{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "f9e39a86-a9db-4571-bdc1-bf2a14675345",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "import os\n",
    "import json\n",
    "\n",
    "from dotenv import load_dotenv\n",
    "load_dotenv()\n",
    "\n",
    "TAVILY_API_KEY = os.environ.get(\"TAVILY_API_KEY\")\n",
    "OPENAI_API_KEY = os.environ.get(\"OPENAI_API_KEY\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5348dd2b-a2ae-4fa6-8268-be6da402898c",
   "metadata": {},
   "source": [
    "### Use tools ###"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "e47f6678-69ff-4ead-96c7-d4b7cd59e561",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[{'url': 'https://maps.google.com.tw/',\n",
       "  'content': 'Find local businesses, view maps and get driving directions in Google Maps.'},\n",
       " {'url': 'https://www.google.com.tw/maps?hl=zh-TW&tab=wl&output=classic&dg=brw',\n",
       "  'content': '利用「Google 地圖」尋找本地商家、檢視地圖或規劃行車路線。'},\n",
       " {'url': 'https://twfile.com/五角味食堂/92277974',\n",
       "  'content': '五角味食堂,商業統一編號:92277974,地址:彰化縣北斗鎮文昌里復興路臨100-1號,負責人姓名:李雅筑,OpenData(4) 五角味食堂(24項情報)-台灣公司情報網 台灣公司情報網'},\n",
       " {'url': 'https://www.findcompany.com.tw/五角味食堂',\n",
       "  'content': '五角味食堂. 資本總額 (元) 30,000. 負責人. 李雅筑. 登記地址. 彰化縣北斗鎮文昌里復興路臨100-1號 郵遞區號查詢. 設立日期. 2023-03-31.'},\n",
       " {'url': 'https://twypage.com/sd-1654806-B-彰化-五角味食堂.html',\n",
       "  'content': '五角味食堂,統編:92277974,地址:彰化縣北斗鎮文昌里復興路臨100-1號,負責人:李雅筑,設立日期:2023-03-31,變更日期:2023-03-31,公司狀態:核准設立 「查詢最新營業狀況請至財政部稅務入口網 」,營業項目:食品什貨、飲料零售業,餐館業'}]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
    "\n",
    "\n",
    "tool = TavilySearchResults()\n",
    "tool.invoke({\"query\": \"五角味食堂\t彰化縣北斗鎮文昌里復興路臨100-1號\"})\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2c1f236e-88bf-46e7-8e39-cbc9d7330f56",
   "metadata": {},
   "source": [
    "### Define agent - AgentExecutor ###"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "22837788-d2f0-48a0-ad71-ff6226d5bd39",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain import hub\n",
    "from langchain.agents import AgentExecutor, create_openai_functions_agent\n",
    "from langchain_openai import ChatOpenAI\n",
    "\n",
    "\n",
    "instructions = \"\"\"As a helpful and rigorous retail analyst, given the provided query and a list of search results for the query,  your task is to first use store name and address to identify relevant information. After that, from the relevant information, extract `store_name`, `address`, `description`, `category`, `provide_alcohol` and `phone_number` from the found relevant information. Note that `category` can only be `小吃店`, `日式料理(含居酒屋，串燒)`, `火(鍋／爐)`, `東南亞料理(不含日韓)`, `海鮮熱炒`,  `特色餐廳(含雞、鵝、牛、羊肉)`, `傳統餐廳`, `燒烤`, `韓式料理(含火鍋，烤肉)`, `西餐廳(含美式，義式，墨式)`, `西餐廳(餐酒館、酒吧、飛鏢吧、pub、lounge bar)`, `西餐廳(土耳其、漢堡、薯條、法式、歐式、印度)` or `早餐`. According to our experience,`provide_alcohol` can be inferred based on whether a store is suitable for  scenarios such as Gathering, Chill, Enjoying Together, Drinking Freely, Winery, Wine Cellar, Wine Storage, Relaxing, Unwinding, Lyrical, Romantic, Pleasant, Stress Relief, Wine and Dine, Light Drinking Gatherings, Birthday Celebrations, Socializing, Parties, Networking, After Work Relaxation with a Drink, Relaxing Places Suitable for Drinking, Every Dish Goes Well with Beer, Shared Dishes, Dining Together, Atmosphere Suitable for Celebratory Drinking, Places Suitable for Light Drinking Gatherings with Friends, Small Shops Suitable for Relaxing and Light Drinking. `description` is a summary of key piece of evidence and reasons that lead you decide `category` and `provide_alcohol` .\n",
    "\n",
    "            It's very important to omit unrelated results. Do not make up any assumption.\n",
    "            Please think step by step, and output a single json that starts with `{` and ends with `}`. An example output json is like {\"store_name\": \"...\", \"address\": \"...\", \"description\": \"... products, service or highlights ...\", \"category\": \"...\", \"phone_number\": \"...\", \"provide_alcohol\": true or false}\n",
    "            If no relevant information has been found, simply output json with empty values.\"\"\"\n",
    "base_prompt = hub.pull(\"langchain-ai/openai-functions-template\")\n",
    "prompt = base_prompt.partial(instructions=instructions)\n",
    "llm = ChatOpenAI(temperature=0, )\n",
    "tavily_tool = TavilySearchResults()\n",
    "tools = [tavily_tool]\n",
    "agent = create_openai_functions_agent(llm, tools, prompt)\n",
    "agent_executor = AgentExecutor(\n",
    "    agent=agent,\n",
    "    tools=tools,\n",
    "    verbose=True,\n",
    ")\n",
    "agent_executor.invoke({\"input\": \"五角味食堂\t彰化縣北斗鎮文昌里復興路臨100-1號\"})\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "38770f28-9950-49dc-a305-0ea180ae417c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3m\n",
      "Invoking: `tavily_search_results_json` with `{'query': '五角味食堂 彰化縣北斗鎮文昌里復興路臨100-1號'}`\n",
      "\n",
      "\n",
      "\u001b[0m\u001b[36;1m\u001b[1;3m[{'url': 'https://www.facebook.com/people/五角味食堂/100088207986612/', 'content': '五角味食堂, 彰化縣. 209 likes · 1 talking about this. 五角味食堂～ 一個結合.台灣.日本.中國.韓國.泰國.口味料理的複合式美食餐廳。 裡面以餃子類為主打!'}, {'url': 'https://twfile.com/五角味食堂/92277974', 'content': '五角味食堂,商業統一編號:92277974,地址:彰化縣北斗鎮文昌里復興路臨100-1號,負責人姓名:李雅筑,OpenData(4) 五角味食堂(24項情報)-台灣公司情報網 台灣公司情報網'}, {'url': 'https://opengovtw.com/ban/92277974', 'content': '所在地為彰化縣北斗鎮文昌里復興路臨100-1號。 ... 五角味食堂: 彰化縣北斗鎮文昌里復興路臨100-1號: 李雅筑: 30000: 獨資: 1120816972: 財政部營業稅籍資料. 營業人名稱: 五角味食堂 : 營業地址: 彰化縣北斗鎮文昌里復興路臨100－1號 :'}, {'url': 'https://www.google.com.tw/maps?hl=zh-TW&tab=wl&output=classic&dg=brw', 'content': '利用「Google 地圖」尋找本地商家、檢視地圖或規劃行車路線。'}, {'url': 'https://maps.google.com.tw/', 'content': 'Find local businesses, view maps and get driving directions in Google Maps.'}]\u001b[0m\u001b[32;1m\u001b[1;3m{\n",
      "\"store_name\": \"五角味食堂\",\n",
      "\"address\": \"彰化縣北斗鎮文昌里復興路臨100-1號\",\n",
      "\"description\": \"五角味食堂是一個結合台灣、日本、中國、韓國、泰國口味料理的複合式美食餐廳，主打餃子類食物。\",\n",
      "\"category\": \"小吃店\",\n",
      "\"phone_number\": \"\",\n",
      "\"provide_alcohol\": false\n",
      "}\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'input': '五角味食堂\\t彰化縣北斗鎮文昌里復興路臨100-1號',\n",
       " 'output': '{\\n\"store_name\": \"五角味食堂\",\\n\"address\": \"彰化縣北斗鎮文昌里復興路臨100-1號\",\\n\"description\": \"五角味食堂是一個結合台灣、日本、中國、韓國、泰國口味料理的複合式美食餐廳，主打餃子類食物。\",\\n\"category\": \"小吃店\",\\n\"phone_number\": \"\",\\n\"provide_alcohol\": false\\n}'}"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": []
  },
  {
   "cell_type": "markdown",
   "id": "479c0691-72b1-4f43-9120-43007ea4c041",
   "metadata": {},
   "source": [
    "### Utilities - external API wrapper (NOT TOOL!) ###"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "3d5884e2-c6b4-4454-bf21-f7b6bbfe2193",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain_community.utilities import SerpAPIWrapper\n",
    "SERPAPI_API_KEY=\"9d4e074bca8f9f7fa9ca5e05b874ea7da4f07cb505292ab29a0e1b91ffa0340a\"\n",
    "os.environ[\"SERPAPI_API_KEY\"] = SERPAPI_API_KEY\n",
    "SERPER_API_KEY=\"37128e339289d0e855c54f9afa9aa489bd7c23da\"\n",
    "os.environ['SERPER_API_KEY']=SERPER_API_KEY\n",
    "\n",
    "from langchain_community.utilities import GoogleSerperAPIWrapper\n",
    "\n",
    "###  SERPER  ###\n",
    "serper = GoogleSerperAPIWrapper(gl = 'tw', lr = 'lang_zh-TW', hl='zh-tw', k = 30) \n",
    "# search.run(\"Obama's first name?\")\n",
    "# serper_results = serper.results(\"宜窩餐飲有限公司 台北市 -inurl:twincn.com -inurl:findcompany.com.tw -inurl:iyp.com.tw -inurl:twypage.com -inurl:alltwcompany.com -inurl:zhupiter.com -inurl:twinc.com.tw\")\n",
    "serper_results = serper.results(\"致仙飲食店 澎湖縣 -inurl:twincn.com -inurl:findcompany.com.tw -inurl:iyp.com.tw -inurl:twypage.com -inurl:alltwcompany.com -inurl:zhupiter.com -inurl:twinc.com.tw\")\n",
    "print( serper_results.keys() )\n",
    "print( serper_results['knowledgeGraph'])\n",
    "print( serper_results['organic'] )\n",
    "\n",
    "\n",
    "###  SERP API  ###\n",
    "serp = SerpAPIWrapper(params = {\n",
    "    \"gl\": 'tw', \n",
    "    \"lr\": 'lang_zh-TW', \n",
    "    \"hl\": 'zh-tw',\n",
    "    \"google_domain\": \"google.com.tw\"\n",
    "}) # utilities\n",
    "# serp_results = serp.results(\"宜窩餐飲有限公司 台北市 -inurl:twincn.com -inurl:findcompany.com.tw -inurl:iyp.com.tw -inurl:twypage.com -inurl:alltwcompany.com -inurl:zhupiter.com -inurl:twinc.com.tw\")\n",
    "# serp_results = serp.results(\"吉祥餛飩麵食館 台北市 -inurl:twincn.com -inurl:findcompany.com.tw -inurl:iyp.com.tw -inurl:twypage.com -inurl:alltwcompany.com -inurl:zhupiter.com -inurl:twinc.com.tw\")\n",
    "serp_results = serp.results(\"致仙飲食店 澎湖縣 -inurl:twincn.com -inurl:findcompany.com.tw -inurl:iyp.com.tw -inurl:twypage.com -inurl:alltwcompany.com -inurl:zhupiter.com -inurl:twinc.com.tw\")\n",
    "\n",
    "\n",
    "print( serp_results.keys() )\n",
    "print( serp_results['knowledge_graph'] \n",
    "      "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "4c7290fb-931a-4f93-8469-ab4821b6c033",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n"
     ]
    },
    {
     "ename": "ValueError",
     "evalue": "An output parsing error occurred. In order to pass this error back to the agent and have it try again, pass `handle_parsing_errors=True` to the AgentExecutor. This is the error: Could not parse output: No.",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mOutputParserException\u001b[0m                     Traceback (most recent call last)",
      "File \u001b[0;32m/data1/env/py310helperbot/lib/python3.10/site-packages/langchain/agents/agent.py:1167\u001b[0m, in \u001b[0;36mAgentExecutor._iter_next_step\u001b[0;34m(self, name_to_tool_map, color_mapping, inputs, intermediate_steps, run_manager)\u001b[0m\n\u001b[1;32m   1166\u001b[0m     \u001b[38;5;66;03m# Call the LLM to see what to do.\u001b[39;00m\n\u001b[0;32m-> 1167\u001b[0m     output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43magent\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mplan\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1168\u001b[0m \u001b[43m        \u001b[49m\u001b[43mintermediate_steps\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1169\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_child\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m   1170\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1171\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1172\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m OutputParserException \u001b[38;5;28;01mas\u001b[39;00m e:\n",
      "File \u001b[0;32m/data1/env/py310helperbot/lib/python3.10/site-packages/langchain/agents/agent.py:732\u001b[0m, in \u001b[0;36mAgent.plan\u001b[0;34m(self, intermediate_steps, callbacks, **kwargs)\u001b[0m\n\u001b[1;32m    731\u001b[0m full_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mllm_chain\u001b[38;5;241m.\u001b[39mpredict(callbacks\u001b[38;5;241m=\u001b[39mcallbacks, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mfull_inputs)\n\u001b[0;32m--> 732\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moutput_parser\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mparse\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfull_output\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/data1/env/py310helperbot/lib/python3.10/site-packages/langchain/agents/output_parsers/self_ask.py:41\u001b[0m, in \u001b[0;36mSelfAskOutputParser.parse\u001b[0;34m(self, text)\u001b[0m\n\u001b[1;32m     40\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfinish_string \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m last_line:\n\u001b[0;32m---> 41\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m OutputParserException(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCould not parse output: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mtext\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m     42\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m AgentFinish({\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124moutput\u001b[39m\u001b[38;5;124m\"\u001b[39m: last_line[\u001b[38;5;28mlen\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfinish_string) :]}, text)\n",
      "\u001b[0;31mOutputParserException\u001b[0m: Could not parse output: No.",
      "\nDuring handling of the above exception, another exception occurred:\n",
      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[22], line 22\u001b[0m\n\u001b[1;32m     12\u001b[0m tools \u001b[38;5;241m=\u001b[39m [\n\u001b[1;32m     13\u001b[0m     Tool(\n\u001b[1;32m     14\u001b[0m         name\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mIntermediate Answer\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m     17\u001b[0m     )\n\u001b[1;32m     18\u001b[0m ]\n\u001b[1;32m     19\u001b[0m self_ask_with_search \u001b[38;5;241m=\u001b[39m initialize_agent(\n\u001b[1;32m     20\u001b[0m     tools, llm, agent\u001b[38;5;241m=\u001b[39mAgentType\u001b[38;5;241m.\u001b[39mSELF_ASK_WITH_SEARCH, verbose\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m     21\u001b[0m )\n\u001b[0;32m---> 22\u001b[0m \u001b[43mself_ask_with_search\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrun\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m五角味食堂\t彰化縣北斗鎮文昌里復興路臨100-1號\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/data1/env/py310helperbot/lib/python3.10/site-packages/langchain_core/_api/deprecation.py:168\u001b[0m, in \u001b[0;36mdeprecated.<locals>.deprecate.<locals>.warning_emitting_wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    166\u001b[0m     warned \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m    167\u001b[0m     emit_warning()\n\u001b[0;32m--> 168\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mwrapped\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/data1/env/py310helperbot/lib/python3.10/site-packages/langchain/chains/base.py:600\u001b[0m, in \u001b[0;36mChain.run\u001b[0;34m(self, callbacks, tags, metadata, *args, **kwargs)\u001b[0m\n\u001b[1;32m    598\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(args) \u001b[38;5;241m!=\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[1;32m    599\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m`run` supports only one positional argument.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m--> 600\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43margs\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcallbacks\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtags\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtags\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmetadata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmetadata\u001b[49m\u001b[43m)\u001b[49m[\n\u001b[1;32m    601\u001b[0m         _output_key\n\u001b[1;32m    602\u001b[0m     ]\n\u001b[1;32m    604\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m kwargs \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m args:\n\u001b[1;32m    605\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m(kwargs, callbacks\u001b[38;5;241m=\u001b[39mcallbacks, tags\u001b[38;5;241m=\u001b[39mtags, metadata\u001b[38;5;241m=\u001b[39mmetadata)[\n\u001b[1;32m    606\u001b[0m         _output_key\n\u001b[1;32m    607\u001b[0m     ]\n",
      "File \u001b[0;32m/data1/env/py310helperbot/lib/python3.10/site-packages/langchain_core/_api/deprecation.py:168\u001b[0m, in \u001b[0;36mdeprecated.<locals>.deprecate.<locals>.warning_emitting_wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    166\u001b[0m     warned \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m    167\u001b[0m     emit_warning()\n\u001b[0;32m--> 168\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mwrapped\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/data1/env/py310helperbot/lib/python3.10/site-packages/langchain/chains/base.py:383\u001b[0m, in \u001b[0;36mChain.__call__\u001b[0;34m(self, inputs, return_only_outputs, callbacks, tags, metadata, run_name, include_run_info)\u001b[0m\n\u001b[1;32m    351\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Execute the chain.\u001b[39;00m\n\u001b[1;32m    352\u001b[0m \n\u001b[1;32m    353\u001b[0m \u001b[38;5;124;03mArgs:\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    374\u001b[0m \u001b[38;5;124;03m        `Chain.output_keys`.\u001b[39;00m\n\u001b[1;32m    375\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m    376\u001b[0m config \u001b[38;5;241m=\u001b[39m {\n\u001b[1;32m    377\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcallbacks\u001b[39m\u001b[38;5;124m\"\u001b[39m: callbacks,\n\u001b[1;32m    378\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtags\u001b[39m\u001b[38;5;124m\"\u001b[39m: tags,\n\u001b[1;32m    379\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmetadata\u001b[39m\u001b[38;5;124m\"\u001b[39m: metadata,\n\u001b[1;32m    380\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrun_name\u001b[39m\u001b[38;5;124m\"\u001b[39m: run_name,\n\u001b[1;32m    381\u001b[0m }\n\u001b[0;32m--> 383\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    384\u001b[0m \u001b[43m    \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    385\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcast\u001b[49m\u001b[43m(\u001b[49m\u001b[43mRunnableConfig\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m{\u001b[49m\u001b[43mk\u001b[49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mv\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mk\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mv\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mitems\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mv\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mis\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mnot\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m}\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    386\u001b[0m \u001b[43m    \u001b[49m\u001b[43mreturn_only_outputs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mreturn_only_outputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    387\u001b[0m \u001b[43m    \u001b[49m\u001b[43minclude_run_info\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minclude_run_info\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    388\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/data1/env/py310helperbot/lib/python3.10/site-packages/langchain/chains/base.py:166\u001b[0m, in \u001b[0;36mChain.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m    164\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    165\u001b[0m     run_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e)\n\u001b[0;32m--> 166\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m    167\u001b[0m run_manager\u001b[38;5;241m.\u001b[39mon_chain_end(outputs)\n\u001b[1;32m    169\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m include_run_info:\n",
      "File \u001b[0;32m/data1/env/py310helperbot/lib/python3.10/site-packages/langchain/chains/base.py:156\u001b[0m, in \u001b[0;36mChain.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m    153\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m    154\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_validate_inputs(inputs)\n\u001b[1;32m    155\u001b[0m     outputs \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m--> 156\u001b[0m         \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call\u001b[49m\u001b[43m(\u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    157\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m new_arg_supported\n\u001b[1;32m    158\u001b[0m         \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call(inputs)\n\u001b[1;32m    159\u001b[0m     )\n\u001b[1;32m    161\u001b[0m     final_outputs: Dict[\u001b[38;5;28mstr\u001b[39m, Any] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mprep_outputs(\n\u001b[1;32m    162\u001b[0m         inputs, outputs, return_only_outputs\n\u001b[1;32m    163\u001b[0m     )\n\u001b[1;32m    164\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n",
      "File \u001b[0;32m/data1/env/py310helperbot/lib/python3.10/site-packages/langchain/agents/agent.py:1433\u001b[0m, in \u001b[0;36mAgentExecutor._call\u001b[0;34m(self, inputs, run_manager)\u001b[0m\n\u001b[1;32m   1431\u001b[0m \u001b[38;5;66;03m# We now enter the agent loop (until it returns something).\u001b[39;00m\n\u001b[1;32m   1432\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_should_continue(iterations, time_elapsed):\n\u001b[0;32m-> 1433\u001b[0m     next_step_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_take_next_step\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1434\u001b[0m \u001b[43m        \u001b[49m\u001b[43mname_to_tool_map\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1435\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcolor_mapping\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1436\u001b[0m \u001b[43m        \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1437\u001b[0m \u001b[43m        \u001b[49m\u001b[43mintermediate_steps\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1438\u001b[0m \u001b[43m        \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1439\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1440\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(next_step_output, AgentFinish):\n\u001b[1;32m   1441\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_return(\n\u001b[1;32m   1442\u001b[0m             next_step_output, intermediate_steps, run_manager\u001b[38;5;241m=\u001b[39mrun_manager\n\u001b[1;32m   1443\u001b[0m         )\n",
      "File \u001b[0;32m/data1/env/py310helperbot/lib/python3.10/site-packages/langchain/agents/agent.py:1139\u001b[0m, in \u001b[0;36mAgentExecutor._take_next_step\u001b[0;34m(self, name_to_tool_map, color_mapping, inputs, intermediate_steps, run_manager)\u001b[0m\n\u001b[1;32m   1130\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_take_next_step\u001b[39m(\n\u001b[1;32m   1131\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m   1132\u001b[0m     name_to_tool_map: Dict[\u001b[38;5;28mstr\u001b[39m, BaseTool],\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1136\u001b[0m     run_manager: Optional[CallbackManagerForChainRun] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m   1137\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Union[AgentFinish, List[Tuple[AgentAction, \u001b[38;5;28mstr\u001b[39m]]]:\n\u001b[1;32m   1138\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_consume_next_step(\n\u001b[0;32m-> 1139\u001b[0m         [\n\u001b[1;32m   1140\u001b[0m             a\n\u001b[1;32m   1141\u001b[0m             \u001b[38;5;28;01mfor\u001b[39;00m a \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_iter_next_step(\n\u001b[1;32m   1142\u001b[0m                 name_to_tool_map,\n\u001b[1;32m   1143\u001b[0m                 color_mapping,\n\u001b[1;32m   1144\u001b[0m                 inputs,\n\u001b[1;32m   1145\u001b[0m                 intermediate_steps,\n\u001b[1;32m   1146\u001b[0m                 run_manager,\n\u001b[1;32m   1147\u001b[0m             )\n\u001b[1;32m   1148\u001b[0m         ]\n\u001b[1;32m   1149\u001b[0m     )\n",
      "File \u001b[0;32m/data1/env/py310helperbot/lib/python3.10/site-packages/langchain/agents/agent.py:1139\u001b[0m, in \u001b[0;36m<listcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m   1130\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_take_next_step\u001b[39m(\n\u001b[1;32m   1131\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m   1132\u001b[0m     name_to_tool_map: Dict[\u001b[38;5;28mstr\u001b[39m, BaseTool],\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1136\u001b[0m     run_manager: Optional[CallbackManagerForChainRun] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m   1137\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Union[AgentFinish, List[Tuple[AgentAction, \u001b[38;5;28mstr\u001b[39m]]]:\n\u001b[1;32m   1138\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_consume_next_step(\n\u001b[0;32m-> 1139\u001b[0m         [\n\u001b[1;32m   1140\u001b[0m             a\n\u001b[1;32m   1141\u001b[0m             \u001b[38;5;28;01mfor\u001b[39;00m a \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_iter_next_step(\n\u001b[1;32m   1142\u001b[0m                 name_to_tool_map,\n\u001b[1;32m   1143\u001b[0m                 color_mapping,\n\u001b[1;32m   1144\u001b[0m                 inputs,\n\u001b[1;32m   1145\u001b[0m                 intermediate_steps,\n\u001b[1;32m   1146\u001b[0m                 run_manager,\n\u001b[1;32m   1147\u001b[0m             )\n\u001b[1;32m   1148\u001b[0m         ]\n\u001b[1;32m   1149\u001b[0m     )\n",
      "File \u001b[0;32m/data1/env/py310helperbot/lib/python3.10/site-packages/langchain/agents/agent.py:1178\u001b[0m, in \u001b[0;36mAgentExecutor._iter_next_step\u001b[0;34m(self, name_to_tool_map, color_mapping, inputs, intermediate_steps, run_manager)\u001b[0m\n\u001b[1;32m   1176\u001b[0m     raise_error \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m\n\u001b[1;32m   1177\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m raise_error:\n\u001b[0;32m-> 1178\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m   1179\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mAn output parsing error occurred. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m   1180\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mIn order to pass this error back to the agent and have it try \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m   1181\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124magain, pass `handle_parsing_errors=True` to the AgentExecutor. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m   1182\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mThis is the error: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mstr\u001b[39m(e)\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m   1183\u001b[0m     )\n\u001b[1;32m   1184\u001b[0m text \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mstr\u001b[39m(e)\n\u001b[1;32m   1185\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandle_parsing_errors, \u001b[38;5;28mbool\u001b[39m):\n",
      "\u001b[0;31mValueError\u001b[0m: An output parsing error occurred. In order to pass this error back to the agent and have it try again, pass `handle_parsing_errors=True` to the AgentExecutor. This is the error: Could not parse output: No."
     ]
    }
   ],
   "source": [
    "from langchain.agents import AgentType, Tool, initialize_agent\n",
    "\n",
    "instructions = \"\"\"As a helpful and rigorous retail analyst, given the provided query and a list of search results for the query,  your task is to first use store name and address to identify relevant information. After that, from the relevant information, extract `store_name`, `address`, `description`, `category`, `provide_alcohol` and `phone_number` from the found relevant information. Note that `category` can only be `小吃店`, `日式料理(含居酒屋，串燒)`, `火(鍋／爐)`, `東南亞料理(不含日韓)`, `海鮮熱炒`,  `特色餐廳(含雞、鵝、牛、羊肉)`, `傳統餐廳`, `燒烤`, `韓式料理(含火鍋，烤肉)`, `西餐廳(含美式，義式，墨式)`, `西餐廳(餐酒館、酒吧、飛鏢吧、pub、lounge bar)`, `西餐廳(土耳其、漢堡、薯條、法式、歐式、印度)` or `早餐`. According to our experience,`provide_alcohol` can be inferred based on whether a store is suitable for  scenarios such as Gathering, Chill, Enjoying Together, Drinking Freely, Winery, Wine Cellar, Wine Storage, Relaxing, Unwinding, Lyrical, Romantic, Pleasant, Stress Relief, Wine and Dine, Light Drinking Gatherings, Birthday Celebrations, Socializing, Parties, Networking, After Work Relaxation with a Drink, Relaxing Places Suitable for Drinking, Every Dish Goes Well with Beer, Shared Dishes, Dining Together, Atmosphere Suitable for Celebratory Drinking, Places Suitable for Light Drinking Gatherings with Friends, Small Shops Suitable for Relaxing and Light Drinking. `description` is a summary of key piece of evidence and reasons that lead you decide `category` and `provide_alcohol` .\n",
    "\n",
    "            It's very important to omit unrelated results. Do not make up any assumption.\n",
    "            Please think step by step, and output a single json that starts with `{` and ends with `}`. An example output json is like {\"store_name\": \"...\", \"address\": \"...\", \"description\": \"... products, service or highlights ...\", \"category\": \"...\", \"phone_number\": \"...\", \"provide_alcohol\": true or false}\n",
    "            If no relevant information has been found, simply output json with empty values.\"\"\"\n",
    "base_prompt = hub.pull(\"langchain-ai/openai-functions-template\")\n",
    "prompt = base_prompt.partial(instructions=instructions)\n",
    "llm = ChatOpenAI(temperature=0, )\n",
    "serp = SerpAPIWrapper() # utilities\n",
    "# serp.results(\"五角味食堂\t彰化縣北斗鎮文昌里復興路臨100-1號\")\n",
    "tools = [\n",
    "    Tool(\n",
    "        name=\"Intermediate Answer\",\n",
    "        func=serp.run,\n",
    "        description=\"useful for when you need to get factual information with search\",\n",
    "    )\n",
    "]\n",
    "self_ask_with_search = initialize_agent(\n",
    "    tools, llm, agent=AgentType.SELF_ASK_WITH_SEARCH, verbose=True\n",
    ")\n",
    "self_ask_with_search.run(\"五角味食堂\t彰化縣北斗鎮文昌里復興路臨100-1號\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "68b499ad-3014-4d52-a30a-d750980d030e",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "id": "3a4c34ba-7af8-4e63-aa82-946cb27651ec",
   "metadata": {},
   "source": [
    "### LCEL ###"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "03543ce2-1406-4534-8071-12e172b770a8",
   "metadata": {},
   "outputs": [],
   "source": [
    "import getpass\n",
    "import os\n",
    "\n",
    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass()\n",
    "\n",
    "from langchain_openai import ChatOpenAI\n",
    "\n",
    "model = ChatOpenAI(model=\"gpt-4\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3980df79-f7b2-465f-9c88-d6bf401eb1e2",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4505be03-1225-41bf-a62b-9bf29784a24c",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e48659bc-d39c-425e-a452-39f0c6e16428",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "72723ffe-4b96-4bfb-b9ae-9718b3da4ea6",
   "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": "3.10.14"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}