mirror of
				https://github.com/hwchase17/langchain.git
				synced 2025-11-04 10:10:09 +00:00 
			
		
		
		
	Big docs refactor! Motivation is to make it easier for people to find resources they are looking for. To accomplish this, there are now three main sections: - Getting Started: steps for getting started, walking through most core functionality - Modules: these are different modules of functionality that langchain provides. Each part here has a "getting started", "how to", "key concepts" and "reference" section (except in a few select cases where it didnt easily fit). - Use Cases: this is to separate use cases (like summarization, question answering, evaluation, etc) from the modules, and provide a different entry point to the code base. There is also a full reference section, as well as extra resources (glossary, gallery, etc) Co-authored-by: Shreya Rajpal <ShreyaR@users.noreply.github.com>
		
			
				
	
	
		
			98 lines
		
	
	
		
			2.5 KiB
		
	
	
	
		
			Plaintext
		
	
	
	
	
	
			
		
		
	
	
			98 lines
		
	
	
		
			2.5 KiB
		
	
	
	
		
			Plaintext
		
	
	
	
	
	
{
 | 
						|
 "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
 | 
						|
}
 |