File IndexIVF.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 IVFSearchParameters = SearchParametersIVF¶
Variables
- FAISS_API bool check_compatible_for_merge_expensive_check
- FAISS_API IndexIVFStats indexIVF_stats
-
struct Level1Quantizer¶
- #include <IndexIVF.h>
Encapsulates a quantizer object for the IndexIVF
The class isolates the fields that are independent of the storage of the lists (especially training)
Subclassed by faiss::IndexIVF
Public Functions
-
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.
-
size_t coarse_code_size() const¶
compute the number of bytes required to store list ids
-
Level1Quantizer()¶
-
~Level1Quantizer()¶
Public Members
-
size_t nlist = 0¶
number of inverted lists
-
char quantizer_trains_alone = 0¶
= 0: use the quantizer as index in a kmeans training = 1: just pass on the training set to the train() of the quantizer = 2: kmeans training on a flat index + add the centroids to the quantizer
-
bool own_fields = false¶
whether object owns the quantizer
-
ClusteringParameters cp¶
to override default clustering params
-
void train_q1(size_t n, const float *x, bool verbose, MetricType metric_type)¶
-
struct SearchParametersIVF : public faiss::SearchParameters¶
Subclassed by faiss::IVFPQSearchParameters
Public Functions
-
inline virtual ~SearchParametersIVF()¶
Public Members
-
size_t nprobe = 1¶
number of probes at query time
-
size_t max_codes = 0¶
max nb of codes to visit to do a query
-
SearchParameters *quantizer_params = nullptr¶
-
inline virtual ~SearchParametersIVF()¶
-
struct IndexIVF : public faiss::Index, public faiss::Level1Quantizer¶
- #include <IndexIVF.h>
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.
Subclassed by faiss::IndexIVFAdditiveQuantizer, faiss::IndexIVFFastScan, faiss::IndexIVFFlat, faiss::IndexIVFPQ, faiss::IndexIVFScalarQuantizer, faiss::IndexIVFSpectralHash
Public Functions
-
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.
-
virtual void reset() override¶
removes all elements from the database.
-
virtual void train(idx_t n, const float *x) override¶
Trains the quantizer and calls train_residual to train sub-quantizers.
-
virtual void add_with_ids(idx_t n, const float *x, const idx_t *xids) override¶
default implementation that calls encode_vectors
-
virtual void add_core(idx_t n, const float *x, const idx_t *xids, const idx_t *precomputed_idx)¶
Implementation of vector addition where the vector assignments are predefined. The default implementation hands over the code extraction to encode_vectors.
- Parameters:
precomputed_idx – quantization indices for the input vectors (size n)
-
virtual void encode_vectors(idx_t n, const float *x, const idx_t *list_nos, uint8_t *codes, bool include_listno = false) const = 0¶
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
include_listno – include the list ids in the code (in this case add ceil(log8(nlist)) to the code size)
-
void add_sa_codes(idx_t n, const uint8_t *codes, const idx_t *xids)¶
Add vectors that are computed with the standalone codec
- Parameters:
codes – codes to add size n * sa_code_size()
xids – corresponding ids, size n
-
virtual void train_residual(idx_t n, const float *x)¶
Sub-classes that encode the residuals can train their encoders here does nothing by default
-
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, IndexIVFStats *stats = nullptr) const¶
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
stats – search stats to be updated (can be null)
-
virtual void search(idx_t n, const float *x, idx_t k, float *distances, idx_t *labels, const SearchParameters *params = nullptr) const override¶
assign the vectors, then call search_preassign
-
virtual void range_search(idx_t n, const float *x, float radius, RangeSearchResult *result, const SearchParameters *params = nullptr) const override¶
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
-
void range_search_preassigned(idx_t nx, const float *x, float radius, const idx_t *keys, const float *coarse_dis, RangeSearchResult *result, bool store_pairs = false, const IVFSearchParameters *params = nullptr, IndexIVFStats *stats = nullptr) const¶
-
virtual InvertedListScanner *get_InvertedListScanner(bool store_pairs = false, const IDSelector *sel = nullptr) const¶
Get a scanner for this index (store_pairs means ignore labels)
The default search implementation uses this to compute the distances
-
virtual void reconstruct(idx_t key, float *recons) const override¶
reconstruct a vector. Works only if maintain_direct_map is set to 1 or 2
-
virtual void update_vectors(int nv, const idx_t *idx, const float *v)¶
Update a subset of vectors.
The index must have a direct_map
- Parameters:
nv – nb of vectors to update
idx – vector indices to update, size nv
v – vectors of new values, size nv*d
-
virtual void reconstruct_n(idx_t i0, idx_t ni, float *recons) const override¶
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
-
virtual void search_and_reconstruct(idx_t n, const float *x, idx_t k, float *distances, idx_t *labels, float *recons, const SearchParameters *params = nullptr) const override¶
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)
-
virtual void reconstruct_from_offset(int64_t list_no, int64_t offset, float *recons) const¶
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.
-
virtual size_t remove_ids(const IDSelector &sel) override¶
Dataset manipulation functions.
-
virtual void check_compatible_for_merge(const Index &otherIndex) const override¶
check that the two indexes are compatible (ie, they are trained in the same way and have the same parameters). Otherwise throw.
-
virtual void merge_from(Index &otherIndex, idx_t add_id) override¶
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)
-
virtual CodePacker *get_CodePacker() const¶
-
virtual void copy_subset_to(IndexIVF &other, InvertedLists::subset_type_t subset_type, idx_t a1, idx_t a2) const¶
copy a subset of the entries index to the other index see Invlists::copy_subset_to for the meaning of subset_type
-
~IndexIVF() override¶
-
inline size_t get_list_size(size_t list_no) const¶
-
bool check_ids_sorted() const¶
are the ids sorted?
-
void make_direct_map(bool new_maintain_direct_map = true)¶
initialize a direct map
- Parameters:
new_maintain_direct_map – if true, create a direct map, else clear it
-
void replace_invlists(InvertedLists *il, bool own = false)¶
replace the inverted lists, old one is deallocated if own_invlists
-
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()
-
IndexIVF()¶
-
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.
-
size_t coarse_code_size() const¶
compute the number of bytes required to store list ids
Public Members
-
InvertedLists *invlists = nullptr¶
Access to the actual data.
-
bool own_invlists = false¶
-
size_t code_size = 0¶
code size per vector in bytes
-
size_t nprobe = 1¶
number of probes at query time
-
size_t max_codes = 0¶
max nb of codes to visit to do a query
-
int parallel_mode = 0¶
Parallel mode determines how queries are parallelized with OpenMP
0 (default): split over queries 1: parallelize over inverted lists 2: parallelize over both 3: split over queries with a finer granularity
PARALLEL_MODE_NO_HEAP_INIT: binary or with the previous to prevent the heap to be initialized and finalized
-
const int PARALLEL_MODE_NO_HEAP_INIT = 1024¶
-
DirectMap direct_map¶
optional map that maps back ids to invlist entries. This enables reconstruct()
-
size_t nlist = 0¶
number of inverted lists
-
char quantizer_trains_alone = 0¶
= 0: use the quantizer as index in a kmeans training = 1: just pass on the training set to the train() of the quantizer = 2: kmeans training on a flat index + add the centroids to the quantizer
-
bool own_fields = false¶
whether object owns the quantizer
-
ClusteringParameters cp¶
to override default clustering params
-
IndexIVF(Index *quantizer, size_t d, size_t nlist, size_t code_size, MetricType metric = METRIC_L2)¶
-
struct InvertedListScanner¶
- #include <IndexIVF.h>
Object that handles a query. The inverted lists to scan are provided externally. The object has a lot of state, but distance_to_code and scan_codes can be called in multiple threads
Public Functions
-
inline InvertedListScanner(bool store_pairs = false, const IDSelector *sel = nullptr)¶
-
virtual void set_query(const float *query_vector) = 0¶
from now on we handle this query.
-
virtual void set_list(idx_t list_no, float coarse_dis) = 0¶
following codes come from this inverted list
-
virtual float distance_to_code(const uint8_t *code) const = 0¶
compute a single query-to-code distance
-
virtual size_t scan_codes(size_t n, const uint8_t *codes, const idx_t *ids, float *distances, idx_t *labels, size_t k) const¶
scan a set of codes, compute distances to current query and update heap of results if necessary. Default implemetation calls distance_to_code.
- Parameters:
n – number of codes to scan
codes – codes to scan (n * code_size)
ids – corresponding ids (ignored if store_pairs)
distances – heap distances (size k)
labels – heap labels (size k)
k – heap size
- Returns:
number of heap updates performed
-
virtual size_t iterate_codes(InvertedListsIterator *iterator, float *distances, idx_t *labels, size_t k, size_t &list_size) const¶
-
virtual void scan_codes_range(size_t n, const uint8_t *codes, const idx_t *ids, float radius, RangeQueryResult &result) const¶
scan a set of codes, compute distances to current query and update results if distances are below radius
(default implementation fails)
-
virtual void iterate_codes_range(InvertedListsIterator *iterator, float radius, RangeQueryResult &result, size_t &list_size) const¶
-
inline virtual ~InvertedListScanner()¶
-
inline InvertedListScanner(bool store_pairs = false, const IDSelector *sel = nullptr)¶
-
struct IndexIVFStats¶
-
using IVFSearchParameters = SearchParametersIVF¶