File IndexAdditiveQuantizer.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.

struct AdditiveCoarseQuantizer : public faiss::Index
#include <IndexAdditiveQuantizer.h>

A “virtual” index where the elements are the residual quantizer centroids.

Intended for use as a coarse quantizer in an IndexIVF.

Subclassed by faiss::LocalSearchCoarseQuantizer, faiss::ResidualCoarseQuantizer

Public Functions

explicit AdditiveCoarseQuantizer(idx_t d = 0, AdditiveQuantizer *aq = nullptr, MetricType metric = METRIC_L2)
virtual void add(idx_t n, const float *x) override

N/A.

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 reconstruct(idx_t key, float *recons) const override

Reconstruct a stored vector (or an approximation if lossy coding)

this function may not be defined for some indexes

Parameters
  • key – id of the vector to reconstruct

  • recons – reconstucted vector (size d)

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

N/A.

Public Members

AdditiveQuantizer *aq
std::vector<float> centroid_norms

norms of centroids, useful for knn-search

struct IndexAdditiveQuantizer : public faiss::Index
#include <IndexAdditiveQuantizer.h>

Abstract class for additive quantizers. The search functions are in common.

Subclassed by faiss::IndexLocalSearchQuantizer, faiss::IndexResidualQuantizer

Public Types

using Search_type_t = AdditiveQuantizer::Search_type_t

Public Functions

explicit IndexAdditiveQuantizer(idx_t d = 0, AdditiveQuantizer *aq = nullptr, MetricType metric = METRIC_L2)
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 reset() override

removes all elements from the database.

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 size_t sa_code_size() const override

size of the produced codes in bytes

virtual void sa_encode(idx_t n, const float *x, uint8_t *bytes) const override

encode a set of vectors

Parameters
  • n – number of vectors

  • x – input vectors, size n * d

  • bytes – output encoded vectors, size n * sa_code_size()

virtual void sa_decode(idx_t n, const uint8_t *bytes, float *x) const override

encode a set of vectors

Parameters
  • n – number of vectors

  • bytes – input encoded vectors, size n * sa_code_size()

  • x – output vectors, size n * d

Public Members

AdditiveQuantizer *aq
size_t code_size

size of residual quantizer codes + norms

std::vector<uint8_t> codes

Codes. Size ntotal * rq.code_size.

struct IndexLocalSearchQuantizer : public faiss::IndexAdditiveQuantizer

Public Types

using Search_type_t = AdditiveQuantizer::Search_type_t

Public Functions

IndexLocalSearchQuantizer(int d, size_t M, size_t nbits, MetricType metric = METRIC_L2, Search_type_t search_type = AdditiveQuantizer::ST_decompress)

Constructor.

Parameters
  • d – dimensionality of the input vectors

  • M – number of subquantizers

  • nbits – number of bit per subvector index

  • d – dimensionality of the input vectors

  • M – number of subquantizers

  • nbits – number of bit per subvector index

IndexLocalSearchQuantizer()
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 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 reset() override

removes all elements from the database.

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 size_t sa_code_size() const override

size of the produced codes in bytes

virtual void sa_encode(idx_t n, const float *x, uint8_t *bytes) const override

encode a set of vectors

Parameters
  • n – number of vectors

  • x – input vectors, size n * d

  • bytes – output encoded vectors, size n * sa_code_size()

virtual void sa_decode(idx_t n, const uint8_t *bytes, float *x) const override

encode a set of vectors

Parameters
  • n – number of vectors

  • bytes – input encoded vectors, size n * sa_code_size()

  • x – output vectors, size n * d

Public Members

LocalSearchQuantizer lsq
AdditiveQuantizer *aq
size_t code_size

size of residual quantizer codes + norms

std::vector<uint8_t> codes

Codes. Size ntotal * rq.code_size.

struct IndexResidualQuantizer : public faiss::IndexAdditiveQuantizer
#include <IndexAdditiveQuantizer.h>

Index based on a residual quantizer. Stored vectors are approximated by residual quantization codes. Can also be used as a codec

Public Types

using Search_type_t = AdditiveQuantizer::Search_type_t

Public Functions

IndexResidualQuantizer(int d, size_t M, size_t nbits, MetricType metric = METRIC_L2, Search_type_t search_type = AdditiveQuantizer::ST_decompress)

Constructor.

Parameters
  • d – dimensionality of the input vectors

  • M – number of subquantizers

  • nbits – number of bit per subvector index

  • d – dimensionality of the input vectors

  • M – number of subquantizers

  • nbits – number of bit per subvector index

IndexResidualQuantizer(int d, const std::vector<size_t> &nbits, MetricType metric = METRIC_L2, Search_type_t search_type = AdditiveQuantizer::ST_decompress)
IndexResidualQuantizer()
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 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 reset() override

removes all elements from the database.

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 size_t sa_code_size() const override

size of the produced codes in bytes

virtual void sa_encode(idx_t n, const float *x, uint8_t *bytes) const override

encode a set of vectors

Parameters
  • n – number of vectors

  • x – input vectors, size n * d

  • bytes – output encoded vectors, size n * sa_code_size()

virtual void sa_decode(idx_t n, const uint8_t *bytes, float *x) const override

encode a set of vectors

Parameters
  • n – number of vectors

  • bytes – input encoded vectors, size n * sa_code_size()

  • x – output vectors, size n * d

Public Members

ResidualQuantizer rq

The residual quantizer used to encode the vectors.

AdditiveQuantizer *aq
size_t code_size

size of residual quantizer codes + norms

std::vector<uint8_t> codes

Codes. Size ntotal * rq.code_size.

struct LocalSearchCoarseQuantizer : public faiss::AdditiveCoarseQuantizer

Public Functions

LocalSearchCoarseQuantizer(int d, size_t M, size_t nbits, MetricType metric = METRIC_L2)

Constructor.

Parameters
  • d – dimensionality of the input vectors

  • M – number of subquantizers

  • nbits – number of bit per subvector index

  • d – dimensionality of the input vectors

  • M – number of subquantizers

  • nbits – number of bit per subvector index

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

N/A.

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 reconstruct(idx_t key, float *recons) const override

Reconstruct a stored vector (or an approximation if lossy coding)

this function may not be defined for some indexes

Parameters
  • key – id of the vector to reconstruct

  • recons – reconstucted vector (size d)

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

N/A.

Public Members

LocalSearchQuantizer lsq

The residual quantizer used to encode the vectors.

AdditiveQuantizer *aq
std::vector<float> centroid_norms

norms of centroids, useful for knn-search

struct ResidualCoarseQuantizer : public faiss::AdditiveCoarseQuantizer
#include <IndexAdditiveQuantizer.h>

The ResidualCoarseQuantizer is a bit specialized compared to the default AdditiveCoarseQuantizer because it can use a beam search at search time (slow but may be useful for very large vocabularies)

Public Functions

void set_beam_factor(float new_beam_factor)

computes centroid norms if required

ResidualCoarseQuantizer(int d, size_t M, size_t nbits, MetricType metric = METRIC_L2)

Constructor.

Parameters
  • d – dimensionality of the input vectors

  • M – number of subquantizers

  • nbits – number of bit per subvector index

  • d – dimensionality of the input vectors

  • M – number of subquantizers

  • nbits – number of bit per subvector index

ResidualCoarseQuantizer(int d, const std::vector<size_t> &nbits, MetricType metric = METRIC_L2)
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

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

N/A.

virtual void reconstruct(idx_t key, float *recons) const override

Reconstruct a stored vector (or an approximation if lossy coding)

this function may not be defined for some indexes

Parameters
  • key – id of the vector to reconstruct

  • recons – reconstucted vector (size d)

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

N/A.

Public Members

ResidualQuantizer rq

The residual quantizer used to encode the vectors.

float beam_factor

factor between the beam size and the search k if negative, use exact search-to-centroid

AdditiveQuantizer *aq
std::vector<float> centroid_norms

norms of centroids, useful for knn-search