{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Notebook for creating the documents based on the curated QA pair dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from ipynb.fs.defs.preprocess_data import store_documents\n",
    "from langchain.docstore.document import Document\n",
    "import json\n",
    "\n",
    "# Load QA dataset\n",
    "with open(\"./../input_data/QA_dataset/golden_qa_set.json\", 'r') as file:\n",
    "    golden_qa_set = json.load(file)\n",
    "\n",
    "# Remove duplicate answers (Kersten + Secondary Literature) and template answers\n",
    "indices_to_remove = list(range(102, 121)) + list(range(122, 133)) + list(range(134, 157))\n",
    "indices_to_remove = sorted(set(indices_to_remove), reverse=True)\n",
    "for index in indices_to_remove:\n",
    "    del golden_qa_set['qa_set'][index]\n",
    "\n",
    "question_set = [qa['question'] for qa in golden_qa_set['qa_set']]\n",
    "golden_answer_set = [qa['golden_answer'] for qa in golden_qa_set['qa_set']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create one document for each question\n",
    "all_qa_dataset_documents = []\n",
    "for q, a in zip(question_set, golden_answer_set):\n",
    "\n",
    "    document = Document(\n",
    "    page_content=f\"{q} \\n {a}\", \n",
    "    metadata={\n",
    "        \"source\": \"QA Dataset\",\n",
    "        \"title\": \"QA Dataset\"\n",
    "    })\n",
    "    all_qa_dataset_documents.append(document)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "store_documents(all_qa_dataset_documents, \"./../input_data/QA_dataset/all_documents\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "venv",
   "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}