File IndexNNDescent.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 IndexNNDescent : public faiss::Index¶
- #include <IndexNNDescent.h>
The NNDescent index is a normal random-access index with an NNDescent link structure built on top
Subclassed by faiss::IndexNNDescentFlat
Public Types
-
using storage_idx_t = NNDescent::storage_idx_t¶
Public Functions
-
explicit IndexNNDescent(int d = 0, int K = 32, MetricType metric = METRIC_L2)¶
-
~IndexNNDescent() override¶
-
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 SearchParameters *params = nullptr) const override¶
entry point for search
-
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 reset() override¶
removes all elements from the database.
-
using storage_idx_t = NNDescent::storage_idx_t¶
-
struct IndexNNDescentFlat : public faiss::IndexNNDescent¶
- #include <IndexNNDescent.h>
Flat index topped with with a NNDescent structure to access elements more efficiently.
Public Types
-
using storage_idx_t = NNDescent::storage_idx_t¶
Public Functions
-
IndexNNDescentFlat()¶
-
IndexNNDescentFlat(int d, int K, MetricType metric = METRIC_L2)¶
-
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 SearchParameters *params = nullptr) const override¶
entry point for search
-
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 reset() override¶
removes all elements from the database.
-
using storage_idx_t = NNDescent::storage_idx_t¶
-
struct IndexNNDescent : public faiss::Index¶