L2-Memory.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "a786c77c",
   "metadata": {},
   "source": [
    "# LangChain: Memory\n",
    "\n",
    "## Outline\n",
    "* ConversationBufferMemory\n",
    "* ConversationBufferWindowMemory\n",
    "* ConversationTokenBufferMemory\n",
    "* ConversationSummaryMemory"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1297dcd5",
   "metadata": {},
   "source": [
    "## ConversationBufferMemory"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "a1f518f5",
   "metadata": {
    "height": 132
   },
   "outputs": [],
   "source": [
    "import os\n",
    "\n",
    "from dotenv import load_dotenv, find_dotenv\n",
    "_ = load_dotenv(find_dotenv()) # read local .env file\n",
    "\n",
    "import warnings\n",
    "warnings.filterwarnings('ignore')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "20ad6fe2",
   "metadata": {
    "height": 81
   },
   "outputs": [],
   "source": [
    "from langchain.chat_models import ChatOpenAI\n",
    "from langchain.chains import ConversationChain\n",
    "from langchain.memory import ConversationBufferMemory\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "88bdf13d",
   "metadata": {
    "height": 132
   },
   "outputs": [],
   "source": [
    "llm = ChatOpenAI(temperature=0.0)\n",
    "memory = ConversationBufferMemory()\n",
    "conversation = ConversationChain(\n",
    "    llm=llm, \n",
    "    memory = memory,\n",
    "    verbose=True\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "db24677d",
   "metadata": {
    "height": 30
   },
   "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: Hi, my name is Andrew\n",
      "AI:\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "\"Hello Andrew, it's nice to meet you. My name is AI. How can I assist you today?\""
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "conversation.predict(input=\"Hi, my name is Andrew\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "cc3ef937",
   "metadata": {
    "height": 30
   },
   "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: Hi, my name is Andrew\n",
      "AI: Hello Andrew, it's nice to meet you. My name is AI. How can I assist you today?\n",
      "Human: What is 1+1?\n",
      "AI:\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'The answer to 1+1 is 2.'"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "conversation.predict(input=\"What is 1+1?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "acf3339a",
   "metadata": {
    "height": 30
   },
   "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: Hi, my name is Andrew\n",
      "AI: Hello Andrew, it's nice to meet you. My name is AI. How can I assist you today?\n",
      "Human: What is 1+1?\n",
      "AI: The answer to 1+1 is 2.\n",
      "Human: What is my name?\n",
      "AI:\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'Your name is Andrew, as you mentioned earlier.'"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "conversation.predict(input=\"What is my name?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "2529400d",
   "metadata": {
    "height": 30
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Human: Hi, my name is Andrew\n",
      "AI: Hello Andrew, it's nice to meet you. My name is AI. How can I assist you today?\n",
      "Human: What is 1+1?\n",
      "AI: The answer to 1+1 is 2.\n",
      "Human: What is my name?\n",
      "AI: Your name is Andrew, as you mentioned earlier.\n"
     ]
    }
   ],
   "source": [
    "print(memory.buffer)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "5018cb0a",
   "metadata": {
    "height": 30
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'history': \"Human: Hi, my name is Andrew\\nAI: Hello Andrew, it's nice to meet you. My name is AI. How can I assist you today?\\nHuman: What is 1+1?\\nAI: The answer to 1+1 is 2.\\nHuman: What is my name?\\nAI: Your name is Andrew, as you mentioned earlier.\"}"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "memory.load_memory_variables({})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "14219b70",
   "metadata": {
    "height": 30
   },
   "outputs": [],
   "source": [
    "memory = ConversationBufferMemory()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "a36e9905",
   "metadata": {
    "height": 47
   },
   "outputs": [],
   "source": [
    "memory.save_context({\"input\": \"Hi\"}, \n",
    "                    {\"output\": \"What's up\"})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "61631b1f",
   "metadata": {
    "height": 30
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Human: Hi\n",
      "AI: What's up\n"
     ]
    }
   ],
   "source": [
    "print(memory.buffer)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "a2fdf9ec",
   "metadata": {
    "height": 30
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'history': \"Human: Hi\\nAI: What's up\"}"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "memory.load_memory_variables({})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "7ca79256",
   "metadata": {
    "height": 47
   },
   "outputs": [],
   "source": [
    "memory.save_context({\"input\": \"Not much, just hanging\"}, \n",
    "                    {\"output\": \"Cool\"})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "890a4497",
   "metadata": {
    "height": 30
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'history': \"Human: Hi\\nAI: What's up\\nHuman: Not much, just hanging\\nAI: Cool\"}"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "memory.load_memory_variables({})"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cf98e9ff",
   "metadata": {},
   "source": [
    "## ConversationBufferWindowMemory"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "66eeccc3",
   "metadata": {
    "height": 30
   },
   "outputs": [],
   "source": [
    "from langchain.memory import ConversationBufferWindowMemory"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "3ea6233e",
   "metadata": {
    "height": 30
   },
   "outputs": [],
   "source": [
    "memory = ConversationBufferWindowMemory(k=1)               "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "dc4553fb",
   "metadata": {
    "height": 98
   },
   "outputs": [],
   "source": [
    "memory.save_context({\"input\": \"Hi\"},\n",
    "                    {\"output\": \"What's up\"})\n",
    "memory.save_context({\"input\": \"Not much, just hanging\"},\n",
    "                    {\"output\": \"Cool\"})\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "6a788403",
   "metadata": {
    "height": 30
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'history': 'Human: Not much, just hanging\\nAI: Cool'}"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "memory.load_memory_variables({})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "4087bc87",
   "metadata": {
    "height": 132
   },
   "outputs": [],
   "source": [
    "llm = ChatOpenAI(temperature=0.0)\n",
    "memory = ConversationBufferWindowMemory(k=1)\n",
    "conversation = ConversationChain(\n",
    "    llm=llm, \n",
    "    memory = memory,\n",
    "    verbose=False\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "4faaa952",
   "metadata": {
    "height": 30
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\"Hello Andrew, it's nice to meet you. My name is AI. How can I assist you today?\""
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "conversation.predict(input=\"Hi, my name is Andrew\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "bb20ddaa",
   "metadata": {
    "height": 30
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'The answer to 1+1 is 2.'"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "conversation.predict(input=\"What is 1+1?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "489b2194",
   "metadata": {
    "height": 30
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\"I'm sorry, I don't have access to that information. Could you please tell me your name?\""
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "conversation.predict(input=\"What is my name?\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d2931b92",
   "metadata": {},
   "source": [
    "## ConversationTokenBufferMemory"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "9f6d063c",
   "metadata": {
    "height": 30
   },
   "outputs": [],
   "source": [
    "#!pip install tiktoken"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "fb9020ed",
   "metadata": {
    "height": 64
   },
   "outputs": [],
   "source": [
    "from langchain.memory import ConversationTokenBufferMemory\n",
    "from langchain.llms import OpenAI\n",
    "llm = ChatOpenAI(temperature=0.0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "43582ee6",
   "metadata": {
    "height": 132
   },
   "outputs": [],
   "source": [
    "memory = ConversationTokenBufferMemory(llm=llm, max_token_limit=30)\n",
    "memory.save_context({\"input\": \"AI is what?!\"},\n",
    "                    {\"output\": \"Amazing!\"})\n",
    "memory.save_context({\"input\": \"Backpropagation is what?\"},\n",
    "                    {\"output\": \"Beautiful!\"})\n",
    "memory.save_context({\"input\": \"Chatbots are what?\"}, \n",
    "                    {\"output\": \"Charming!\"})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "284288e1",
   "metadata": {
    "height": 30
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'history': 'AI: Beautiful!\\nHuman: Chatbots are what?\\nAI: Charming!'}"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "memory.load_memory_variables({})"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5ff55d5d",
   "metadata": {},
   "source": [
    "## ConversationSummaryMemory"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "72dcf8b1",
   "metadata": {
    "height": 47
   },
   "outputs": [],
   "source": [
    "from langchain.memory import ConversationSummaryBufferMemory\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "4a5b238f",
   "metadata": {
    "height": 268
   },
   "outputs": [],
   "source": [
    "# create a long string\n",
    "schedule = \"There is a meeting at 8am with your product team. \\\n",
    "You will need your powerpoint presentation prepared. \\\n",
    "9am-12pm have time to work on your LangChain \\\n",
    "project which will go quickly because Langchain is such a powerful tool. \\\n",
    "At Noon, lunch at the italian resturant with a customer who is driving \\\n",
    "from over an hour away to meet you to understand the latest in AI. \\\n",
    "Be sure to bring your laptop to show the latest LLM demo.\"\n",
    "\n",
    "memory = ConversationSummaryBufferMemory(llm=llm, max_token_limit=100)\n",
    "memory.save_context({\"input\": \"Hello\"}, {\"output\": \"What's up\"})\n",
    "memory.save_context({\"input\": \"Not much, just hanging\"},\n",
    "                    {\"output\": \"Cool\"})\n",
    "memory.save_context({\"input\": \"What is on the schedule today?\"}, \n",
    "                    {\"output\": f\"{schedule}\"})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "2e4ecabe",
   "metadata": {
    "height": 30
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'history': \"System: The human and AI engage in small talk before discussing the day's schedule. The AI informs the human of a morning meeting with the product team, time to work on the LangChain project, and a lunch meeting with a customer interested in the latest AI developments.\"}"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "memory.load_memory_variables({})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "6728edba",
   "metadata": {
    "height": 98
   },
   "outputs": [],
   "source": [
    "conversation = ConversationChain(\n",
    "    llm=llm, \n",
    "    memory = memory,\n",
    "    verbose=True\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "9a221b1d",
   "metadata": {
    "height": 30
   },
   "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",
      "System: The human and AI engage in small talk before discussing the day's schedule. The AI informs the human of a morning meeting with the product team, time to work on the LangChain project, and a lunch meeting with a customer interested in the latest AI developments.\n",
      "Human: What would be a good demo to show?\n",
      "AI:\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "\"Based on the customer's interest in AI developments, I would suggest showcasing our latest natural language processing capabilities. We could demonstrate how our AI can accurately understand and respond to complex language queries, and even provide personalized recommendations based on the user's preferences. Additionally, we could highlight our AI's ability to learn and adapt over time, making it a valuable tool for businesses looking to improve their customer experience.\""
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "conversation.predict(input=\"What would be a good demo to show?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "bb582617",
   "metadata": {
    "height": 30
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'history': \"System: The human and AI engage in small talk before discussing the day's schedule. The AI informs the human of a morning meeting with the product team, time to work on the LangChain project, and a lunch meeting with a customer interested in the latest AI developments. The human asks what would be a good demo to show.\\nAI: Based on the customer's interest in AI developments, I would suggest showcasing our latest natural language processing capabilities. We could demonstrate how our AI can accurately understand and respond to complex language queries, and even provide personalized recommendations based on the user's preferences. Additionally, we could highlight our AI's ability to learn and adapt over time, making it a valuable tool for businesses looking to improve their customer experience.\"}"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "memory.load_memory_variables({})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4ba827aa",
   "metadata": {
    "height": 30
   },
   "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
}