LangChainGuides/BasicAgent.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Create Your First AI Agent with LangChain\n",
    "\n",
    "Large Language Models are powerful but they have some limitations. Let's focus on 2 of them:\n",
    "- the knowledge cut-off,\n",
    "- mistakes in math.\n",
    "\n",
    "The idea for this project is use LangChain to build a basic AI Agent and give him 2 tools: Google search and a calculator.\n",
    "\n",
    "We'll use a prompting technique called **ReAct** (Reasoning & Acting).\n",
    "\n",
    "*Can our AI Agent take advantage of the toolkit we provided?*\n",
    "\n",
    "Let's find out!\n",
    "\n",
    "By following this tutorial, you'll learn how to:\n",
    "1. Create an AI agent using the LangChain library\n",
    "2. What is ReAct prompting.\n",
    "3. Use google search with agents.\n",
    "4. Use LLM math tool.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Import necessary libraries & Load Env Variables\n",
    "\n",
    "First, we need to install some packages. Just run `pip install openai langchain python-doteenv google-search-results` to install them.\n",
    "\n",
    "For the project, we'll need 2 API keys:\n",
    "1. OpenAI API key for the conversational agent. You can grab it here: https://platform.openai.com/account/api-keys\n",
    "2. SERP API key for google search. You can grab it here: https://serpapi.com/"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import os\n",
    "from dotenv import load_dotenv\n",
    "\n",
    "# load_dotenv()\n",
    "\n",
    "# Get the absolute path of the current script\n",
    "script_dir = os.path.abspath(os.getcwd())\n",
    "\n",
    "# Get the absolute path of the parent directory\n",
    "parent_dir = os.path.join(script_dir, os.pardir)\n",
    "\n",
    "dotenv_path = os.path.join(parent_dir, '.env')\n",
    "# Load the .env file from the parent directory\n",
    "load_dotenv(dotenv_path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'2a5096fc18b65b3fcab02a9bc50c45c5338d9895252875761d92b26dfb2d9181'"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "os.getenv(\"SERPAPI_API_KEY\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Using Models without Agents\n",
    "\n",
    "In this part, we'll quickly go over the standard way of using OpenAI models."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.llms import OpenAI\n",
    "\n",
    "llm = OpenAI(temperature=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'text-davinci-003'"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "llm.model_name"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'\\n\\nThe Los Angeles Lakers are the current NBA champions.'"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "llm.predict(\"Who is the current NBA champion?\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Using Chat Models"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.chat_models import ChatOpenAI\n",
    "\n",
    "chat_llm = ChatOpenAI(temperature=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'gpt-3.5-turbo'"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "chat_llm.model_name"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'As of September 2021, the current NBA champion is the Milwaukee Bucks. They won the championship in the 2020-2021 season.'"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "chat_llm.predict(\"Who is the current NBA champion?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "gpt4 = ChatOpenAI(model=\"gpt-4\", temperature=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "ChatOpenAI(client=<class 'openai.api_resources.chat_completion.ChatCompletion'>, model_name='gpt-4', temperature=0.0, openai_api_key='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', openai_api_base='', openai_organization='', openai_proxy='')"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gpt4.model_name"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'As of the end of the 2020-2021 season, the current NBA champion is the Milwaukee Bucks.'"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gpt4.predict(\"Who is the current NBA champion?\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Finding the NBA all-time leading scorer.\n",
    "\n",
    "This is a great example to test both limitations: the knowledge cut-off & math mistakes. \n",
    "\n",
    "In 2023, LeBron James surpassed Kareem Abdul-Jabbar as the NBA all-time leading scorer. So we expect GPT-4 to answer Kareem. Then we want to take the total points to the power of 0.42 to make the calculation more challenging."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'The NBA all-time leading scorer is Kareem Abdul-Jabbar with a total of 38,387 points. His total points to the power of 0.42 is approximately 137.97.'"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gpt4.predict(\"Who is the NBA all-time leading scorer? What's his total points to the power of 0.42?\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Both answers are wrong!\n",
    "1. It's LeBron James (the knowledge cut-off issue).\n",
    "2. It should be approximately 84 (bad math).\n",
    "\n",
    "Let's see if we can overcome the limitations!"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Adding the Agent\n",
    "\n",
    "We'll use an Agent that uses **Chain-of-Thought Reasoning (ReAct)**\n",
    "\n",
    "<img src=\"images/TAO.png\" alt=\"Image Alt Text\" width=\"600\">"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.agents import load_tools\n",
    "from langchain.agents import initialize_agent\n",
    "from langchain.agents import AgentType"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Standard Agent with the DaVinci model\n",
    "\n",
    "First, we'll try to use the agent for the standard LLM: `text-davinci-003`"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We give our Agent 2 tools:\n",
    "1. SEPR API for Google Search so we get the answers that are true TODAY. *Note:* requires `pip install google-search-results`\n",
    "2. `llm-math` for calculations."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "llm = OpenAI(temperature=0)\n",
    "\n",
    "# adding the tools\n",
    "tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "To apply ReAct prompting we use `agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "# initializing the agent\n",
    "agent_executor = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "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 I need to find out who won the most recent NBA championship\n",
      "Action: Search\n",
      "Action Input: \"2020 NBA Champions\"\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m{'title': 'NBA', 'rankings': 'NBA Finals', 'thumbnail': 'https://serpapi.com/searches/651bf4a095bf92492e92fdaa/images/e568f1d4e23e3a0e3359b9d7a36ae41dca170eeb5f549ee64c2318754ac54440.png', 'games': [{'tournament': 'NBA', 'arena': 'AdventHealth Arena at ESPN Wide World of Sports Complex', 'status': 'Final', 'date': 'Oct 11, 20', 'video_highlights': {'link': 'https://www.youtube.com/watch?v=czq7usfGiZY&feature=onebox', 'thumbnail': 'https://serpapi.com/searches/651bf4a095bf92492e92fdaa/images/e568f1d4e23e3a0e84b774e26c3d382125e827c5974d947a154b51dfed1f642f917191f83e557c7b70f070d3167b72fafd8cf3dbc9c5a246.jpeg', 'duration': '9:56'}, 'teams': [{'name': 'Lakers', 'score': '106', 'thumbnail': 'https://serpapi.com/searches/651bf4a095bf92492e92fdaa/images/e568f1d4e23e3a0e84b774e26c3d382187637fc68e482d3f591c4784e21ee6742f0ddf745f5e59f7b7d8288de8aa6c1a.png'}, {'name': 'Heat', 'score': '93', 'thumbnail': 'https://serpapi.com/searches/651bf4a095bf92492e92fdaa/images/e568f1d4e23e3a0e84b774e26c3d382187637fc68e482d3f5f1722c8a08cc0fdb42261d32d2de8e7408fa347b40c0a32.png'}]}, {'tournament': 'NBA', 'arena': 'AdventHealth Arena at ESPN Wide World of Sports Complex', 'status': 'Final', 'date': 'Oct 9, 20', 'video_highlights': {'link': 'https://www.youtube.com/watch?v=1S1cXaqkIRQ&feature=onebox', 'thumbnail': 'https://serpapi.com/searches/651bf4a095bf92492e92fdaa/images/e568f1d4e23e3a0e84b774e26c3d3821f8d7339a8123548d29d179aa99e7ad3d95bca9c63cbd00b761edb95f68022b4cf9375ea351bc5918.jpeg', 'duration': '9:50'}, 'teams': [{'name': 'Heat', 'score': '111', 'thumbnail': 'https://serpapi.com/searches/651bf4a095bf92492e92fdaa/images/e568f1d4e23e3a0e84b774e26c3d382196e401766691baaa194147fee974403dec7184ac912a099b06335d0a2e0fb411.png'}, {'name': 'Lakers', 'score': '108', 'thumbnail': 'https://serpapi.com/searches/651bf4a095bf92492e92fdaa/images/e568f1d4e23e3a0e84b774e26c3d382196e401766691baaa00ed72f33a1886b23eb31c8f5483d9ec73ba112e50b4ccf2.png'}]}, {'tournament': 'NBA', 'arena': 'AdventHealth Arena at ESPN Wide World of Sports Complex', 'status': 'Final', 'date': 'Oct 6, 20', 'video_highlights': {'link': 'https://www.youtube.com/watch?v=Bh90U367Ivc&feature=onebox', 'thumbnail': 'https://serpapi.com/searches/651bf4a095bf92492e92fdaa/images/e568f1d4e23e3a0e84b774e26c3d38216fffefeff5e3ed1a7719963044fb177c0e6c849af4574c9462c50285abfdd09d1fc58e8ae41f5058.jpeg', 'duration': '9:47'}, 'teams': [{'name': 'Lakers', 'score': '102', 'thumbnail': 'https://serpapi.com/searches/651bf4a095bf92492e92fdaa/images/e568f1d4e23e3a0e84b774e26c3d3821df27767a43b56f33fa677f947e39cca6d6b3316b3853de4b3734d45083f54c00.png'}, {'name': 'Heat', 'score': '96', 'thumbnail': 'https://serpapi.com/searches/651bf4a095bf92492e92fdaa/images/e568f1d4e23e3a0e84b774e26c3d3821df27767a43b56f33236747433e4c00759563e7d95f2c6b080117c2ea5987b233.png'}]}, {'tournament': 'NBA', 'arena': 'AdventHealth Arena at ESPN Wide World of Sports Complex', 'status': 'Final', 'date': 'Oct 4, 20', 'video_highlights': {'link': 'https://www.youtube.com/watch?v=yqiq97qlAwo&feature=onebox', 'thumbnail': 'https://serpapi.com/searches/651bf4a095bf92492e92fdaa/images/e568f1d4e23e3a0e84b774e26c3d38213023f22c116a9ddc99bd3feaaff4472f5fde41bbc034cbafd40e3bba9fcdcdb0307f9419ef7830d3.jpeg', 'duration': '9:53'}, 'teams': [{'name': 'Lakers', 'score': '104', 'thumbnail': 'https://serpapi.com/searches/651bf4a095bf92492e92fdaa/images/e568f1d4e23e3a0e84b774e26c3d382102d75fb5650b2b82e6d3f3109c9d4567bb4ce493c574d3c9f8f9253dc847c9c7.png'}, {'name': 'Heat', 'score': '115', 'thumbnail': 'https://serpapi.com/searches/651bf4a095bf92492e92fdaa/images/e568f1d4e23e3a0e84b774e26c3d382102d75fb5650b2b82baffbf6cff3986bc8307a26ad2dbbbc5fd316340a5a02a13.png'}]}, {'tournament': 'NBA', 'arena': 'AdventHealth Arena at ESPN Wide World of Sports Complex', 'status': 'Final', 'date': 'Oct 2, 20', 'video_highlights': {'link': 'https://www.youtube.com/watch?v=jUnCLlDTgq0&feature=onebox', 'thumbnail': 'https://serpapi.com/searches/651bf4a095bf92492e92fdaa/images/e568f1d4e23e3a0e84b774e26c3d3821583cafab94c4e7f996b06a06c41ea4b2f94b60ee71d0a5ce7018544e98824af0d8aef55b6aa0d233.jpeg', 'duration': '9:42'}, 'teams': [{'name': 'Heat', 'score': '114', 'thumbnail': 'https://serpapi.com/searches/651bf4a095bf92492e92fdaa/images/e568f1d4e23e3a0e84b774e26c3d382181d42c55d7f8a54a5083b596d3a358ab90a7292ae40698734af18cc52824ee5b.png'}, {'name': 'Lakers', 'score': '124', 'thumbnail': 'https://serpapi.com/searches/651bf4a095bf92492e92fdaa/images/e568f1d4e23e3a0e84b774e26c3d382181d42c55d7f8a54aaf29a095fe59273700bca46498ffd2314b1d72828fc0d5fb.png'}]}, {'tournament': 'NBA', 'arena': 'AdventHealth Arena at ESPN Wide World of Sports Complex', 'status': 'Final', 'date': 'Sep 30, 20', 'video_highlights': {'link': 'https://www.youtube.com/watch?v=AmwTYudvE80&feature=onebox', 'thumbnail': 'https://serpapi.com/searches/651bf4a095bf92492e92fdaa/images/e568f1d4e23e3a0e84b774e26c3d3821a19ecf3ea3ffa1f597f157e0fa25d406e8138d9778eb3e2d20e9c85e0ac5824a5c2e0f036abe2991.jpeg', 'duration': '9:51'}, 'teams': [{'name': 'Heat', 'score': '98', 'thumbnail': 'https://serpapi.com/searches/651bf4a095bf92492e92fdaa/images/e568f1d4e23e3a0e84b774e26c3d3821fcefd7c6c1ec94641f40b81c836112f953fd15b1460708989659fb17e1f55aa9.png'}, {'name': 'Lakers', 'score': '116', 'thumbnail': 'https://serpapi.com/searches/651bf4a095bf92492e92fdaa/images/e568f1d4e23e3a0e84b774e26c3d3821fcefd7c6c1ec94644bc8623d53335aadde018fbe8f6f8f9dc075f1772cdc3782.png'}]}]}\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m The Lakers have won the most recent NBA championship.\n",
      "Final Answer: The Los Angeles Lakers are the 2020 NBA Champions.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'input': 'Who is the current NBA Champion?',\n",
       " 'output': 'The Los Angeles Lakers are the 2020 NBA Champions.'}"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent_executor.invoke({\"input\": \"Who is the current NBA Champion?\"})"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**The answer is wrong!**\n",
    "\n",
    "Our Agent assumes it's 2020, so it took \"the current\" part of our prompt as 2020...\n",
    "\n",
    "Why does he assume it's 2020? Because that's when it had its knowledge cut-off."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "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 I need to find out who won the NBA title in 2023\n",
      "Action: Search\n",
      "Action Input: \"NBA title 2023\"\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m{'title': 'NBA', 'rankings': 'NBA Finals', 'thumbnail': 'https://serpapi.com/searches/651bf508c9de45d6da429b22/images/ee44ec191643b582e5669e7b39e1efa347aa52467bffd138153c2d71f3cb20a7.png', 'games': [{'tournament': 'NBA', 'arena': 'Ball Arena', 'status': 'Final', 'date': 'Jun 12, 23', 'video_highlights': {'link': 'https://www.youtube.com/watch?v=ucZZdf94LbI&feature=onebox', 'thumbnail': 'https://serpapi.com/searches/651bf508c9de45d6da429b22/images/ee44ec191643b582030df48d546e38bb0844011134d085aa11b07b134734c796c8e77ae11baf6644cfb746b936a645036ce885d36f1b4380.jpeg', 'duration': '9:51'}, 'teams': [{'name': 'Heat', 'score': '89', 'thumbnail': 'https://serpapi.com/searches/651bf508c9de45d6da429b22/images/ee44ec191643b582030df48d546e38bb811e2de0f99d7f4796efb9ecd0d2dd54a7c0c8b4ba9b7798e1459993ca3be27c.png'}, {'name': 'Nuggets', 'score': '94', 'thumbnail': 'https://serpapi.com/searches/651bf508c9de45d6da429b22/images/ee44ec191643b582030df48d546e38bb811e2de0f99d7f47766149fdc081bf83ac1f2eb863f1d656048971ff14aad6ee.png'}]}, {'tournament': 'NBA', 'arena': 'FTX Arena', 'status': 'Final', 'date': 'Jun 9, 23', 'video_highlights': {'link': 'https://www.youtube.com/watch?v=Y0p8PzJ2eMw&feature=onebox', 'thumbnail': 'https://serpapi.com/searches/651bf508c9de45d6da429b22/images/ee44ec191643b582030df48d546e38bba083b6cb574b08f79db6117aa476e797cbe00aa1c381ddeb947e0ad9d9cee4ac83cfd646cb7c4eeb.jpeg', 'duration': '9:53'}, 'teams': [{'name': 'Nuggets', 'score': '108', 'thumbnail': 'https://serpapi.com/searches/651bf508c9de45d6da429b22/images/ee44ec191643b582030df48d546e38bb1a49c22fc7661a5125e36ba033d89a6b4eecdfd342c7898543a80d16ac75d596.png'}, {'name': 'Heat', 'score': '95', 'thumbnail': 'https://serpapi.com/searches/651bf508c9de45d6da429b22/images/ee44ec191643b582030df48d546e38bb1a49c22fc7661a5158d815bbc217939023d3464acea7122dc4ce153b9b614cd5.png'}]}, {'tournament': 'NBA', 'arena': 'FTX Arena', 'status': 'Final', 'date': 'Jun 7, 23', 'video_highlights': {'link': 'https://www.youtube.com/watch?v=5_wL0QrJT_M&feature=onebox', 'thumbnail': 'https://serpapi.com/searches/651bf508c9de45d6da429b22/images/ee44ec191643b582030df48d546e38bb4f8f6ae81fcd5e5ad03df5bd239d178e7cd7430e82ce05df8426928aa1abaa69b3a0d6970ea7f256.jpeg', 'duration': '9:59'}, 'teams': [{'name': 'Nuggets', 'score': '109', 'thumbnail': 'https://serpapi.com/searches/651bf508c9de45d6da429b22/images/ee44ec191643b582030df48d546e38bb3f8d7f8e7945f22a3531bb8ff2391dcd8dc22510a6ae5ed62cfc0cf32114ade8.png'}, {'name': 'Heat', 'score': '94', 'thumbnail': 'https://serpapi.com/searches/651bf508c9de45d6da429b22/images/ee44ec191643b582030df48d546e38bb3f8d7f8e7945f22af21e5acc3b8a6bb9c1c113402b3d6ae9e6c7d982762eeda0.png'}]}, {'tournament': 'NBA', 'arena': 'Ball Arena', 'status': 'Final', 'date': 'Jun 4, 23', 'video_highlights': {'link': 'https://www.youtube.com/watch?v=pjSflSwIDEc&feature=onebox', 'thumbnail': 'https://serpapi.com/searches/651bf508c9de45d6da429b22/images/ee44ec191643b582030df48d546e38bb201dbcfc9265790626fa169414dcea61041a320d05b0fdcbd62993a70b73140b9b7f59851336cbf1.jpeg', 'duration': '9:57'}, 'teams': [{'name': 'Heat', 'score': '111', 'thumbnail': 'https://serpapi.com/searches/651bf508c9de45d6da429b22/images/ee44ec191643b582030df48d546e38bbd66aa84c8fd7496c1c507c01c5c5c1af8647112dbf58eb1321262681e03510a1.png'}, {'name': 'Nuggets', 'score': '108', 'thumbnail': 'https://serpapi.com/searches/651bf508c9de45d6da429b22/images/ee44ec191643b582030df48d546e38bbd66aa84c8fd7496c158142910d9c79f08ddf443d58799f6fb268ebee3671e882.png'}]}, {'tournament': 'NBA', 'arena': 'Ball Arena', 'status': 'Final', 'date': 'Jun 1, 23', 'video_highlights': {'link': 'https://www.youtube.com/watch?v=IQ3btTsFDTc&feature=onebox', 'thumbnail': 'https://serpapi.com/searches/651bf508c9de45d6da429b22/images/ee44ec191643b582030df48d546e38bb05256dae91a809e74394038770e3a89c39afc80f831d1a98368ab174c865d4a7df01e94c06473bb7.jpeg', 'duration': '9:59'}, 'teams': [{'name': 'Heat', 'score': '93', 'thumbnail': 'https://serpapi.com/searches/651bf508c9de45d6da429b22/images/ee44ec191643b582030df48d546e38bb8bbb8c5a20bddf2ba2f750684c98ef9c3b82122f32f88060ac6a05176d1e29c2.png'}, {'name': 'Nuggets', 'score': '104', 'thumbnail': 'https://serpapi.com/searches/651bf508c9de45d6da429b22/images/ee44ec191643b582030df48d546e38bb8bbb8c5a20bddf2b83ad12805e0514161702168fb84d71a40ad4be1e9c27afe5.png'}]}]}\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m The Nuggets won the NBA title in 2023.\n",
      "Final Answer: The Nuggets won the NBA title in 2023.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'input': 'Who won the NBA title in 2023?',\n",
       " 'output': 'The Nuggets won the NBA title in 2023.'}"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent_executor.invoke({\"input\": \"Who won the NBA title in 2023?\"})"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Although the answer is good, we had to \"force\" the Agent to type 2023 in the search."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "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 I need to find out who the NBA all-time leading scorer is and then calculate his total points to the power of 0.42\n",
      "Action: Search\n",
      "Action Input: NBA all-time leading scorer\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3mLeBron James · 38,652\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I need to calculate 38,652 to the power of 0.42\n",
      "Action: Calculator\n",
      "Action Input: 38,652^0.42\u001b[0m\n",
      "Observation: \u001b[33;1m\u001b[1;3mAnswer: 84.45244506356971\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
      "Final Answer: LeBron James is the NBA all-time leading scorer with a total points of 84.45244506356971 to the power of 0.42.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'input': \"Who is the NBA all-time leading scorer? What's his total points to the power of 0.42?\",\n",
       " 'output': 'LeBron James is the NBA all-time leading scorer with a total points of 84.45244506356971 to the power of 0.42.'}"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent_executor.invoke({\"input\": \"Who is the NBA all-time leading scorer? What's his total points to the power of 0.42?\"})"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Cool, we've got the right answer about the all-time leading scorer and the math is also correct!\n",
    "\n",
    "However... Here's another issue! It took the calculation and assigned it to Lebron's total points, which is incorrect.\n",
    "\n",
    "Can the Chat Agent do better than this?"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Agent for Chat Models + Defining Tools\n",
    "\n",
    "This time we skip the math agent."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.utilities import SerpAPIWrapper\n",
    "from langchain.agents import initialize_agent, Tool, AgentType\n",
    "\n",
    "search = SerpAPIWrapper()\n",
    "new_tools = [\n",
    "    Tool(\n",
    "        name=\"Search\",\n",
    "        func=search.run,\n",
    "        description=\"useful for when you need to answer questions about current events. You should ask targeted questions\",\n",
    "    ),\n",
    "]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "To use the Chat Agent, we need to make 2 changes:\n",
    "1. Use a Chat model - `ChatOpenAI(temperature=0)`\n",
    "2. Change the agent type to include \"chat\" - `agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mThought: I can use the Search tool to find the answer to this question.\n",
      "\n",
      "Action:\n",
      "```\n",
      "{\n",
      "  \"action\": \"Search\",\n",
      "  \"action_input\": \"current FIFA men's world champion\"\n",
      "}\n",
      "```\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3mThe reigning champions are Argentina, who won their third title at the 2022 tournament.\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3mI now know the final answer.\n",
      "Final Answer: The current FIFA men's world champion is Argentina.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "\"The current FIFA men's world champion is Argentina.\""
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from langchain.chat_models import ChatOpenAI\n",
    "\n",
    "agent = initialize_agent(\n",
    "    new_tools, \n",
    "    ChatOpenAI(temperature=0), \n",
    "    agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, \n",
    "    verbose=True, \n",
    "    # handle_parsing_errors=\"Check your output and make sure it conforms!\"\n",
    "    )\n",
    "\n",
    "agent.run(\"Who is the Current FIFA men's world champion?\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "No assumption about the year! Is it true for the NBA too?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mI should use the Search tool to find the current NBA champion.\n",
      "\n",
      "Action:\n",
      "```\n",
      "{\n",
      "  \"action\": \"Search\",\n",
      "  \"action_input\": \"current NBA champion\"\n",
      "}\n",
      "```\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3mDenver Nuggets\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3mThe observation is incorrect. I need to refine my search query to get the correct answer.\n",
      "\n",
      "Action:\n",
      "```\n",
      "{\n",
      "  \"action\": \"Search\",\n",
      "  \"action_input\": \"2021 NBA champion\"\n",
      "}\n",
      "```\n",
      "\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m{'title': 'NBA', 'rankings': 'NBA Finals', 'thumbnail': 'https://serpapi.com/searches/651bf635797ac6c57f903e77/images/3ab47b1fdc51794aaa70568c619c75b84166ca3ceb52b96b37c42934cb077e43.png', 'games': [{'tournament': 'NBA', 'arena': 'Fiserv Forum', 'status': 'Final', 'date': 'Jul 20, 21', 'video_highlights': {'link': 'https://www.youtube.com/watch?v=xxRQ5nne7fs&feature=onebox', 'thumbnail': 'https://serpapi.com/searches/651bf635797ac6c57f903e77/images/3ab47b1fdc51794a018967e8c8832584b085d5d0a2ae5b2447bb304bb85558f98be7045f3ecf4f090c70d1ea3b23c13d9bea1de32c6f6383.jpeg', 'duration': '9:57'}, 'teams': [{'name': 'Suns', 'score': '98', 'thumbnail': 'https://serpapi.com/searches/651bf635797ac6c57f903e77/images/3ab47b1fdc51794a018967e8c8832584ed98abdba16de4babd3d18e4732f57990edd0a684f563c6e5579e13cbcb188fe.png'}, {'name': 'Bucks', 'score': '105', 'thumbnail': 'https://serpapi.com/searches/651bf635797ac6c57f903e77/images/3ab47b1fdc51794a018967e8c8832584ed98abdba16de4ba010f00c0804ee9c2852c5cd0b4b40288b8c06abf2f1fa162.png'}]}, {'tournament': 'NBA', 'arena': 'Footprint Center', 'status': 'Final', 'date': 'Jul 17, 21', 'video_highlights': {'link': 'https://www.youtube.com/watch?v=NQVD6ddpwco&feature=onebox', 'thumbnail': 'https://serpapi.com/searches/651bf635797ac6c57f903e77/images/3ab47b1fdc51794a018967e8c88325847016242c23f12907bf16381f6fc5b4be51a07a38672c0a59e6f1f8948f12259cc71b2e6430951b77.jpeg', 'duration': '9:43'}, 'teams': [{'name': 'Bucks', 'score': '123', 'thumbnail': 'https://serpapi.com/searches/651bf635797ac6c57f903e77/images/3ab47b1fdc51794a018967e8c8832584abb794ddbad3352dc0b458d8d17a2c94fd025c52fc2a058f9fd26298281c5d2c.png'}, {'name': 'Suns', 'score': '119', 'thumbnail': 'https://serpapi.com/searches/651bf635797ac6c57f903e77/images/3ab47b1fdc51794a018967e8c8832584abb794ddbad3352ddef9103741314dff6d7778393e76d46f0e09ae4ae028a20a.png'}]}, {'tournament': 'NBA', 'arena': 'Fiserv Forum', 'status': 'Final', 'date': 'Jul 14, 21', 'video_highlights': {'link': 'https://www.youtube.com/watch?v=a_39qOCpDco&feature=onebox', 'thumbnail': 'https://serpapi.com/searches/651bf635797ac6c57f903e77/images/3ab47b1fdc51794a018967e8c88325849e1b5a9aa752b2c2ef4f45f32a9c68f3e67609ebccdee17779375f87c27c09333bd0ec95fcb23e08.jpeg', 'duration': '9:52'}, 'teams': [{'name': 'Suns', 'score': '103', 'thumbnail': 'https://serpapi.com/searches/651bf635797ac6c57f903e77/images/3ab47b1fdc51794a018967e8c8832584b9f5331764c4e2144fdb881f18fdef22813d081a6496108970790df8ba153da5.png'}, {'name': 'Bucks', 'score': '109', 'thumbnail': 'https://serpapi.com/searches/651bf635797ac6c57f903e77/images/3ab47b1fdc51794a018967e8c8832584b9f5331764c4e21488f463367e26217f2da4902422a10dcca39a754bca6d9196.png'}]}, {'tournament': 'NBA', 'arena': 'Fiserv Forum', 'status': 'Final', 'date': 'Jul 11, 21', 'video_highlights': {'link': 'https://www.youtube.com/watch?v=61pqEPT3MfI&feature=onebox', 'thumbnail': 'https://serpapi.com/searches/651bf635797ac6c57f903e77/images/3ab47b1fdc51794a018967e8c883258485e0d424a266c64a57b412ac25512e3205f8fab037c590ee67d81f22b8b8aa8ccb3071321e1d2ac4.jpeg', 'duration': '9:47'}, 'teams': [{'name': 'Suns', 'score': '100', 'thumbnail': 'https://serpapi.com/searches/651bf635797ac6c57f903e77/images/3ab47b1fdc51794a018967e8c8832584aaeec18136edd89eb5562522b6b727c28264c7fde651c1009d5b6d304b6371dc.png'}, {'name': 'Bucks', 'score': '120', 'thumbnail': 'https://serpapi.com/searches/651bf635797ac6c57f903e77/images/3ab47b1fdc51794a018967e8c8832584aaeec18136edd89ea9f4c3e7f6aa170e0107aa2ce691fce941204905f8174b69.png'}]}, {'tournament': 'NBA', 'arena': 'Footprint Center', 'status': 'Final', 'date': 'Jul 8, 21', 'video_highlights': {'link': 'https://www.youtube.com/watch?v=oJZrEOmctc4&feature=onebox', 'thumbnail': 'https://serpapi.com/searches/651bf635797ac6c57f903e77/images/3ab47b1fdc51794a018967e8c8832584cfa5949c0fc8e421aae4a88740bba7e02fabb3fa28dcd30e90ca4809a29f393ded5cedb18f99352c.jpeg', 'duration': '9:51'}, 'teams': [{'name': 'Bucks', 'score': '108', 'thumbnail': 'https://serpapi.com/searches/651bf635797ac6c57f903e77/images/3ab47b1fdc51794a018967e8c88325842fc2d354f35bcc85fbb4f72c610a68473d469965e3106a432e70156dd4f8427a.png'}, {'name': 'Suns', 'score': '118', 'thumbnail': 'https://serpapi.com/searches/651bf635797ac6c57f903e77/images/3ab47b1fdc51794a018967e8c88325842fc2d354f35bcc857226c45b5b32dd23c873e923f01d91721b5c94fb5ccd3183.png'}]}, {'tournament': 'NBA', 'arena': 'Footprint Center', 'status': 'Final', 'date': 'Jul 6, 21', 'video_highlights': {'link': 'https://www.youtube.com/watch?v=Fm5lzr1J25Y&feature=onebox', 'thumbnail': 'https://serpapi.com/searches/651bf635797ac6c57f903e77/images/3ab47b1fdc51794a018967e8c8832584e48ec1615e597948d8ecf9b2fe8036d4de0b23efc2dbc36ab47aa72830c8cf14920c5006d453a0b7.jpeg', 'duration': '9:58'}, 'teams': [{'name': 'Bucks', 'score': '105', 'thumbnail': 'https://serpapi.com/searches/651bf635797ac6c57f903e77/images/3ab47b1fdc51794a018967e8c8832584a93d29ce32b2cdaf84344ac3fa976d936e213c57a76046bcc173fbcb5185d723.png'}, {'name': 'Suns', 'score': '118', 'thumbnail': 'https://serpapi.com/searches/651bf635797ac6c57f903e77/images/3ab47b1fdc51794a018967e8c8832584a93d29ce32b2cdaff1ea95e65dac1b021c56abb3bb4442c320d2edae4cd452c0.png'}]}]}\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3mThe observation shows that the Milwaukee Bucks are the current NBA champions. \n",
      "\n",
      "Final Answer: The Milwaukee Bucks are the current NBA champions.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'The Milwaukee Bucks are the current NBA champions.'"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent.run(\"Who is the current NBA champion?\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "I absolutely love this example because it shows that Agent's aren't perfect!\n",
    "\n",
    "Look at the first \"Thought\" part. It says: **The observation is incorrect** although it was correct!\n",
    "\n",
    "I don't know why our model did it. I assume it was because it didn't match the answer from 2021...\n",
    "\n",
    "I've ran the code previously and it ended up giving me Denver Nuggets.\n",
    "\n",
    "But this time was different. The Agent started the second iteration typing \"2021 NBA champion\" in google search."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Will it handle our math question?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mQuestion: Who is the NBA all-time leading scorer? What's his total points to the power of 0.42?\n",
      "Thought: I can use the Search tool to find the answer to the first question and then calculate the second part using a calculator.\n",
      "Action:\n",
      "```\n",
      "{\n",
      "  \"action\": \"Search\",\n",
      "  \"action_input\": \"NBA all-time leading scorer\"\n",
      "}\n",
      "```\n",
      "\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3mLeBron James · 38,652\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3mI have found that LeBron James is the NBA all-time leading scorer with 38,652 points. Now I can calculate his total points to the power of 0.42 using a calculator.\n",
      "Action:\n",
      "```\n",
      "{\n",
      "  \"action\": \"Search\",\n",
      "  \"action_input\": \"38652^0.42\"\n",
      "}\n",
      "```\n",
      "\n",
      "\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m84.45244506356968\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3mI have calculated that LeBron James' total points to the power of 0.42 is approximately 84.45244506356968.\n",
      "Final Answer: LeBron James is the NBA all-time leading scorer with 38,652 points and his total points to the power of 0.42 is approximately 84.45244506356968.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'LeBron James is the NBA all-time leading scorer with 38,652 points and his total points to the power of 0.42 is approximately 84.45244506356968.'"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent.run(\"Who is the NBA all-time leading scorer? What's his total points to the power of 0.42?\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Awesome! Everything is great here!"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Creating GPT-4 AI Agent\n",
    "\n",
    "Let's test the same but for GPT-4. Let's try to add the calculator as a tool as well."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.utilities import SerpAPIWrapper\n",
    "from langchain.agents import initialize_agent, Tool, AgentType, load_tools\n",
    "from langchain.chat_models import ChatOpenAI\n",
    "\n",
    "search = SerpAPIWrapper()\n",
    "\n",
    "gpt4 = ChatOpenAI(model=\"gpt-4\", temperature=0)\n",
    "\n",
    "# create the serp tool\n",
    "serp_tool = Tool(\n",
    "        name=\"Search\",\n",
    "        func=search.run,\n",
    "        description=\"useful for when you need to answer questions about current events. You should ask targeted questions\",\n",
    "    )\n",
    "\n",
    "# Initialize tools with calculator and the model\n",
    "gpt4_tools = load_tools([\"llm-math\"], llm=gpt4)\n",
    "# add the serp tool\n",
    "gpt4_tools = gpt4_tools + [serp_tool]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mThought: I need to find out the current FIFA men's world champion. I can use the Search tool to find this information.\n",
      "Action:\n",
      "```\n",
      "{\n",
      "  \"action\": \"Search\",\n",
      "  \"action_input\": \"Current FIFA men's world champion\"\n",
      "}\n",
      "```\u001b[0m\n",
      "Observation: \u001b[33;1m\u001b[1;3mThe reigning champions are Argentina, who won their third title at the 2022 tournament.\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3mI now know the final answer.\n",
      "Final Answer: The current FIFA men's world champion is Argentina.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "\"The current FIFA men's world champion is Argentina.\""
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# initialize GPT-4 Agent\n",
    "gpt4agent = initialize_agent(\n",
    "    gpt4_tools, \n",
    "    ChatOpenAI(model=\"gpt-4\", temperature=0), \n",
    "    agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, \n",
    "    verbose=True, \n",
    "    # handle_parsing_errors=\"Check your output and make sure it conforms!\"\n",
    "    )\n",
    "\n",
    "gpt4agent.run(\"Who is the Current FIFA men's world champion?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mThought: I need to find out who the current NBA champion is. I can use the Search tool to find this information.\n",
      "Action:\n",
      "```\n",
      "{\n",
      "  \"action\": \"Search\",\n",
      "  \"action_input\": \"current NBA champion\"\n",
      "}\n",
      "```\u001b[0m\n",
      "Observation: \u001b[33;1m\u001b[1;3mDenver Nuggets\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3mThe search results show that the current NBA champion is the Denver Nuggets.\n",
      "Final Answer: The current NBA champion is the Denver Nuggets.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'The current NBA champion is the Denver Nuggets.'"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gpt4agent.run(\"Who is the current NBA champion?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mThought: I need to find out who the NBA all-time leading scorer is and how many total points he scored. I will use the Search tool to find this information.\n",
      "Action:\n",
      "```\n",
      "{\n",
      "  \"action\": \"Search\",\n",
      "  \"action_input\": \"NBA all-time leading scorer and total points\"\n",
      "}\n",
      "```\u001b[0m\n",
      "Observation: \u001b[33;1m\u001b[1;3mLeBron James points tracker: NBA's all-time top scorer closing in on 47,000 career points. Team USA's two-time Olympic gold medallist broke the career NBA regular season points scoring record held by Kareem Abdul-Jabbar. Basketball hero LeBron James is now the NBA's all-time top scorer.\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3mThe NBA all-time leading scorer is LeBron James. However, the total points mentioned is not specific and seems to be an approximation. I need to find the exact total points scored by LeBron James. I will use the Search tool again to find this information.\n",
      "Action:\n",
      "```\n",
      "{\n",
      "  \"action\": \"Search\",\n",
      "  \"action_input\": \"LeBron James total NBA points\"\n",
      "}\n",
      "```\u001b[0m\n",
      "Observation: \u001b[33;1m\u001b[1;3m38,652\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3mLeBron James has scored a total of 38,652 points in the NBA. Now I need to calculate 38,652 to the power of 0.42. I will use the Calculator tool for this.\n",
      "Action:\n",
      "```\n",
      "{\n",
      "  \"action\": \"Calculator\",\n",
      "  \"action_input\": \"38652^0.42\"\n",
      "}\n",
      "```\n",
      "\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3mAnswer: 84.45244506356971\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3mI now know the final answer. LeBron James is the NBA all-time leading scorer and 38,652 points to the power of 0.42 is approximately 84.45. \n",
      "Final Answer: The NBA all-time leading scorer is LeBron James and 38,652 points to the power of 0.42 is approximately 84.45.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'The NBA all-time leading scorer is LeBron James and 38,652 points to the power of 0.42 is approximately 84.45.'"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gpt4agent.run(\"Who is the NBA all-time leading scorer? What's his total points to the power of 0.42?\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Asking about the Volleyball\n",
    "\n",
    "Volleyball is the second or third most popular sport in Poland. But it's a niche sport in other countries. So I was curious how our models will handle the question about the European Champions.\n",
    "\n",
    "And this question has 1 more interesting part. European Championships took place in September 2021. Which is very close to the knowledge cut-off for our GPT models..."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\"As of September 2021, the current men's volleyball European champion is Serbia. They won the title in 2019 by defeating Slovenia in the final.\""
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "chat_llm.predict(\"Who is the current men's volleyball european champion?\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Cool, GPT-3.5 answered with the 2019 champions. So it has no information about the 2021 results. How about GPT-4?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\"As of my last update in October 2021, the current men's volleyball European champion is Slovenia. They won the 2021 Men's European Volleyball Championship.\""
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gpt4.predict(\"Who is the current men's volleyball european champion?\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Wrong!\n",
    "\n",
    "Slovenia has lost against Italy in the finals...\n",
    "\n",
    "Can our Agent find the correct and updated answer??"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mThought: I can use the Search tool to find the current men's volleyball European champion.\n",
      "\n",
      "Action:\n",
      "```\n",
      "{\n",
      "  \"action\": \"Search\",\n",
      "  \"action_input\": \"current men's volleyball European champion\"\n",
      "}\n",
      "```\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3mThe initial gap between championships was variable, but since 1975 they have been awarded every two years. The current champion is Poland, which won its second title at the 2023 tournament.\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3mThe current men's volleyball European champion is Poland.\n",
      "\n",
      "Final Answer: Poland\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'Poland'"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent.run(\"Who is the current men's volleyball european champion?\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Yes, it can!"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Conclusions\n",
    "\n",
    "So I hope this notebook gave you some hands-on experience with AI Agents that you can easily build with LangChain."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "langchain",
   "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": "3.9.17"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}