usearch 2.0.1

Smaller & Faster Single-File Vector Search Engine from Unum
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from usearch.io import load_matrix\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "vectors = load_matrix(\"datasets/arxiv_2M/abstract.e5-base-v2.fbin\", view=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "vectors.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from usearch.index import Index, USES_SIMSIMD, USES_NATIVE_F16\n",
    "\n",
    "index = Index(ndim=vectors.shape[1], metric=\"cos\", dtype=\"i8\")\n",
    "index.hardware_acceleration, USES_SIMSIMD, USES_NATIVE_F16"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "import os\n",
    "\n",
    "if os.path.exists(\"cluster.i8.usearch\"):\n",
    "    index.load(\"cluster.i8.usearch\")\n",
    "\n",
    "if len(index) == 0:\n",
    "    index.add(None, vectors, log=True)\n",
    "    index.save(\"cluster.i8.usearch\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "clustering = index.cluster(min_count=10, max_count=15, threads=60)\n",
    "clustering"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(f\"{len(clustering.centroids_popularity[0])} unique clusters for {len(index)} members\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "clustering.plot_centroids_popularity()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "nx.draw_networkx(g)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import networkx as nx\n",
    "\n",
    "G = g\n",
    "\n",
    "node_sizes = nx.get_node_attributes(G, \"size\").values()\n",
    "max_node_size = max(node_sizes)\n",
    "node_sizes = [size * 10 / max_node_size for size in node_sizes]\n",
    "\n",
    "edge_labels = nx.get_edge_attributes(G, \"distance\")\n",
    "edge_labels = {edge: f\"{label:.2}\" for edge, label in edge_labels.items()}\n",
    "\n",
    "pos = nx.spring_layout(G, seed=7)\n",
    "nx.draw_networkx_nodes(G, pos, node_size=node_sizes)\n",
    "nx.draw_networkx_edges(G, pos, edgelist=G.edges(data=False))\n",
    "nx.draw_networkx_labels(G, pos, font_size=10, font_family=\"sans-serif\")\n",
    "nx.draw_networkx_edge_labels(G, pos, edge_labels, font_size=5)\n",
    "\n",
    "ax = plt.gca()\n",
    "ax.margins(0.08)\n",
    "plt.axis(\"off\")\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.11"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}