{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Example notebook on how to extract a source from the database and save it in another format"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "\n",
    "from buster.docparser import read_documents, write_documents"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Path to the database\n",
    "db_path = \"documents.db\"\n",
    "\n",
    "# Source to extract\n",
    "target = \"pytorch\"\n",
    "df = read_documents(db_path, target)\n",
    "\n",
    "# If you want to save it as tar.gz\n",
    "filepath = os.path.join('buster/data/', f'document_embeddings_{target}.tar.gz')\n",
    "write_documents(filepath, target, df)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "milabot",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "name": "python",
   "version": "3.10.9"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "9db6f4b791ef587fd310257e87896b12053c9010399595f881592a25a8a29679"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}