{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "0c3f1df8",
   "metadata": {},
   "source": [
    "# Self Ask With Search\n",
    "\n",
    "This notebook showcases the Self Ask With Search chain."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "7e3b513e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new chain...\u001b[0m\n",
      "What is the hometown of the reigning men's U.S. Open champion?\n",
      "Are follow up questions needed here:\u001b[102m Yes.\n",
      "Follow up: Who is the reigning men's U.S. Open champion?\u001b[0m\n",
      "Intermediate answer: \u001b[103mCarlos Alcaraz won the 2022 Men's single title while Poland's Iga Swiatek won the Women's single title defeating Tunisian's Ons Jabeur..\u001b[0m\u001b[102m\n",
      "Follow up: Where is Carlos Alcaraz from?\u001b[0m\n",
      "Intermediate answer: \u001b[103mEl Palmar, Murcia, Spain.\u001b[0m\u001b[102m\n",
      "So the final answer is: El Palmar, Murcia, Spain\u001b[0m\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'\\nSo the final answer is: El Palmar, Murcia, Spain'"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from langchain import SelfAskWithSearchChain, OpenAI, SerpAPIChain\n",
    "\n",
    "llm = OpenAI(temperature=0)\n",
    "search = SerpAPIChain()\n",
    "\n",
    "self_ask_with_search = SelfAskWithSearchChain(llm=llm, search_chain=search, verbose=True)\n",
    "\n",
    "self_ask_with_search.run(\"What is the hometown of the reigning men's U.S. Open champion?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "683d69e7",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}