDMapTemplate(IndexT *index)

void add_with_ids(idx_t n, const component_t *x, const idx_t *xids) override

Parameters: xids – if non-null, ids to store for the vectors (size n)

void add(idx_t n, const component_t *x) override: this will fail. Use add_with_ids

void search(idx_t n, const component_t *x, idx_t k, distance_t *distances, idx_t *labels) const override

void train(idx_t n, const component_t *x) override

void reset() override

size_t remove_ids(const IDSelector &sel) override: remove ids adapted to IndexFlat

void range_search(idx_t n, const component_t *x, distance_t radius, RangeSearchResult *result) const override

~IndexIDMapTemplate() override

inline IndexIDMapTemplate()

Public Members

IndexT *index

bool own_fields: ! the sub-index

std::vector<idx_t> id_map: ! whether pointers are deleted in destructo

struct IndexSplitVectors : public faiss::Index 

#include <MetaIndexes.h>

splits input vectors in segments and assigns each segment to a sub-index used to distribute a MultiIndexQuantizer

Public Functions

explicit IndexSplitVectors(idx_t d, bool threaded = false): sum of dimensions seen so far

void add_sub_index(Index*)

void sync_with_sub_indexes()

virtual void add(idx_t n, const float *x) override

Add n vectors of dimension d to the index.

Vectors are implicitly assigned labels ntotal .. ntotal + n - 1 This function slices the input vectors in chunks smaller than blocksize_add and calls add_core.

Parameters: x – input matrix, size n * d

virtual void search(idx_t n, const float *x, idx_t k, float *distances, idx_t *labels) const override

query n vectors of dimension d to the index.

return at most k vectors. If there are not enough results for a query, the result array is padded with -1s.

Parameters

x – input vectors to search, size n * d
labels – output labels of the NNs, size n*k
distances – output pairwise distances, size n*k

virtual void train(idx_t n, const float *x) override

Perform training on a representative set of vectors

Parameters

n – nb of training vectors
x – training vecors, size n * d

virtual void reset() override: removes all elements from the database.

~IndexSplitVectors() override

Public Members

bool own_fields

bool threaded

std::vector<Index*> sub_indexes

idx_t sum_d