langchain/docs/extras/modules/agents/how_to/add_memory_openai_functions.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "0c9954e9",
   "metadata": {},
   "source": [
    "# Add Memory to OpenAI Functions Agent\n",
    "\n",
    "This notebook goes over how to add memory to OpenAI Functions agent."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "ac594f26",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/harrisonchase/.pyenv/versions/3.9.1/envs/langchain/lib/python3.9/site-packages/deeplake/util/check_latest_version.py:32: UserWarning: A newer version of deeplake (3.6.4) is available. It's recommended that you update to the latest version using `pip install -U deeplake`.\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "from langchain import (\n",
    "    LLMMathChain,\n",
    "    OpenAI,\n",
    "    SerpAPIWrapper,\n",
    "    SQLDatabase,\n",
    "    SQLDatabaseChain,\n",
    ")\n",
    "from langchain.agents import initialize_agent, Tool\n",
    "from langchain.agents import AgentType\n",
    "from langchain.chat_models import ChatOpenAI"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "1e7844e7",
   "metadata": {},
   "outputs": [],
   "source": [
    "llm = ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo-0613\")\n",
    "search = SerpAPIWrapper()\n",
    "llm_math_chain = LLMMathChain.from_llm(llm=llm, verbose=True)\n",
    "db = SQLDatabase.from_uri(\"sqlite:///../../../../../notebooks/Chinook.db\")\n",
    "db_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True)\n",
    "tools = [\n",
    "    Tool(\n",
    "        name=\"Search\",\n",
    "        func=search.run,\n",
    "        description=\"useful for when you need to answer questions about current events. You should ask targeted questions\",\n",
    "    ),\n",
    "    Tool(\n",
    "        name=\"Calculator\",\n",
    "        func=llm_math_chain.run,\n",
    "        description=\"useful for when you need to answer questions about math\",\n",
    "    ),\n",
    "    Tool(\n",
    "        name=\"FooBar-DB\",\n",
    "        func=db_chain.run,\n",
    "        description=\"useful for when you need to answer questions about FooBar. Input should be in the form of a question containing full context\",\n",
    "    ),\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "54ca3b82",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.prompts import MessagesPlaceholder\n",
    "from langchain.memory import ConversationBufferMemory\n",
    "agent_kwargs = {\n",
    "    \"extra_prompt_messages\": [MessagesPlaceholder(variable_name=\"memory\")],\n",
    "}\n",
    "memory = ConversationBufferMemory(memory_key=\"memory\", return_messages=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "81af5658",
   "metadata": {},
   "outputs": [],
   "source": [
    "agent = initialize_agent(\n",
    "    tools, \n",
    "    llm, \n",
    "    agent=AgentType.OPENAI_FUNCTIONS, \n",
    "    verbose=True, \n",
    "    agent_kwargs=agent_kwargs, \n",
    "    memory=memory\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "8ab08f43",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new  chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mHello! How can I assist you today?\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'Hello! How can I assist you today?'"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent.run(\"hi\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "520a81f4",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new  chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mNice to meet you, Bob! How can I help you today?\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'Nice to meet you, Bob! How can I help you today?'"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent.run(\"my name is bob\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "8bc4a69f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new  chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mYour name is Bob.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'Your name is Bob.'"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent.run(\"whats my name\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "40def1b7",
   "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": 5
}