langchain/docs/modules/memory/examples/motorhead_memory_managed.ipynb

{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Motörhead Memory (Managed)\n",
    "[Motörhead](https://github.com/getmetal/motorhead) is a memory server implemented in Rust. It automatically handles incremental summarization in the background and allows for stateless applications.\n",
    "\n",
    "## Setup\n",
    "\n",
    "See instructions at [Motörhead](https://docs.getmetal.io/motorhead/introduction) for running the managed version of Motorhead. You can retrieve your `api_key` and `client_id` by creating an account on [Metal](https://getmetal.io).\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.memory.motorhead_memory import MotorheadMemory\n",
    "from langchain import OpenAI, LLMChain, PromptTemplate\n",
    "\n",
    "template = \"\"\"You are a chatbot having a conversation with a human.\n",
    "\n",
    "{chat_history}\n",
    "Human: {human_input}\n",
    "AI:\"\"\"\n",
    "\n",
    "prompt = PromptTemplate(\n",
    "    input_variables=[\"chat_history\", \"human_input\"], \n",
    "    template=template\n",
    ")\n",
    "memory = MotorheadMemory(\n",
    "    api_key=\"YOUR_API_KEY\",\n",
    "    client_id=\"YOUR_CLIENT_ID\"\n",
    "    session_id=\"testing-1\",\n",
    "    memory_key=\"chat_history\"\n",
    ")\n",
    "\n",
    "await memory.init();  # loads previous state from Motörhead 🤘\n",
    "\n",
    "llm_chain = LLMChain(\n",
    "    llm=OpenAI(), \n",
    "    prompt=prompt, \n",
    "    verbose=True, \n",
    "    memory=memory,\n",
    ")\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
      "Prompt after formatting:\n",
      "\u001b[32;1m\u001b[1;3mYou are a chatbot having a conversation with a human.\n",
      "\n",
      "\n",
      "Human: hi im bob\n",
      "AI:\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "' Hi Bob, nice to meet you! How are you doing today?'"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "llm_chain.run(\"hi im bob\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
      "Prompt after formatting:\n",
      "\u001b[32;1m\u001b[1;3mYou are a chatbot having a conversation with a human.\n",
      "\n",
      "Human: hi im bob\n",
      "AI:  Hi Bob, nice to meet you! How are you doing today?\n",
      "Human: whats my name?\n",
      "AI:\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "' You said your name is Bob. Is that correct?'"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "llm_chain.run(\"whats my name?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
      "Prompt after formatting:\n",
      "\u001b[32;1m\u001b[1;3mYou are a chatbot having a conversation with a human.\n",
      "\n",
      "Human: hi im bob\n",
      "AI:  Hi Bob, nice to meet you! How are you doing today?\n",
      "Human: whats my name?\n",
      "AI:  You said your name is Bob. Is that correct?\n",
      "Human: whats for dinner?\n",
      "AI:\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "\"  I'm sorry, I'm not sure what you're asking. Could you please rephrase your question?\""
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "llm_chain.run(\"whats for dinner?\")"
   ]
  },
  {
   "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": "3.9.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}