cookbook/llm_math.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "e71e720f",
   "metadata": {},
   "source": [
    "# Math chain\n",
    "\n",
    "This notebook showcases using LLMs and Python REPLs to do complex word math problems."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "44e9ba31",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
      "What is 13 raised to the .3432 power?\u001b[32;1m\u001b[1;3m\n",
      "```text\n",
      "13 ** .3432\n",
      "```\n",
      "...numexpr.evaluate(\"13 ** .3432\")...\n",
      "\u001b[0m\n",
      "Answer: \u001b[33;1m\u001b[1;3m2.4116004626599237\u001b[0m\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'Answer: 2.4116004626599237'"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from langchain.chains import LLMMathChain\n",
    "from langchain_openai import OpenAI\n",
    "\n",
    "llm = OpenAI(temperature=0)\n",
    "llm_math = LLMMathChain.from_llm(llm, verbose=True)\n",
    "\n",
    "llm_math.invoke(\"What is 13 raised to the .3432 power?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e978bb8e",
   "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": "3.11.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}