{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2b931208",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain_community.document_loaders import TextLoader\n",
    "from langchain_text_splitters import CharacterTextSplitter\n",
    "from langchain_chroma import Chroma"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "1adaad97",
   "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>isbn13</th>\n",
       "      <th>isbn10</th>\n",
       "      <th>title</th>\n",
       "      <th>authors</th>\n",
       "      <th>categories</th>\n",
       "      <th>thumbnail</th>\n",
       "      <th>description</th>\n",
       "      <th>published_year</th>\n",
       "      <th>average_rating</th>\n",
       "      <th>num_pages</th>\n",
       "      <th>ratings_count</th>\n",
       "      <th>agg_of_book</th>\n",
       "      <th>title_and_subtitle</th>\n",
       "      <th>tagged_description</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>9780002005883</td>\n",
       "      <td>0002005883</td>\n",
       "      <td>Gilead</td>\n",
       "      <td>Marilynne Robinson</td>\n",
       "      <td>Fiction</td>\n",
       "      <td>http://books.google.com/books/content?id=KQZCP...</td>\n",
       "      <td>A NOVEL THAT READERS and critics have been eag...</td>\n",
       "      <td>2004.0</td>\n",
       "      <td>3.85</td>\n",
       "      <td>247.0</td>\n",
       "      <td>361.0</td>\n",
       "      <td>21.0</td>\n",
       "      <td>Gilead</td>\n",
       "      <td>9780002005883 A NOVEL THAT READERS and critics...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>9780002261982</td>\n",
       "      <td>0002261987</td>\n",
       "      <td>Spider's Web</td>\n",
       "      <td>Charles Osborne;Agatha Christie</td>\n",
       "      <td>Detective and mystery stories</td>\n",
       "      <td>http://books.google.com/books/content?id=gA5GP...</td>\n",
       "      <td>A new 'Christie for Christmas' -- a full-lengt...</td>\n",
       "      <td>2000.0</td>\n",
       "      <td>3.83</td>\n",
       "      <td>241.0</td>\n",
       "      <td>5164.0</td>\n",
       "      <td>25.0</td>\n",
       "      <td>Spider's Web: A Novel</td>\n",
       "      <td>9780002261982 A new 'Christie for Christmas' -...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>9780006178736</td>\n",
       "      <td>0006178731</td>\n",
       "      <td>Rage of angels</td>\n",
       "      <td>Sidney Sheldon</td>\n",
       "      <td>Fiction</td>\n",
       "      <td>http://books.google.com/books/content?id=FKo2T...</td>\n",
       "      <td>A memorable, mesmerizing heroine Jennifer -- b...</td>\n",
       "      <td>1993.0</td>\n",
       "      <td>3.93</td>\n",
       "      <td>512.0</td>\n",
       "      <td>29532.0</td>\n",
       "      <td>32.0</td>\n",
       "      <td>Rage of angels</td>\n",
       "      <td>9780006178736 A memorable, mesmerizing heroine...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>9780006280897</td>\n",
       "      <td>0006280897</td>\n",
       "      <td>The Four Loves</td>\n",
       "      <td>Clive Staples Lewis</td>\n",
       "      <td>Christian life</td>\n",
       "      <td>http://books.google.com/books/content?id=XhQ5X...</td>\n",
       "      <td>Lewis' work on the nature of love divides love...</td>\n",
       "      <td>2002.0</td>\n",
       "      <td>4.15</td>\n",
       "      <td>170.0</td>\n",
       "      <td>33684.0</td>\n",
       "      <td>23.0</td>\n",
       "      <td>The Four Loves</td>\n",
       "      <td>9780006280897 Lewis' work on the nature of lov...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>9780006280934</td>\n",
       "      <td>0006280935</td>\n",
       "      <td>The Problem of Pain</td>\n",
       "      <td>Clive Staples Lewis</td>\n",
       "      <td>Christian life</td>\n",
       "      <td>http://books.google.com/books/content?id=Kk-uV...</td>\n",
       "      <td>\"In The Problem of Pain, C.S. Lewis, one of th...</td>\n",
       "      <td>2002.0</td>\n",
       "      <td>4.09</td>\n",
       "      <td>176.0</td>\n",
       "      <td>37569.0</td>\n",
       "      <td>23.0</td>\n",
       "      <td>The Problem of Pain</td>\n",
       "      <td>9780006280934 \"In The Problem of Pain, C.S. Le...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5192</th>\n",
       "      <td>9788172235222</td>\n",
       "      <td>8172235224</td>\n",
       "      <td>Mistaken Identity</td>\n",
       "      <td>Nayantara Sahgal</td>\n",
       "      <td>Indic fiction (English)</td>\n",
       "      <td>http://books.google.com/books/content?id=q-tKP...</td>\n",
       "      <td>On A Train Journey Home To North India After L...</td>\n",
       "      <td>2003.0</td>\n",
       "      <td>2.93</td>\n",
       "      <td>324.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>Mistaken Identity</td>\n",
       "      <td>9788172235222 On A Train Journey Home To North...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5193</th>\n",
       "      <td>9788173031014</td>\n",
       "      <td>8173031010</td>\n",
       "      <td>Journey to the East</td>\n",
       "      <td>Hermann Hesse</td>\n",
       "      <td>Adventure stories</td>\n",
       "      <td>http://books.google.com/books/content?id=rq6JP...</td>\n",
       "      <td>This book tells the tale of a man who goes on ...</td>\n",
       "      <td>2002.0</td>\n",
       "      <td>3.70</td>\n",
       "      <td>175.0</td>\n",
       "      <td>24.0</td>\n",
       "      <td>23.0</td>\n",
       "      <td>Journey to the East</td>\n",
       "      <td>9788173031014 This book tells the tale of a ma...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5194</th>\n",
       "      <td>9788179921623</td>\n",
       "      <td>817992162X</td>\n",
       "      <td>The Monk Who Sold His Ferrari: A Fable About F...</td>\n",
       "      <td>Robin Sharma</td>\n",
       "      <td>Health &amp; Fitness</td>\n",
       "      <td>http://books.google.com/books/content?id=c_7mf...</td>\n",
       "      <td>Wisdom to Create a Life of Passion, Purpose, a...</td>\n",
       "      <td>2003.0</td>\n",
       "      <td>3.82</td>\n",
       "      <td>198.0</td>\n",
       "      <td>1568.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>The Monk Who Sold His Ferrari: A Fable About F...</td>\n",
       "      <td>9788179921623 Wisdom to Create a Life of Passi...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5195</th>\n",
       "      <td>9788185300535</td>\n",
       "      <td>8185300534</td>\n",
       "      <td>I Am that</td>\n",
       "      <td>Sri Nisargadatta Maharaj;Sudhakar S. Dikshit</td>\n",
       "      <td>Philosophy</td>\n",
       "      <td>http://books.google.com/books/content?id=Fv_JP...</td>\n",
       "      <td>This collection of the timeless teachings of o...</td>\n",
       "      <td>1999.0</td>\n",
       "      <td>4.51</td>\n",
       "      <td>531.0</td>\n",
       "      <td>104.0</td>\n",
       "      <td>26.0</td>\n",
       "      <td>I Am that: Talks with Sri Nisargadatta Maharaj</td>\n",
       "      <td>9788185300535 This collection of the timeless ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5196</th>\n",
       "      <td>9789027712059</td>\n",
       "      <td>9027712050</td>\n",
       "      <td>The Berlin Phenomenology</td>\n",
       "      <td>Georg Wilhelm Friedrich Hegel</td>\n",
       "      <td>History</td>\n",
       "      <td>http://books.google.com/books/content?id=Vy7Sk...</td>\n",
       "      <td>Since the three volume edition ofHegel's Philo...</td>\n",
       "      <td>1981.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>210.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>44.0</td>\n",
       "      <td>The Berlin Phenomenology</td>\n",
       "      <td>9789027712059 Since the three volume edition o...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5197 rows × 14 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "             isbn13      isbn10  \\\n",
       "0     9780002005883  0002005883   \n",
       "1     9780002261982  0002261987   \n",
       "2     9780006178736  0006178731   \n",
       "3     9780006280897  0006280897   \n",
       "4     9780006280934  0006280935   \n",
       "...             ...         ...   \n",
       "5192  9788172235222  8172235224   \n",
       "5193  9788173031014  8173031010   \n",
       "5194  9788179921623  817992162X   \n",
       "5195  9788185300535  8185300534   \n",
       "5196  9789027712059  9027712050   \n",
       "\n",
       "                                                  title  \\\n",
       "0                                                Gilead   \n",
       "1                                          Spider's Web   \n",
       "2                                        Rage of angels   \n",
       "3                                        The Four Loves   \n",
       "4                                   The Problem of Pain   \n",
       "...                                                 ...   \n",
       "5192                                  Mistaken Identity   \n",
       "5193                                Journey to the East   \n",
       "5194  The Monk Who Sold His Ferrari: A Fable About F...   \n",
       "5195                                          I Am that   \n",
       "5196                           The Berlin Phenomenology   \n",
       "\n",
       "                                           authors  \\\n",
       "0                               Marilynne Robinson   \n",
       "1                  Charles Osborne;Agatha Christie   \n",
       "2                                   Sidney Sheldon   \n",
       "3                              Clive Staples Lewis   \n",
       "4                              Clive Staples Lewis   \n",
       "...                                            ...   \n",
       "5192                              Nayantara Sahgal   \n",
       "5193                                 Hermann Hesse   \n",
       "5194                                  Robin Sharma   \n",
       "5195  Sri Nisargadatta Maharaj;Sudhakar S. Dikshit   \n",
       "5196                 Georg Wilhelm Friedrich Hegel   \n",
       "\n",
       "                         categories  \\\n",
       "0                           Fiction   \n",
       "1     Detective and mystery stories   \n",
       "2                           Fiction   \n",
       "3                    Christian life   \n",
       "4                    Christian life   \n",
       "...                             ...   \n",
       "5192        Indic fiction (English)   \n",
       "5193              Adventure stories   \n",
       "5194               Health & Fitness   \n",
       "5195                     Philosophy   \n",
       "5196                        History   \n",
       "\n",
       "                                              thumbnail  \\\n",
       "0     http://books.google.com/books/content?id=KQZCP...   \n",
       "1     http://books.google.com/books/content?id=gA5GP...   \n",
       "2     http://books.google.com/books/content?id=FKo2T...   \n",
       "3     http://books.google.com/books/content?id=XhQ5X...   \n",
       "4     http://books.google.com/books/content?id=Kk-uV...   \n",
       "...                                                 ...   \n",
       "5192  http://books.google.com/books/content?id=q-tKP...   \n",
       "5193  http://books.google.com/books/content?id=rq6JP...   \n",
       "5194  http://books.google.com/books/content?id=c_7mf...   \n",
       "5195  http://books.google.com/books/content?id=Fv_JP...   \n",
       "5196  http://books.google.com/books/content?id=Vy7Sk...   \n",
       "\n",
       "                                            description  published_year  \\\n",
       "0     A NOVEL THAT READERS and critics have been eag...          2004.0   \n",
       "1     A new 'Christie for Christmas' -- a full-lengt...          2000.0   \n",
       "2     A memorable, mesmerizing heroine Jennifer -- b...          1993.0   \n",
       "3     Lewis' work on the nature of love divides love...          2002.0   \n",
       "4     \"In The Problem of Pain, C.S. Lewis, one of th...          2002.0   \n",
       "...                                                 ...             ...   \n",
       "5192  On A Train Journey Home To North India After L...          2003.0   \n",
       "5193  This book tells the tale of a man who goes on ...          2002.0   \n",
       "5194  Wisdom to Create a Life of Passion, Purpose, a...          2003.0   \n",
       "5195  This collection of the timeless teachings of o...          1999.0   \n",
       "5196  Since the three volume edition ofHegel's Philo...          1981.0   \n",
       "\n",
       "      average_rating  num_pages  ratings_count  agg_of_book  \\\n",
       "0               3.85      247.0          361.0         21.0   \n",
       "1               3.83      241.0         5164.0         25.0   \n",
       "2               3.93      512.0        29532.0         32.0   \n",
       "3               4.15      170.0        33684.0         23.0   \n",
       "4               4.09      176.0        37569.0         23.0   \n",
       "...              ...        ...            ...          ...   \n",
       "5192            2.93      324.0            0.0         22.0   \n",
       "5193            3.70      175.0           24.0         23.0   \n",
       "5194            3.82      198.0         1568.0         22.0   \n",
       "5195            4.51      531.0          104.0         26.0   \n",
       "5196            0.00      210.0            0.0         44.0   \n",
       "\n",
       "                                     title_and_subtitle  \\\n",
       "0                                                Gilead   \n",
       "1                                 Spider's Web: A Novel   \n",
       "2                                        Rage of angels   \n",
       "3                                        The Four Loves   \n",
       "4                                   The Problem of Pain   \n",
       "...                                                 ...   \n",
       "5192                                  Mistaken Identity   \n",
       "5193                                Journey to the East   \n",
       "5194  The Monk Who Sold His Ferrari: A Fable About F...   \n",
       "5195     I Am that: Talks with Sri Nisargadatta Maharaj   \n",
       "5196                           The Berlin Phenomenology   \n",
       "\n",
       "                                     tagged_description  \n",
       "0     9780002005883 A NOVEL THAT READERS and critics...  \n",
       "1     9780002261982 A new 'Christie for Christmas' -...  \n",
       "2     9780006178736 A memorable, mesmerizing heroine...  \n",
       "3     9780006280897 Lewis' work on the nature of lov...  \n",
       "4     9780006280934 \"In The Problem of Pain, C.S. Le...  \n",
       "...                                                 ...  \n",
       "5192  9788172235222 On A Train Journey Home To North...  \n",
       "5193  9788173031014 This book tells the tale of a ma...  \n",
       "5194  9788179921623 Wisdom to Create a Life of Passi...  \n",
       "5195  9788185300535 This collection of the timeless ...  \n",
       "5196  9789027712059 Since the three volume edition o...  \n",
       "\n",
       "[5197 rows x 14 columns]"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "books = pd.read_csv(\"books_cleaned.csv\")\n",
    "books"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "4144c4c6",
   "metadata": {},
   "outputs": [],
   "source": [
    "books[\"tagged_description\"].to_csv(\"tagged_description.txt\",\n",
    "                                   sep = \"\\n\",\n",
    "                                   index = False,\n",
    "                                   header = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "80bd0392",
   "metadata": {},
   "outputs": [],
   "source": [
    "raw_documents = TextLoader(\"tagged_description.txt\", encoding='utf-8').load()\n",
    "text_splitter = CharacterTextSplitter(chunk_size=0, chunk_overlap=0, separator=\"\\n\")\n",
    "documents = text_splitter.split_documents(raw_documents)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "ddbb69ec",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Document(metadata={'source': 'tagged_description.txt'}, page_content='9780002005883 A NOVEL THAT READERS and critics have been eagerly anticipating for over a decade, Gilead is an astonishingly imagined story of remarkable lives. John Ames is a preacher, the son of a preacher and the grandson (both maternal and paternal) of preachers. It’s 1956 in Gilead, Iowa, towards the end of the Reverend Ames’s life, and he is absorbed in recording his family’s story, a legacy for the young son he will never see grow up. Haunted by his grandfather’s presence, John tells of the rift between his grandfather and his father: the elder, an angry visionary who fought for the abolitionist cause, and his son, an ardent pacifist. He is troubled, too, by his prodigal namesake, Jack (John Ames) Boughton, his best friend’s lost son who returns to Gilead searching for forgiveness and redemption. Told in John Ames’s joyous, rambling voice that finds beauty, humour and truth in the smallest of life’s details, Gilead is a song of celebration and acceptance of the best and the worst the world has to offer. At its heart is a tale of the sacred bonds between fathers and sons, pitch-perfect in style and story, set to dazzle critics and readers alike.')"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "documents[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1bc1e564",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\0105725U\\Documents\\Personal\\Book-recommender\\books_env\\Lib\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n",
      "c:\\Users\\0105725U\\Documents\\Personal\\Book-recommender\\books_env\\Lib\\site-packages\\huggingface_hub\\file_download.py:143: UserWarning: `huggingface_hub` cache-system uses symlinks by default to efficiently store duplicated files but your machine does not support them in C:\\Users\\0105725U\\.cache\\huggingface\\hub\\models--sentence-transformers--paraphrase-MiniLM-L3-v2. Caching files will still work but in a degraded version that might require more space on your disk. This warning can be disabled by setting the `HF_HUB_DISABLE_SYMLINKS_WARNING` environment variable. For more details, see https://huggingface.co/docs/huggingface_hub/how-to-cache#limitations.\n",
      "To support symlinks on Windows, you either need to activate Developer Mode or to run Python as an administrator. In order to activate developer mode, see this article: https://docs.microsoft.com/en-us/windows/apps/get-started/enable-your-device-for-development\n",
      "  warnings.warn(message)\n",
      "Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`\n"
     ]
    }
   ],
   "source": [
    "from langchain_community.embeddings import HuggingFaceEmbeddings\n",
    "from langchain.vectorstores import Chroma\n",
    "\n",
    "embedding_model = HuggingFaceEmbeddings(model_name=\"sentence-transformers/paraphrase-MiniLM-L3-v2\")\n",
    "\n",
    "db_books = Chroma.from_documents(\n",
    "    documents,\n",
    "    embedding=embedding_model\n",
    ")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "8ed611b6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[Document(metadata={'source': 'tagged_description.txt'}, page_content=\"9780941807555 THE LITTLE BIG BOOK FOR GOD'S CHILDREN is a wonderful resource for parents looking to introduce their children to the wisdom and beauty of Christian faith. Illustrated with early twentieth-century art from artists such as Jessie Wilcox Smith, Ellen H. Clapsaddle, and Maud and Miska Petersham, this Little Big Book presents selected bible stories, parables, and verses; poems and prayers; excerpts and fables; songs and hymns; and activities - all collected in one delightful volume. A celebration of God's enduring message of love, GOD'S CHILDREN is sure to provide an endless wellspring of inspiration and hope.\"),\n",
       " Document(metadata={'source': 'tagged_description.txt'}, page_content='9788122200850 This book is the story of a young girl obsessed by a childhood prophecy of disaster. The author builds up an atmosphere of tension and oppression, in the middle of an Indian summer.'),\n",
       " Document(metadata={'source': 'tagged_description.txt'}, page_content='9780374422080 This Newbery Honor Book tells the story of 11 -year-old Primrose, who lives in a small fishing village in British Columbia. She recounts her experiences and all she learns about human nature and the unpredictability of life after her parents are lost at sea.'),\n",
       " Document(metadata={'source': 'tagged_description.txt'}, page_content=\"9780802431486 Drawn from years of counseling and the author's own parenting experiences, this valuable resource, filled with Scripture passages and accompanying practical applications, provides principles for raising and nurturing children in these uncertain and rapidly changing times. Original.\"),\n",
       " Document(metadata={'source': 'tagged_description.txt'}, page_content='9780374299194 The author describes growing up in a family of all boys in Webster Groves, Missouri, reflecting on such topics as the dynamics of a Christian youth fellowship, his role as the school prankster, his marriage, and the life lessons he has learned from birds.'),\n",
       " Document(metadata={'source': 'tagged_description.txt'}, page_content='9780671631987 With more than half a million copies in print, Teach Your Child to Read in 100 Easy Lessons is the definitive guide to giving your child the reading skills needed now for a better chance at tomorrow, while bringing you and your child closer together. Is your child halfway through first grade and still unable to read? Is your preschooler bored with coloring and ready for reading? Do you want to help your child read, but are afraid you’ll do something wrong? Teach Your Child to Read in 100 Easy Lessons is a complete, step-by-step program that shows patents simply and clearly how to teach their children to read. Twenty minutes a day is all you need, and within 100 teaching days your child will be reading on a solid second-grade reading level. It’s a sensible, easy-to-follow, and enjoyable way to help your child gain the essential skills of reading. Everything you need is here—no paste, no scissors, no flash cards, no complicated directions—just you and your child learning together. One hundred lessons, fully illustrated and color-coded for clarity, give your child the basic and more advanced skills needed to become a good reader.'),\n",
       " Document(metadata={'source': 'tagged_description.txt'}, page_content='9780143037392 Explains the importance of reading aloud to children, offers guidance on how to set up a read-aloud atmosphere in the home or classroom, and recommends titles to select.'),\n",
       " Document(metadata={'source': 'tagged_description.txt'}, page_content=\"9780064406925 The Little House books tell the story of a little pioneer girl and her family as they traveled by covered wagon across the Midwest. Laura Ingalls Wilder's classic books, illustrated with Garth Williams' timeless artwork, have been cherished by millions of readers ever since they were first published over sixty years ago. This My First Little House Book introduces Almanzo Wilder, the young boy from Farmer Boy who would one day marry Laura Ingalls. In Winter on the Farm, Almanzo goes through his afternoon barn chores, and then sits down to eat a hearty farm supper with his family. In this first book about Almanzo, young readers are able to share in the warmth and joy of another Little House family and celebrate new Little House adventures. Winter on the Farm is the first in an ongoing series about Laura’s beloved farmer boy.\"),\n",
       " Document(metadata={'source': 'tagged_description.txt'}, page_content='\"9780064462341 The pioneer spirit lives on... Readers around the world know and love Laura, the little girl born in the Big Woods of Wisconsin and raised in covered wagons and on wide open prairies. Now Little House fans can learn more about \"\"Half-pint\"\" in this, the first picture book biography book of Laura Ingalls Wilder. With a simple, glowing text by noted historian and Little House scholar William Anderson, and glorious paintings by Dan Andreasen, Pioneer Girl is a very special portrait of a writer whose classic books and poineer adventures have made her one of the most popular literary figures in America. This picture-book biography of Laura Ingalls Wilder tells the remarkable story of the pioneer girl who would one day immortalize her adventures in the beloved Little House books. Written in simple, glowing text by noted Little House scholar William Anderson, and illustrated with glorious paintings by artist Dan Andreasen, this wonderful first biography captures the very essence of the little girl called ‘Half-pint,\\' whose classic books and pioneer adventures have made her one of the most popular literary figures in America. This picture-book biography of Laura Ingalls Wilder tells the remarkable story of the pioneer girl who would one day immortalize her adventures in the beloved Little House books. Written in simple, glowing text by noted Little House scholar William Anderson, and illustrated with glorious paintings by artist Dan Andreasen, this wonderful first biography captures the very essence of the little girl called ‘Half-pint,’ whose classic books and pioneer adventures have made her one of the most popular literary figures in America.\"'),\n",
       " Document(metadata={'source': 'tagged_description.txt'}, page_content='9780743243780 The author describes his coming of age as a teacher, storyteller, and writer, a personal journey during which he spent fifteen years finding his voice in the classroom, and came to terms with the undervalued importance of teaching.')]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "query = \"A book to teach children about nature\"\n",
    "docs = db_books.similarity_search(query, k = 10)\n",
    "docs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "47e4c48c",
   "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>isbn13</th>\n",
       "      <th>isbn10</th>\n",
       "      <th>title</th>\n",
       "      <th>authors</th>\n",
       "      <th>categories</th>\n",
       "      <th>thumbnail</th>\n",
       "      <th>description</th>\n",
       "      <th>published_year</th>\n",
       "      <th>average_rating</th>\n",
       "      <th>num_pages</th>\n",
       "      <th>ratings_count</th>\n",
       "      <th>agg_of_book</th>\n",
       "      <th>title_and_subtitle</th>\n",
       "      <th>tagged_description</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>4264</th>\n",
       "      <td>9780941807555</td>\n",
       "      <td>094180755X</td>\n",
       "      <td>The Little Big Book for God's Children</td>\n",
       "      <td>Lena Tabori;Alice Wong</td>\n",
       "      <td>Religion</td>\n",
       "      <td>http://books.google.com/books/content?id=s2PfT...</td>\n",
       "      <td>THE LITTLE BIG BOOK FOR GOD'S CHILDREN is a wo...</td>\n",
       "      <td>2001.0</td>\n",
       "      <td>4.88</td>\n",
       "      <td>352.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>24.0</td>\n",
       "      <td>The Little Big Book for God's Children</td>\n",
       "      <td>9780941807555 THE LITTLE BIG BOOK FOR GOD'S CH...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             isbn13      isbn10                                   title  \\\n",
       "4264  9780941807555  094180755X  The Little Big Book for God's Children   \n",
       "\n",
       "                     authors categories  \\\n",
       "4264  Lena Tabori;Alice Wong   Religion   \n",
       "\n",
       "                                              thumbnail  \\\n",
       "4264  http://books.google.com/books/content?id=s2PfT...   \n",
       "\n",
       "                                            description  published_year  \\\n",
       "4264  THE LITTLE BIG BOOK FOR GOD'S CHILDREN is a wo...          2001.0   \n",
       "\n",
       "      average_rating  num_pages  ratings_count  agg_of_book  \\\n",
       "4264            4.88      352.0            8.0         24.0   \n",
       "\n",
       "                          title_and_subtitle  \\\n",
       "4264  The Little Big Book for God's Children   \n",
       "\n",
       "                                     tagged_description  \n",
       "4264  9780941807555 THE LITTLE BIG BOOK FOR GOD'S CH...  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "books[books[\"isbn13\"] == int(docs[0].page_content.split()[0].strip())]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "43ed7a8c",
   "metadata": {},
   "outputs": [],
   "source": [
    "def retrieve_semantic_recommendation(\n",
    "        query:str,\n",
    "        top_k: int = 10,\n",
    ") -> pd.DataFrame :\n",
    "    recs = db_books.similarity_search(query, k = 50)\n",
    "\n",
    "    books_list = []\n",
    "\n",
    "    for i in range (0, len(recs)):\n",
    "        books_list += [int(recs[i].page_content.strip('\"\"').split()[0])]\n",
    "\n",
    "    return books[books[\"isbn13\"].isin(books_list)].head(top_k)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "89dfb386",
   "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>isbn13</th>\n",
       "      <th>isbn10</th>\n",
       "      <th>title</th>\n",
       "      <th>authors</th>\n",
       "      <th>categories</th>\n",
       "      <th>thumbnail</th>\n",
       "      <th>description</th>\n",
       "      <th>published_year</th>\n",
       "      <th>average_rating</th>\n",
       "      <th>num_pages</th>\n",
       "      <th>ratings_count</th>\n",
       "      <th>agg_of_book</th>\n",
       "      <th>title_and_subtitle</th>\n",
       "      <th>tagged_description</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>31</th>\n",
       "      <td>9780007105045</td>\n",
       "      <td>0007105045</td>\n",
       "      <td>Tree and Leaf</td>\n",
       "      <td>John Ronald Reuel Tolkien</td>\n",
       "      <td>Literary Collections</td>\n",
       "      <td>http://books.google.com/books/content?id=aPb_A...</td>\n",
       "      <td>\"The two works 'On fairy-stories' and 'Leaf by...</td>\n",
       "      <td>2001.0</td>\n",
       "      <td>4.09</td>\n",
       "      <td>176.0</td>\n",
       "      <td>2245.0</td>\n",
       "      <td>24.0</td>\n",
       "      <td>Tree and Leaf: The Homecoming of Beorhtnoth : ...</td>\n",
       "      <td>9780007105045 \"The two works 'On fairy-stories...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>267</th>\n",
       "      <td>9780060882600</td>\n",
       "      <td>0060882603</td>\n",
       "      <td>The Annotated Charlotte's Web</td>\n",
       "      <td>E. B. White</td>\n",
       "      <td>Juvenile Nonfiction</td>\n",
       "      <td>http://books.google.com/books/content?id=vaYYH...</td>\n",
       "      <td>Charlotte's Web, one of America's best-loved c...</td>\n",
       "      <td>2006.0</td>\n",
       "      <td>4.16</td>\n",
       "      <td>320.0</td>\n",
       "      <td>41.0</td>\n",
       "      <td>19.0</td>\n",
       "      <td>The Annotated Charlotte's Web</td>\n",
       "      <td>9780060882600 Charlotte's Web, one of America'...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>324</th>\n",
       "      <td>9780060959036</td>\n",
       "      <td>0060959037</td>\n",
       "      <td>Prodigal Summer</td>\n",
       "      <td>Barbara Kingsolver</td>\n",
       "      <td>Fiction</td>\n",
       "      <td>http://books.google.com/books/content?id=06IwG...</td>\n",
       "      <td>Barbara Kingsolver's fifth novel is a hymn to ...</td>\n",
       "      <td>2001.0</td>\n",
       "      <td>4.00</td>\n",
       "      <td>444.0</td>\n",
       "      <td>85440.0</td>\n",
       "      <td>24.0</td>\n",
       "      <td>Prodigal Summer: A Novel</td>\n",
       "      <td>9780060959036 Barbara Kingsolver's fifth novel...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>397</th>\n",
       "      <td>9780062512796</td>\n",
       "      <td>006251279X</td>\n",
       "      <td>The Pilgrimage</td>\n",
       "      <td>Paulo Coelho;Alan R. Clarke</td>\n",
       "      <td>Fiction</td>\n",
       "      <td>http://books.google.com/books/content?id=atdJc...</td>\n",
       "      <td>Previously published as The Diary of a Magus, ...</td>\n",
       "      <td>1995.0</td>\n",
       "      <td>3.65</td>\n",
       "      <td>272.0</td>\n",
       "      <td>878.0</td>\n",
       "      <td>30.0</td>\n",
       "      <td>The Pilgrimage</td>\n",
       "      <td>9780062512796 Previously published as The Diar...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>416</th>\n",
       "      <td>9780064406925</td>\n",
       "      <td>006440692X</td>\n",
       "      <td>Winter on the Farm</td>\n",
       "      <td>Laura Ingalls Wilder</td>\n",
       "      <td>Juvenile Fiction</td>\n",
       "      <td>http://books.google.com/books/content?id=IvlKH...</td>\n",
       "      <td>The Little House books tell the story of a lit...</td>\n",
       "      <td>1997.0</td>\n",
       "      <td>4.13</td>\n",
       "      <td>32.0</td>\n",
       "      <td>400.0</td>\n",
       "      <td>28.0</td>\n",
       "      <td>Winter on the Farm</td>\n",
       "      <td>9780064406925 The Little House books tell the ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>429</th>\n",
       "      <td>9780064434980</td>\n",
       "      <td>0064434982</td>\n",
       "      <td>The Deer in the Wood</td>\n",
       "      <td>Laura Ingalls Wilder</td>\n",
       "      <td>Juvenile Fiction</td>\n",
       "      <td>http://books.google.com/books/content?id=V7YDW...</td>\n",
       "      <td>Even the youngest child can enjoy a special ad...</td>\n",
       "      <td>1999.0</td>\n",
       "      <td>4.17</td>\n",
       "      <td>32.0</td>\n",
       "      <td>302.0</td>\n",
       "      <td>26.0</td>\n",
       "      <td>The Deer in the Wood</td>\n",
       "      <td>9780064434980 Even the youngest child can enjo...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>434</th>\n",
       "      <td>9780064462044</td>\n",
       "      <td>0064462048</td>\n",
       "      <td>My Little House Crafts Book</td>\n",
       "      <td>Carolyn Strom Collins</td>\n",
       "      <td>Juvenile Nonfiction</td>\n",
       "      <td>http://books.google.com/books/content?id=lTzrs...</td>\n",
       "      <td>Make the same pioneer crafts that Laura did! I...</td>\n",
       "      <td>1998.0</td>\n",
       "      <td>4.05</td>\n",
       "      <td>64.0</td>\n",
       "      <td>56.0</td>\n",
       "      <td>27.0</td>\n",
       "      <td>My Little House Crafts Book: 18 Projects from ...</td>\n",
       "      <td>9780064462044 Make the same pioneer crafts tha...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>435</th>\n",
       "      <td>9780064462341</td>\n",
       "      <td>006446234X</td>\n",
       "      <td>Pioneer Girl</td>\n",
       "      <td>William Anderson</td>\n",
       "      <td>Juvenile Nonfiction</td>\n",
       "      <td>http://books.google.com/books/content?id=Sj4UD...</td>\n",
       "      <td>The pioneer spirit lives on... Readers around ...</td>\n",
       "      <td>2000.0</td>\n",
       "      <td>4.15</td>\n",
       "      <td>32.0</td>\n",
       "      <td>414.0</td>\n",
       "      <td>25.0</td>\n",
       "      <td>Pioneer Girl: The Story of Laura Ingalls Wilder</td>\n",
       "      <td>9780064462341 The pioneer spirit lives on... R...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>440</th>\n",
       "      <td>9780066238500</td>\n",
       "      <td>0066238501</td>\n",
       "      <td>The Chronicles of Narnia (adult)</td>\n",
       "      <td>C. S. Lewis</td>\n",
       "      <td>Fiction</td>\n",
       "      <td>http://books.google.com/books/content?id=3VGkK...</td>\n",
       "      <td>Journeys to the end of the world, fantastic cr...</td>\n",
       "      <td>2001.0</td>\n",
       "      <td>4.26</td>\n",
       "      <td>767.0</td>\n",
       "      <td>425445.0</td>\n",
       "      <td>24.0</td>\n",
       "      <td>The Chronicles of Narnia (adult)</td>\n",
       "      <td>9780066238500 Journeys to the end of the world...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>442</th>\n",
       "      <td>9780067575208</td>\n",
       "      <td>006757520X</td>\n",
       "      <td>The Sense of Wonder</td>\n",
       "      <td>Rachel Carson</td>\n",
       "      <td>Nature</td>\n",
       "      <td>http://books.google.com/books/content?id=Zee5S...</td>\n",
       "      <td>First published more than three decades ago, t...</td>\n",
       "      <td>1998.0</td>\n",
       "      <td>4.39</td>\n",
       "      <td>112.0</td>\n",
       "      <td>1160.0</td>\n",
       "      <td>27.0</td>\n",
       "      <td>The Sense of Wonder</td>\n",
       "      <td>9780067575208 First published more than three ...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            isbn13      isbn10                             title  \\\n",
       "31   9780007105045  0007105045                     Tree and Leaf   \n",
       "267  9780060882600  0060882603     The Annotated Charlotte's Web   \n",
       "324  9780060959036  0060959037                   Prodigal Summer   \n",
       "397  9780062512796  006251279X                    The Pilgrimage   \n",
       "416  9780064406925  006440692X                Winter on the Farm   \n",
       "429  9780064434980  0064434982              The Deer in the Wood   \n",
       "434  9780064462044  0064462048       My Little House Crafts Book   \n",
       "435  9780064462341  006446234X                      Pioneer Girl   \n",
       "440  9780066238500  0066238501  The Chronicles of Narnia (adult)   \n",
       "442  9780067575208  006757520X               The Sense of Wonder   \n",
       "\n",
       "                         authors            categories  \\\n",
       "31     John Ronald Reuel Tolkien  Literary Collections   \n",
       "267                  E. B. White   Juvenile Nonfiction   \n",
       "324           Barbara Kingsolver               Fiction   \n",
       "397  Paulo Coelho;Alan R. Clarke               Fiction   \n",
       "416         Laura Ingalls Wilder      Juvenile Fiction   \n",
       "429         Laura Ingalls Wilder      Juvenile Fiction   \n",
       "434        Carolyn Strom Collins   Juvenile Nonfiction   \n",
       "435             William Anderson   Juvenile Nonfiction   \n",
       "440                  C. S. Lewis               Fiction   \n",
       "442                Rachel Carson                Nature   \n",
       "\n",
       "                                             thumbnail  \\\n",
       "31   http://books.google.com/books/content?id=aPb_A...   \n",
       "267  http://books.google.com/books/content?id=vaYYH...   \n",
       "324  http://books.google.com/books/content?id=06IwG...   \n",
       "397  http://books.google.com/books/content?id=atdJc...   \n",
       "416  http://books.google.com/books/content?id=IvlKH...   \n",
       "429  http://books.google.com/books/content?id=V7YDW...   \n",
       "434  http://books.google.com/books/content?id=lTzrs...   \n",
       "435  http://books.google.com/books/content?id=Sj4UD...   \n",
       "440  http://books.google.com/books/content?id=3VGkK...   \n",
       "442  http://books.google.com/books/content?id=Zee5S...   \n",
       "\n",
       "                                           description  published_year  \\\n",
       "31   \"The two works 'On fairy-stories' and 'Leaf by...          2001.0   \n",
       "267  Charlotte's Web, one of America's best-loved c...          2006.0   \n",
       "324  Barbara Kingsolver's fifth novel is a hymn to ...          2001.0   \n",
       "397  Previously published as The Diary of a Magus, ...          1995.0   \n",
       "416  The Little House books tell the story of a lit...          1997.0   \n",
       "429  Even the youngest child can enjoy a special ad...          1999.0   \n",
       "434  Make the same pioneer crafts that Laura did! I...          1998.0   \n",
       "435  The pioneer spirit lives on... Readers around ...          2000.0   \n",
       "440  Journeys to the end of the world, fantastic cr...          2001.0   \n",
       "442  First published more than three decades ago, t...          1998.0   \n",
       "\n",
       "     average_rating  num_pages  ratings_count  agg_of_book  \\\n",
       "31             4.09      176.0         2245.0         24.0   \n",
       "267            4.16      320.0           41.0         19.0   \n",
       "324            4.00      444.0        85440.0         24.0   \n",
       "397            3.65      272.0          878.0         30.0   \n",
       "416            4.13       32.0          400.0         28.0   \n",
       "429            4.17       32.0          302.0         26.0   \n",
       "434            4.05       64.0           56.0         27.0   \n",
       "435            4.15       32.0          414.0         25.0   \n",
       "440            4.26      767.0       425445.0         24.0   \n",
       "442            4.39      112.0         1160.0         27.0   \n",
       "\n",
       "                                    title_and_subtitle  \\\n",
       "31   Tree and Leaf: The Homecoming of Beorhtnoth : ...   \n",
       "267                      The Annotated Charlotte's Web   \n",
       "324                           Prodigal Summer: A Novel   \n",
       "397                                     The Pilgrimage   \n",
       "416                                 Winter on the Farm   \n",
       "429                               The Deer in the Wood   \n",
       "434  My Little House Crafts Book: 18 Projects from ...   \n",
       "435    Pioneer Girl: The Story of Laura Ingalls Wilder   \n",
       "440                   The Chronicles of Narnia (adult)   \n",
       "442                                The Sense of Wonder   \n",
       "\n",
       "                                    tagged_description  \n",
       "31   9780007105045 \"The two works 'On fairy-stories...  \n",
       "267  9780060882600 Charlotte's Web, one of America'...  \n",
       "324  9780060959036 Barbara Kingsolver's fifth novel...  \n",
       "397  9780062512796 Previously published as The Diar...  \n",
       "416  9780064406925 The Little House books tell the ...  \n",
       "429  9780064434980 Even the youngest child can enjo...  \n",
       "434  9780064462044 Make the same pioneer crafts tha...  \n",
       "435  9780064462341 The pioneer spirit lives on... R...  \n",
       "440  9780066238500 Journeys to the end of the world...  \n",
       "442  9780067575208 First published more than three ...  "
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "retrieve_semantic_recommendation(\"A book to teach children about nature\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f655cdbb",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "books_env",
   "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": "3.13.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}