faiss 0.2.3 → 0.2.5

data/vendor/faiss/faiss/Index.h

@@ -18,7 +18,7 @@
 
 #define FAISS_VERSION_MAJOR 1
 #define FAISS_VERSION_MINOR 7
-#define FAISS_VERSION_PATCH 1
+#define FAISS_VERSION_PATCH 3
 
 /**
  * @namespace faiss
@@ -38,11 +38,24 @@
 
 namespace faiss {
 
-/// Forward declarations see AuxIndexStructures.h
+/// Forward declarations see impl/AuxIndexStructures.h, impl/IDSelector.h and
+/// impl/DistanceComputer.h
 struct IDSelector;
 struct RangeSearchResult;
 struct DistanceComputer;
 
+/** Parent class for the optional search paramenters.
+ *
+ * Sub-classes with additional search parameters should inherit this class.
+ * Ownership of the object fields is always to the caller.
+ */
+struct SearchParameters {
+    /// if non-null, only these IDs will be considered during search.
+    IDSelector* sel = nullptr;
+    /// make sure we can dynamic_cast this
+    virtual ~SearchParameters() {}
+};
+
 /** Abstract structure for an index, supports adding vectors and searching them.
  *
  * All vectors provided at add or search time are 32-bit float arrays,
@@ -114,7 +127,8 @@ struct Index {
             const float* x,
             idx_t k,
             float* distances,
-            idx_t* labels) const = 0;
+            idx_t* labels,
+            const SearchParameters* params = nullptr) const = 0;
 
     /** query n vectors of dimension d to the index.
      *
@@ -130,7 +144,8 @@ struct Index {
             idx_t n,
             const float* x,
             float radius,
-            RangeSearchResult* result) const;
+            RangeSearchResult* result,
+            const SearchParameters* params = nullptr) const;
 
     /** return the indexes of the k vectors closest to the query x.
      *
@@ -157,6 +172,16 @@ struct Index {
      */
     virtual void reconstruct(idx_t key, float* recons) const;
 
+    /** Reconstruct several stored vectors (or an approximation if lossy coding)
+     *
+     * this function may not be defined for some indexes
+     * @param n        number of vectors to reconstruct
+     * @param keys        ids of the vectors to reconstruct (size n)
+     * @param recons      reconstucted vector (size n * d)
+     */
+    virtual void reconstruct_batch(idx_t n, const idx_t* keys, float* recons)
+            const;
+
     /** Reconstruct vectors i0 to i0 + ni - 1
      *
      * this function may not be defined for some indexes
@@ -178,7 +203,8 @@ struct Index {
             idx_t k,
             float* distances,
             idx_t* labels,
-            float* recons) const;
+            float* recons,
+            const SearchParameters* params = nullptr) const;
 
     /** Computes a residual vector after indexing encoding.
      *
@@ -234,13 +260,24 @@ struct Index {
      */
     virtual void sa_encode(idx_t n, const float* x, uint8_t* bytes) const;
 
-    /** encode a set of vectors
+    /** decode a set of vectors
      *
      * @param n       number of vectors
      * @param bytes   input encoded vectors, size n * sa_code_size()
      * @param x       output vectors, size n * d
      */
     virtual void sa_decode(idx_t n, const uint8_t* bytes, float* x) const;
+
+    /** 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 void merge_from(Index& otherIndex, idx_t add_id = 0);
+
+    /** check that the two indexes are compatible (ie, they are
+     * trained in the same way and have the same
+     * parameters). Otherwise throw. */
+    virtual void check_compatible_for_merge(const Index& otherIndex) const;
 };
 
 } // namespace faiss

data/vendor/faiss/faiss/Index2Layer.cpp

@@ -30,16 +30,6 @@
 #include <faiss/utils/distances.h>
 #include <faiss/utils/utils.h>
 
-/*
-#include <faiss/utils/Heap.h>
-
-#include <faiss/Clustering.h>
-
-#include <faiss/utils/hamming.h>
-
-
-*/
-
 namespace faiss {
 
 /*************************************
@@ -52,7 +42,7 @@ Index2Layer::Index2Layer(
         int M,
         int nbit,
         MetricType metric)
-        : Index(quantizer->d, metric),
+        : IndexFlatCodes(0, quantizer->d, metric),
           q1(quantizer, nlist),
           pq(quantizer->d, M, nbit) {
     is_trained = false;
@@ -116,83 +106,16 @@ void Index2Layer::train(idx_t n, const float* x) {
     is_trained = true;
 }
 
-void Index2Layer::add(idx_t n, const float* x) {
-    idx_t bs = 32768;
-    if (n > bs) {
-        for (idx_t i0 = 0; i0 < n; i0 += bs) {
-            idx_t i1 = std::min(i0 + bs, n);
-            if (verbose) {
-                printf("Index2Layer::add: adding %" PRId64 ":%" PRId64
-                       " / %" PRId64 "\n",
-                       i0,
-                       i1,
-                       n);
-            }
-            add(i1 - i0, x + i0 * d);
-        }
-        return;
-    }
-
-    std::vector<idx_t> codes1(n);
-    q1.quantizer->assign(n, x, codes1.data());
-    std::vector<float> residuals(n * d);
-    for (idx_t i = 0; i < n; i++) {
-        q1.quantizer->compute_residual(
-                x + i * d, residuals.data() + i * d, codes1[i]);
-    }
-    std::vector<uint8_t> codes2(n * code_size_2);
-
-    pq.compute_codes(residuals.data(), codes2.data(), n);
-
-    codes.resize((ntotal + n) * code_size);
-    uint8_t* wp = &codes[ntotal * code_size];
-
-    {
-        int i = 0x11223344;
-        const char* ip = (char*)&i;
-        FAISS_THROW_IF_NOT_MSG(
-                ip[0] == 0x44, "works only on a little-endian CPU");
-    }
-
-    // copy to output table
-    for (idx_t i = 0; i < n; i++) {
-        memcpy(wp, &codes1[i], code_size_1);
-        wp += code_size_1;
-        memcpy(wp, &codes2[i * code_size_2], code_size_2);
-        wp += code_size_2;
-    }
-
-    ntotal += n;
-}
-
 void Index2Layer::search(
         idx_t /*n*/,
         const float* /*x*/,
         idx_t /*k*/,
         float* /*distances*/,
-        idx_t* /*labels*/) const {
+        idx_t* /*labels*/,
+        const SearchParameters* /* params */) const {
     FAISS_THROW_MSG("not implemented");
 }
 
-void Index2Layer::reconstruct_n(idx_t i0, idx_t ni, float* recons) const {
-    std::vector<float> recons1(d);
-    FAISS_THROW_IF_NOT(i0 >= 0 && i0 + ni <= ntotal);
-    const uint8_t* rp = &codes[i0 * code_size];
-
-    for (idx_t i = 0; i < ni; i++) {
-        idx_t key = 0;
-        memcpy(&key, rp, code_size_1);
-        q1.quantizer->reconstruct(key, recons1.data());
-        rp += code_size_1;
-        pq.decode(rp, recons);
-        for (idx_t j = 0; j < d; j++) {
-            recons[j] += recons1[j];
-        }
-        rp += code_size_2;
-        recons += d;
-    }
-}
-
 void Index2Layer::transfer_to_IVFPQ(IndexIVFPQ& other) const {
     FAISS_THROW_IF_NOT(other.nlist == q1.nlist);
     FAISS_THROW_IF_NOT(other.code_size == code_size_2);
@@ -211,15 +134,6 @@ void Index2Layer::transfer_to_IVFPQ(IndexIVFPQ& other) const {
     other.ntotal = ntotal;
 }
 
-void Index2Layer::reconstruct(idx_t key, float* recons) const {
-    reconstruct_n(key, 1, recons);
-}
-
-void Index2Layer::reset() {
-    ntotal = 0;
-    codes.clear();
-}
-
 namespace {
 
 struct Distance2Level : DistanceComputer {
@@ -259,7 +173,7 @@ struct DistanceXPQ4 : Distance2Level {
 
         FAISS_ASSERT(quantizer);
         M = storage.pq.M;
-        pq_l1_tab = quantizer->xb.data();
+        pq_l1_tab = quantizer->get_xb();
     }
 
     float operator()(idx_t i) override {
@@ -368,12 +282,29 @@ DistanceComputer* Index2Layer::get_distance_computer() const {
 }
 
 /* The standalone codec interface */
-size_t Index2Layer::sa_code_size() const {
-    return code_size;
-}
+
+// block size used in Index2Layer::sa_encode
+int index2layer_sa_encode_bs = 32768;
 
 void Index2Layer::sa_encode(idx_t n, const float* x, uint8_t* bytes) const {
     FAISS_THROW_IF_NOT(is_trained);
+
+    idx_t bs = index2layer_sa_encode_bs;
+    if (n > bs) {
+        for (idx_t i0 = 0; i0 < n; i0 += bs) {
+            idx_t i1 = std::min(i0 + bs, n);
+            if (verbose) {
+                printf("Index2Layer::add: adding %" PRId64 ":%" PRId64
+                       " / %" PRId64 "\n",
+                       i0,
+                       i1,
+                       n);
+            }
+            sa_encode(i1 - i0, x + i0 * d, bytes + i0 * code_size);
+        }
+        return;
+    }
+
     std::unique_ptr<int64_t[]> list_nos(new int64_t[n]);
     q1.quantizer->assign(n, x, list_nos.get());
     std::vector<float> residuals(n * d);

data/vendor/faiss/faiss/Index2Layer.h

@@ -11,8 +11,10 @@
 
 #include <vector>
 
+#include <faiss/IndexFlatCodes.h>
 #include <faiss/IndexIVF.h>
 #include <faiss/IndexPQ.h>
+#include <faiss/impl/platform_macros.h>
 
 namespace faiss {
 
@@ -24,25 +26,19 @@ struct IndexIVFPQ;
  * The class is mainly inteded to store encoded vectors that can be
  * accessed randomly, the search function is not implemented.
  */
-struct Index2Layer : Index {
+struct Index2Layer : IndexFlatCodes {
     /// first level quantizer
     Level1Quantizer q1;
 
     /// second level quantizer is always a PQ
     ProductQuantizer pq;
 
-    /// Codes. Size ntotal * code_size.
-    std::vector<uint8_t> codes;
-
     /// size of the code for the first level (ceil(log8(q1.nlist)))
     size_t code_size_1;
 
     /// size of the code for the second level
     size_t code_size_2;
 
-    /// code_size_1 + code_size_2
-    size_t code_size;
-
     Index2Layer(
             Index* quantizer,
             size_t nlist,
@@ -55,21 +51,14 @@ struct Index2Layer : Index {
 
     void train(idx_t n, const float* x) override;
 
-    void add(idx_t n, const float* x) override;
-
     /// not implemented
     void search(
             idx_t n,
             const float* x,
             idx_t k,
             float* distances,
-            idx_t* labels) const override;
-
-    void reconstruct_n(idx_t i0, idx_t ni, float* recons) const override;
-
-    void reconstruct(idx_t key, float* recons) const override;
-
-    void reset() override;
+            idx_t* labels,
+            const SearchParameters* params = nullptr) const override;
 
     DistanceComputer* get_distance_computer() const override;
 
@@ -77,9 +66,11 @@ struct Index2Layer : Index {
     void transfer_to_IVFPQ(IndexIVFPQ& other) const;
 
     /* The standalone codec interface */
-    size_t sa_code_size() const override;
     void sa_encode(idx_t n, const float* x, uint8_t* bytes) const override;
     void sa_decode(idx_t n, const uint8_t* bytes, float* x) const override;
 };
 
+// block size used in Index2Layer::sa_encode
+FAISS_API extern int index2layer_sa_encode_bs;
+
 } // namespace faiss