{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain import OpenAI\n",
    "from langchain.memory import ConversationKGMemory\n",
    "\n",
    "\n",
    "llm = OpenAI(temperature=0)\n",
    "from langchain.prompts.prompt import PromptTemplate\n",
    "from langchain.chains import ConversationChain\n",
    "\n",
    "template = \"\"\"The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. \n",
    "If the AI does not know the answer to a question, it truthfully says it does not know. The AI ONLY uses information contained in the \"Relevant Information\" section and does not hallucinate.\n",
    "\n",
    "Relevant Information:\n",
    "\n",
    "{history}\n",
    "\n",
    "Conversation:\n",
    "Human: {input}\n",
    "AI:\"\"\"\n",
    "prompt = PromptTemplate(\n",
    "    input_variables=[\"history\", \"input\"], template=template\n",
    ")\n",
    "conversation_with_kg = ConversationChain(\n",
    "    llm=llm, \n",
    "    verbose=True, \n",
    "    prompt=prompt,\n",
    "    memory=ConversationKGMemory(llm=llm)\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
      "Prompt after formatting:\n",
      "\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. \n",
      "If the AI does not know the answer to a question, it truthfully says it does not know. The AI ONLY uses information contained in the \"Relevant Information\" section and does not hallucinate.\n",
      "\n",
      "Relevant Information:\n",
      "\n",
      "\n",
      "\n",
      "Conversation:\n",
      "Human: 你好\n",
      "AI:\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "' 你好！很高兴见到你。我是一个AI，我可以回答你的问题。你想问我什么？'"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "conversation_with_kg.predict(input=\"你好\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
      "Prompt after formatting:\n",
      "\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. \n",
      "If the AI does not know the answer to a question, it truthfully says it does not know. The AI ONLY uses information contained in the \"Relevant Information\" section and does not hallucinate.\n",
      "\n",
      "Relevant Information:\n",
      "\n",
      "\n",
      "\n",
      "Conversation:\n",
      "Human: 我叫李振，我正在帮助张三写作业，他是一名小学生。\n",
      "AI:\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "' 哦，你好李振！很高兴认识你。我知道张三是一名小学生，他有多大了？'"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "conversation_with_kg.predict(input=\"我叫李振，我正在帮助张三写作业，他是一名小学生。\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
      "Prompt after formatting:\n",
      "\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. \n",
      "If the AI does not know the answer to a question, it truthfully says it does not know. The AI ONLY uses information contained in the \"Relevant Information\" section and does not hallucinate.\n",
      "\n",
      "Relevant Information:\n",
      "\n",
      "On 张三: 张三 是 一名小学生.\n",
      "\n",
      "Conversation:\n",
      "Human: 关于张三，你了解多少\n",
      "AI:\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "' 我知道张三是一名小学生。'"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "conversation_with_kg.predict(input=\"关于张三，你了解多少\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "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": "3.10.10"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}