{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import scipy as sp\n",
    "import simsimd as simd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "simsimd_f = simd.cosine\n",
    "conventional_f = sp.spatial.distance.cosine"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "count = 1000 # Common number of documents in a batch\n",
    "ndim = 1536 # OpenAI Ada v2 embeddings API returns 1536-dim vectors\n",
    "A = np.random.randn(count, ndim).astype(np.float32)\n",
    "B = np.random.randn(count, ndim).astype(np.float32)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "16.3 ms ± 3.84 ms per loop (mean ± std. dev. of 10 runs, 1 loop each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit -n 1 -r 10\n",
    "result_np = [conventional_f(A[i], B[i]) for i in range(count)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "437 µs ± 15.6 µs per loop (mean ± std. dev. of 10 runs, 1 loop each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit -n 1 -r 10\n",
    "result_simd = simsimd_f(A, B)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "A = np.random.randn(count, ndim).astype(np.float16)\n",
    "B = np.random.randn(count, ndim).astype(np.float16)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "36.7 ms ± 843 µs per loop (mean ± std. dev. of 10 runs, 1 loop each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit -n 1 -r 10\n",
    "result_np = [conventional_f(A[i], B[i]) for i in range(count)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "437 µs ± 7.61 µs per loop (mean ± std. dev. of 10 runs, 1 loop each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit -n 1 -r 10\n",
    "result_simd = simsimd_f(A, B)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "A = np.random.randint(-100, 100, (count, ndim), np.int8)\n",
    "B = np.random.randint(-100, 100, (count, ndim), np.int8)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "12.4 ms ± 493 µs per loop (mean ± std. dev. of 10 runs, 1 loop each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit -n 1 -r 10\n",
    "result_np = [conventional_f(A[i], B[i]) for i in range(count)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "63.6 µs ± 3.27 µs per loop (mean ± std. dev. of 10 runs, 1 loop each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit -n 1 -r 10\n",
    "result_simd = simsimd_f(A, B)"
   ]
  }
 ],
 "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
}