{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "b60885fa-9b72-494f-80ca-976b0ab2d897",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd \n",
    "\n",
    "pd.set_option('display.max_colwidth', 100)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "3d42b739-8c64-46e2-b0d6-cb8a4fe05e08",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(8, 2)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv('sample_text.csv')\n",
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "c26485ef-4276-4c77-bae3-292b065d0ba5",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/homebrew/anaconda3/lib/python3.11/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "(8, 768)"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sentence_transformers import SentenceTransformer\n",
    "\n",
    "encoder = SentenceTransformer(\"all-mpnet-base-v2\")\n",
    "vectors = encoder.encode(df.text)\n",
    "vectors.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "4f1d88ea-bdb1-4066-94c6-b4d0e6eee442",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "768"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dim = vectors.shape[1]\n",
    "dim"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "d9dd2469-59b1-4c28-882f-790685abcb3a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<faiss.swigfaiss.IndexFlatL2; proxy of <Swig Object of type 'faiss::IndexFlatL2 *' at 0x30b242580> >"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import faiss\n",
    "\n",
    "# index that uses L2 distance to do faster search later on \n",
    "index = faiss.IndexFlatL2() \n",
    "\n",
    "index = faiss.IndexFlatL2(dim)\n",
    "\n",
    "index\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "e43fe842-0b3b-41e7-b562-a8371bafcd40",
   "metadata": {},
   "outputs": [],
   "source": [
    "index.add(vectors)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "eb8ca9ac-4bbb-47f8-b99b-46fc8a6831f2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(768,)"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "search_query=\"finance\" \n",
    "\n",
    "vec = encoder.encode(search_query)\n",
    "vec.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "99e18af2-0958-4d94-bc94-77812031fcf4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1, 768)"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import numpy as np \n",
    "svec = np.array(vec).reshape(1, -1)\n",
    "svec.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "c8d0671e-81d9-4cd3-bbe9-3809b8dc366c",
   "metadata": {},
   "outputs": [],
   "source": [
    "distances, I = index.search(svec, k=2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "ac60d14e-3e3e-4c7c-b548-d739859a6fe8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[5, 2]])"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "I"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "7e3cd9f0-f7b8-4d36-88ba-afe2d293c31b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>text</th>\n",
       "      <th>category</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Navaratri dandiya program at Expo center in Mumbai this october</td>\n",
       "      <td>Event</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>These are the latest fashion trends for this week</td>\n",
       "      <td>Fashion</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                              text category\n",
       "5  Navaratri dandiya program at Expo center in Mumbai this october    Event\n",
       "2                These are the latest fashion trends for this week  Fashion"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.loc[I[0]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "e387b515-7213-4116-97ae-3c4bbcb4a846",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>text</th>\n",
       "      <th>category</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Meditation and yoga can improve mental health</td>\n",
       "      <td>Health</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Fruits, whole grains and vegetables helps control blood pressure</td>\n",
       "      <td>Health</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>These are the latest fashion trends for this week</td>\n",
       "      <td>Fashion</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Vibrant color jeans for male are becoming a trend</td>\n",
       "      <td>Fashion</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>The concert starts at 7 PM tonight</td>\n",
       "      <td>Event</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Navaratri dandiya program at Expo center in Mumbai this october</td>\n",
       "      <td>Event</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Exciting vacation destinations for your next trip</td>\n",
       "      <td>Travel</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Maldives and Srilanka are gaining popularity in terms of low budget vacation places</td>\n",
       "      <td>Travel</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                                                  text  \\\n",
       "0                                        Meditation and yoga can improve mental health   \n",
       "1                     Fruits, whole grains and vegetables helps control blood pressure   \n",
       "2                                    These are the latest fashion trends for this week   \n",
       "3                                    Vibrant color jeans for male are becoming a trend   \n",
       "4                                                   The concert starts at 7 PM tonight   \n",
       "5                      Navaratri dandiya program at Expo center in Mumbai this october   \n",
       "6                                    Exciting vacation destinations for your next trip   \n",
       "7  Maldives and Srilanka are gaining popularity in terms of low budget vacation places   \n",
       "\n",
       "  category  \n",
       "0   Health  \n",
       "1   Health  \n",
       "2  Fashion  \n",
       "3  Fashion  \n",
       "4    Event  \n",
       "5    Event  \n",
       "6   Travel  \n",
       "7   Travel  "
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.11.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}