Download BuyLibs ANN (Approximate Nearest Neighbors with bindings to Annoy for Delphi x64) v1.17.3.8

• AnnoyIndex(f, metric) returns a new index that's read-write and stores vector of f dimensions. Metric can be "angular", "euclidean", "manhattan", "hamming", or "dot".
• a.add_item(i, v) adds item i (any nonnegative integer) with vector v. Note that it will allocate memory for max(i)+1 items.
• a.build(n_trees, n_jobs=-1) builds a forest of n_trees trees. More trees gives higher precision when querying. After calling build, no more items can be added. n_jobs specifies the number of threads used to build the trees. n_jobs=-1 uses all available CPU cores.
• a.save(fn, prefault=False) saves the index to disk and loads it (see next function). After saving, no more items can be added.
• a.load(fn, prefault=False) loads (mmaps) an index from disk. If prefault is set to True, it will pre-read the entire file into memory (using mmap with MAP_POPULATE). Default is False.
• a.unload() unloads.
• a.get_nns_by_item(i, n, search_k=-1, include_distances=False) returns the n closest items. During the query it will inspect up to search_k nodes which defaults to n_trees * n if not provided. search_k gives you a run-time tradeoff between better accuracy and speed. If you set include_distances to True, it will return a 2 element tuple with two lists in it: the second one containing all corresponding distances.
• a.get_nns_by_vector(v, n, search_k=-1, include_distances=False) same but query by vector v.
• a.get_item_vector(i) returns the vector for item i that was previously added.
• a.get_distance(i, j) returns the distance between items i and j. NOTE: this used to return the squared distance, but has been changed as of Aug 2016.
• a.get_n_items() returns the number of items in the index.
• a.get_n_trees() returns the number of trees in the index.
• a.on_disk_build(fn) prepares annoy to build the index in the specified file instead of RAM (execute before adding items, no need to save after build)
• a.set_seed(seed) will initialize the random number generator with the given seed. Only used for building up the tree, i. e. only necessary to pass this before adding the items. Will have no effect after calling a.build(n_trees) or a.load(fn).

Notes:

• There's no bounds checking performed on the values so be careful.
• Annoy uses Euclidean distance of normalized vectors for its angular distance, which for two vectors u,v is equal to sqrt(2(1-cos(u,v)))

The C++ API is very similar: just #include "annoylib.h" to get access to it.

var
  t, u: TAnnIndexAngularSingle;
  v: TAnnVectorSingle;
  r: TAnnVectorInteger;
  i, z: Integer;
const
  f = 40; // Dimensionality of the vectors stored in the index
begin
  t.Init(f); // Initialize Annoy index with vectors of dimension f

  // Generate 1000 random vectors and add them to the index
  for i := 0 to 999 do
  begin
    v.Init();

    // Fill the vector with random values drawn from N(0,1)
    for z := 0 to f - 1 do
      v.PushBack(RandG(0, 1));

    t.AddItem(i, v); // Add the vector with item id = i
  end;

  t.Build(10); // Build the Annoy index using 10 trees.

  t.Save('test.ann'); // Persist the index to disk

  // ------------------------------------------------------------------
  // Load the index from disk into a new instance
  // ------------------------------------------------------------------

  u.Init(f); // Initialize another index object with the same dimensionality

  // Load the index. Annoy uses memory-mapping so loading is very fast
  // and does not require fully copying the data into RAM.
  u.Load('test.ann');

  r.Init(); // Prepare container for nearest neighbor results

  // Query the index:
  // Find the 1000 nearest neighbors to item with id = 0
  u.GetNnsByItem(0, 1000, r);

  // ------------------------------------------------------------------
  // Print resulting neighbor item IDs
  // ------------------------------------------------------------------
  Write('[');
  for i := 0 to r.Size - 1 do
  begin
    if i > 0 then
      Write(', ');
    Write(r[i]);
  end;
  Writeln(']');
end;