langchain/docs/modules/chains/examples/llm_checker.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# LLMCheckerChain\n",
    "This notebook showcases how to use LLMCheckerChain."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new LLMCheckerChain chain...\u001b[0m\n",
      "\n",
      "\n",
      "\u001b[1m> Entering new SequentialChain chain...\u001b[0m\n",
      "\u001b[1mChain 0\u001b[0m:\n",
      "{'statement': '\\nNone. Mammals do not lay eggs.'}\n",
      "\n",
      "\u001b[1mChain 1\u001b[0m:\n",
      "{'assertions': '\\n• Mammals reproduce using live birth\\n• Mammals do not lay eggs\\n• Animals that lay eggs are not mammals'}\n",
      "\n",
      "\u001b[1mChain 2\u001b[0m:\n",
      "{'checked_assertions': '\\n1. True\\n\\n2. True\\n\\n3. False - Mammals are a class of animals that includes animals that lay eggs, such as monotremes (platypus and echidna).'}\n",
      "\n",
      "\u001b[1mChain 3\u001b[0m:\n",
      "{'revised_statement': ' Monotremes, such as the platypus and echidna, lay the biggest eggs of any mammal.'}\n",
      "\n",
      "\n",
      "\u001b[1m> Finished SequentialChain chain.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished LLMCheckerChain chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "' Monotremes, such as the platypus and echidna, lay the biggest eggs of any mammal.'"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from langchain.chains import LLMCheckerChain\n",
    "from langchain.llms import OpenAI\n",
    "\n",
    "llm = OpenAI(temperature=0.7)\n",
    "\n",
    "text = \"What type of mammal lays the biggest eggs?\"\n",
    "\n",
    "checker_chain = LLMCheckerChain(llm=llm, verbose=True)\n",
    "\n",
    "checker_chain.run(text)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "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": "3.10.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}