{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
      "\n",
      "Current conversation:\n",
      "\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，我可以为你提供有关我所在地区的信息。你想知道什么？'"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from langchain.llms import OpenAI\n",
    "from langchain.chains import ConversationChain\n",
    "from langchain.memory import ConversationBufferMemory\n",
    "\n",
    "llm = OpenAI(temperature=0.5)\n",
    "chain = ConversationChain(\n",
    "    llm=llm,\n",
    "    verbose=True,\n",
    "    memory=ConversationBufferMemory(ai_prefix=\"xiaobang\")\n",
    ")\n",
    "chain.predict(input=\"你好\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
      "\n",
      "Current conversation:\n",
      "Human: 你好\n",
      "xiaobang:  你好！很高兴见到你！我是一个AI，我可以为你提供有关我所在地区的信息。你想知道什么？\n",
      "Human: 北京天气怎么样\n",
      "AI:\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "' 北京的天气现在很好！今天是晴天，温度约为20摄氏度，并且有轻微的风。'"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "chain.predict(input=\"北京天气怎么样\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
      "\n",
      "Current conversation:\n",
      "Human: 你好\n",
      "xiaobang:  你好！很高兴见到你！我是一个AI，我可以为你提供有关我所在地区的信息。你想知道什么？\n",
      "Human: 北京天气怎么样\n",
      "xiaobang:  北京的天气现在很好！今天是晴天，温度约为20摄氏度，并且有轻微的风。\n",
      "Human: 天津呢\n",
      "AI:\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "' 对不起，我不知道天津的天气情况。'"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "chain.predict(input=\"天津呢\")"
   ]
  }
 ],
 "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
}