langchain/docs/modules/agents/agents/examples/openai_functions_agent.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "9502d5b0",
   "metadata": {},
   "source": [
    "# OpenAI Functions Agent\n",
    "\n",
    "This notebook showcases using an agent that uses the OpenAI functions ability"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "c0a83623",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain import LLMMathChain, OpenAI, SerpAPIWrapper, SQLDatabase, SQLDatabaseChain\n",
    "from langchain.agents import initialize_agent, Tool\n",
    "from langchain.agents import AgentType\n",
    "from langchain.chat_models import ChatOpenAI"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "6fefaba2",
   "metadata": {},
   "outputs": [],
   "source": [
    "llm = ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo-0613\")\n",
    "search = SerpAPIWrapper()\n",
    "llm_math_chain = LLMMathChain.from_llm(llm=llm, verbose=True)\n",
    "db = SQLDatabase.from_uri(\"sqlite:///../../../../../notebooks/Chinook.db\")\n",
    "db_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True)\n",
    "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",
    "    Tool(\n",
    "        name=\"Calculator\",\n",
    "        func=llm_math_chain.run,\n",
    "        description=\"useful for when you need to answer questions about math\"\n",
    "    ),\n",
    "    Tool(\n",
    "        name=\"FooBar-DB\",\n",
    "        func=db_chain.run,\n",
    "        description=\"useful for when you need to answer questions about FooBar. Input should be in the form of a question containing full context\"\n",
    "    )\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "9ff6cee9",
   "metadata": {},
   "outputs": [],
   "source": [
    "mrkl = initialize_agent(tools, llm, agent=AgentType.OPENAI_FUNCTIONS, verbose=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "ba8e4cbe",
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new  chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3m\n",
      "Invoking: `Search` with `{'query': 'Leo DiCaprio girlfriend'}`\n",
      "\n",
      "\n",
      "\u001b[0m\u001b[36;1m\u001b[1;3mAmidst his casual romance with Gigi, Leo allegedly entered a relationship with 19-year old model, Eden Polani, in February 2023.\u001b[0m\u001b[32;1m\u001b[1;3m\n",
      "Invoking: `Calculator` with `{'expression': '19^0.43'}`\n",
      "\n",
      "\n",
      "\u001b[0m\n",
      "\n",
      "\u001b[1m> Entering new  chain...\u001b[0m\n",
      "19^0.43\u001b[32;1m\u001b[1;3m```text\n",
      "19**0.43\n",
      "```\n",
      "...numexpr.evaluate(\"19**0.43\")...\n",
      "\u001b[0m\n",
      "Answer: \u001b[33;1m\u001b[1;3m3.547023357958959\u001b[0m\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "\u001b[33;1m\u001b[1;3mAnswer: 3.547023357958959\u001b[0m\u001b[32;1m\u001b[1;3mLeo DiCaprio's girlfriend is reportedly Eden Polani. Her current age raised to the power of 0.43 is approximately 3.55.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "\"Leo DiCaprio's girlfriend is reportedly Eden Polani. Her current age raised to the power of 0.43 is approximately 3.55.\""
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mrkl.run(\"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9f5f6743",
   "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": "3.9.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}