#include <IndexIVF.h>

Inheritance diagram for faiss::IndexIVF:

Public Member Functions
	IndexIVF (Index *quantizer, size_t d, size_t nlist, size_t code_size, MetricType metric=METRIC_L2)

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

void	train (idx_t n, const float *x) override
	Trains the quantizer and calls train_residual to train sub-quantizers.

void	add (idx_t n, const float *x) override
	Calls add_with_ids with NULL ids.

void	add_with_ids (idx_t n, const float x, const idx_t xids) override
	default implementation that calls encode_vectors

virtual void	encode_vectors (idx_t n, const float x, const idx_t list_nos, uint8_t *codes) const =0

virtual void	train_residual (idx_t n, const float *x)

virtual void	search_preassigned (idx_t n, const float x, idx_t k, const idx_t assign, const float centroid_dis, float distances, idx_t labels, bool store_pairs, const IVFSearchParameters params=nullptr) const

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

void	range_search (idx_t n, const float x, float radius, RangeSearchResult result) const override

void	range_search_preassigned (idx_t nx, const float x, float radius, const idx_t keys, const float coarse_dis, RangeSearchResult result) const

virtual InvertedListScanner *	get_InvertedListScanner (bool store_pairs=false) const
	get a scanner for this index (store_pairs means ignore labels)

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

void	reconstruct_n (idx_t i0, idx_t ni, float *recons) const override

void	search_and_reconstruct (idx_t n, const float x, idx_t k, float distances, idx_t labels, float recons) const override

virtual void	reconstruct_from_offset (idx_t list_no, idx_t offset, float *recons) const

idx_t	remove_ids (const IDSelector &sel) override
	Dataset manipulation functions.

void	check_compatible_for_merge (const IndexIVF &other) const

virtual void	merge_from (IndexIVF &other, idx_t add_id)

virtual void	copy_subset_to (IndexIVF &other, int subset_type, idx_t a1, idx_t a2) const

size_t	get_list_size (size_t list_no) const

void	make_direct_map (bool new_maintain_direct_map=true)

void	replace_invlists (InvertedLists *il, bool own=false)
	replace the inverted lists, old one is deallocated if own_invlists

Public Member Functions inherited from faiss::Index
	Index (idx_t d=0, MetricType metric=METRIC_L2)

void	assign (idx_t n, const float x, idx_t labels, idx_t k=1)

void	compute_residual (const float x, float residual, idx_t key) const

void	display () const

Public Member Functions inherited from faiss::Level1Quantizer
void	train_q1 (size_t n, const float *x, bool verbose, MetricType metric_type)
	Trains the quantizer and calls train_residual to train sub-quantizers.

	Level1Quantizer (Index *quantizer, size_t nlist)

Public Attributes
InvertedLists *	invlists
	Acess to the actual data.

bool	own_invlists

size_t	code_size
	code size per vector in bytes

size_t	nprobe
	number of probes at query time

size_t	max_codes
	max nb of codes to visit to do a query

int	parallel_mode

bool	maintain_direct_map
	map for direct access to the elements. Enables reconstruct().

std::vector< idx_t >	direct_map

Public Attributes inherited from faiss::Index
int	d
	vector dimension

idx_t	ntotal
	total nb of indexed vectors

bool	verbose
	verbosity level

bool	is_trained
	set if the Index does not require training, or if training is done already

MetricType	metric_type
	type of metric this index uses for search

Public Attributes inherited from faiss::Level1Quantizer
Index *	quantizer
	quantizer that maps vectors to inverted lists

size_t	nlist
	number of possible key values

char	quantizer_trains_alone

bool	own_fields
	whether object owns the quantizer

ClusteringParameters	cp
	to override default clustering params

Index *	clustering_index
	to override index used during clustering

Additional Inherited Members
Public Types inherited from faiss::Index
using	idx_t = long
	all indices are this type

using	component_t = float

using	distance_t = float

Detailed Description

Index based on a inverted file (IVF)

In the inverted file, the quantizer (an Index instance) provides a quantization index for each vector to be added. The quantization index maps to a list (aka inverted list or posting list), where the id of the vector is stored.

The inverted list object is required only after trainng. If none is set externally, an ArrayInvertedLists is used automatically.

At search time, the vector to be searched is also quantized, and only the list corresponding to the quantization index is searched. This speeds up the search by making it non-exhaustive. This can be relaxed using multi-probe search: a few (nprobe) quantization indices are selected and several inverted lists are visited.

Sub-classes implement a post-filtering of the index that refines the distance estimation from the query to databse vectors.

Definition at line 90 of file IndexIVF.h.

Constructor & Destructor Documentation

faiss::IndexIVF::IndexIVF	(	Index *	quantizer,
		size_t	d,
		size_t	nlist,
		size_t	code_size,
		MetricType	metric = `METRIC_L2`
	)

The Inverted file takes a quantizer (an Index) on input, which implements the function mapping a vector to a list identifier. The pointer is borrowed: the quantizer should not be deleted while the IndexIVF is in use.

Definition at line 114 of file IndexIVF.cpp.

Member Function Documentation

void faiss::IndexIVF::check_compatible_for_merge ( const IndexIVF & other ) const

check that the two indexes are compatible (ie, they are trained in the same way and have the same parameters). Otherwise throw.

Definition at line 710 of file IndexIVF.cpp.

void faiss::IndexIVF::copy_subset_to	(	IndexIVF &	other,
		int	subset_type,
		idx_t	a1,
		idx_t	a2
	)		const

virtual

copy a subset of the entries index to the other index

if subset_type == 0: copies ids in [a1, a2) if subset_type == 1: copies ids if id % a1 == a2 if subset_type == 2: copies inverted lists such that a1 elements are left before and a2 elements are after

Definition at line 748 of file IndexIVF.cpp.

virtual void faiss::IndexIVF::encode_vectors	(	idx_t	n,
		const float *	x,
		const idx_t *	list_nos,
		uint8_t *	codes
	)		const

pure virtual

Encodes a set of vectors as they would appear in the inverted lists

Parameters

list_nos	inverted list ids as returned by the quantizer (size n). -1s are ignored.
codes	output codes, size n * code_size

Implemented in faiss::IndexIVFScalarQuantizer, faiss::IndexIVFPQ, faiss::IndexIVFSpectralHash, and faiss::IndexIVFFlat.

void faiss::IndexIVF::make_direct_map ( bool new_maintain_direct_map = true )

intialize a direct map

Parameters

new_maintain_direct_map if true, create a direct map, else clear it

Definition at line 202 of file IndexIVF.cpp.

void faiss::IndexIVF::merge_from	(	IndexIVF &	other,
		idx_t	add_id
	)

virtual

moves the entries from another dataset to self. On output, other is empty. add_id is added to all moved ids (for sequential ids, this would be this->ntotal

Reimplemented in faiss::IndexIVFPQR.

Definition at line 721 of file IndexIVF.cpp.

void faiss::IndexIVF::range_search	(	idx_t	n,
		const float *	x,
		float	radius,
		RangeSearchResult *	result
	)		const

overridevirtual

query n vectors of dimension d to the index.

return all vectors with distance < radius. Note that many indexes do not implement the range_search (only the k-NN search is mandatory).

Parameters

x	input vectors to search, size n * d
radius	search radius
result	result table

Reimplemented from faiss::Index.

Reimplemented in faiss::IndexIVFFlatDedup.

Definition at line 434 of file IndexIVF.cpp.

void faiss::IndexIVF::reconstruct	(	idx_t	key,
		float *	recons
	)		const

overridevirtual

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)

Reimplemented from faiss::Index.

Definition at line 562 of file IndexIVF.cpp.

void faiss::IndexIVF::reconstruct_from_offset	(	idx_t	list_no,
		idx_t	offset,
		float *	recons
	)		const

virtual

Reconstruct a vector given the location in terms of (inv list index + inv list offset) instead of the id.

Useful for reconstructing when the direct_map is not maintained and the inv list offset is computed by search_preassigned() with store_pairs set.

Reimplemented in faiss::IndexIVFPQR, faiss::IndexIVFScalarQuantizer, faiss::IndexIVFFlatDedup, faiss::IndexIVFPQ, and faiss::IndexIVFFlat.

Definition at line 633 of file IndexIVF.cpp.

void faiss::IndexIVF::reconstruct_n	(	idx_t	i0,
		idx_t	ni,
		float *	recons
	)		const

overridevirtual

Reconstruct a subset of the indexed vectors.

Overrides default implementation to bypass reconstruct() which requires direct_map to be maintained.

Parameters

i0	first vector to reconstruct
ni	nb of vectors to reconstruct
recons	output array of reconstructed vectors, size ni * d

Reimplemented from faiss::Index.

Definition at line 574 of file IndexIVF.cpp.

void faiss::IndexIVF::search	(	idx_t	n,
		const float *	x,
		idx_t	k,
		float *	distances,
		idx_t *	labels
	)		const

overridevirtual

assign the vectors, then call search_preassign

Implements faiss::Index.

Definition at line 228 of file IndexIVF.cpp.

void faiss::IndexIVF::search_and_reconstruct	(	idx_t	n,
		const float *	x,
		idx_t	k,
		float *	distances,
		idx_t *	labels,
		float *	recons
	)		const

overridevirtual

Similar to search, but also reconstructs the stored vectors (or an approximation in the case of lossy coding) for the search results.

Overrides default implementation to avoid having to maintain direct_map and instead fetch the code offsets through the store_pairs flag in search_preassigned().

Parameters

recons reconstructed vectors size (n, k, d)

Reimplemented from faiss::Index.

Definition at line 595 of file IndexIVF.cpp.

void faiss::IndexIVF::search_preassigned	(	idx_t	n,
		const float *	x,
		idx_t	k,
		const idx_t *	assign,
		const float *	centroid_dis,
		float *	distances,
		idx_t *	labels,
		bool	store_pairs,
		const IVFSearchParameters *	params = `nullptr`
	)		const

virtual

search a set of vectors, that are pre-quantized by the IVF quantizer. Fill in the corresponding heaps with the query results. The default implementation uses InvertedListScanners to do the search.

Parameters

n	nb of vectors to query
x	query vectors, size nx * d
assign	coarse quantization indices, size nx * nprobe
centroid_dis	distances to coarse centroids, size nx * nprobe
distance	output distances, size n * k
labels	output labels, size n * k
store_pairs	store inv list index + inv list offset instead in upper/lower 32 bit of result, instead of ids (used for reranking).
params	used to override the object's search parameters

Reimplemented in faiss::IndexIVFPQR, and faiss::IndexIVFFlatDedup.

Definition at line 250 of file IndexIVF.cpp.

void faiss::IndexIVF::train_residual	(	idx_t	n,
		const float *	x
	)

virtual

Sub-classes that encode the residuals can train their encoders here does nothing by default

Reimplemented in faiss::IndexIVFPQR, faiss::IndexIVFScalarQuantizer, faiss::IndexIVFPQ, and faiss::IndexIVFSpectralHash.

Definition at line 703 of file IndexIVF.cpp.

Member Data Documentation

int faiss::IndexIVF::parallel_mode

Parallel mode determines how queries are parallelized with OpenMP

0 (default): parallelize over queries 1: parallelize over over inverted lists 2: parallelize over both

Definition at line 106 of file IndexIVF.h.

The documentation for this struct was generated from the following files:

/data/users/hoss/faiss/IndexIVF.h
/data/users/hoss/faiss/IndexIVF.cpp

Public Member Functions

Public Attributes

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

Member Function Documentation

Member Data Documentation