langchain/docs/versioned_docs/version-0.2.x/integrations/toolkits/multion.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# MultiOn\n",
    " \n",
    "[MultiON](https://www.multion.ai/blog/multion-building-a-brighter-future-for-humanity-with-ai-agents) has built an AI Agent that can interact with a broad array of web services and applications. \n",
    "\n",
    "This notebook walks you through connecting LangChain to the `MultiOn` Client in your browser. \n",
    "\n",
    "This enables custom agentic workflow that utilize the power of MultiON agents.\n",
    " \n",
    "To use this toolkit, you will need to add `MultiOn Extension` to your browser: \n",
    "\n",
    "* Create a [MultiON account](https://app.multion.ai/login?callbackUrl=%2Fprofile). \n",
    "* Add  [MultiOn extension for Chrome](https://multion.notion.site/Download-MultiOn-ddddcfe719f94ab182107ca2612c07a5)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "%pip install --upgrade --quiet  multion langchain -q"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "MultionToolkit()"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from langchain_community.agent_toolkits import MultionToolkit\n",
    "\n",
    "toolkit = MultionToolkit()\n",
    "toolkit"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[MultionCreateSession(), MultionUpdateSession(), MultionCloseSession()]"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tools = toolkit.get_tools()\n",
    "tools"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## MultiOn Setup\n",
    "\n",
    "Once you have created an account, create an API key at https://app.multion.ai/. \n",
    "\n",
    "Login to establish connection with your extension."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Logged in.\n"
     ]
    }
   ],
   "source": [
    "# Authorize connection to your Browser extention\n",
    "import multion\n",
    "\n",
    "multion.login()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Use Multion Toolkit within an Agent\n",
    "\n",
    "This will use MultiON chrome extension to perform the desired actions.\n",
    "\n",
    "We can run the below, and view the [trace](https://smith.langchain.com/public/34aaf36d-204a-4ce3-a54e-4a0976f09670/r) to see:\n",
    "\n",
    "* The agent uses the `create_multion_session` tool\n",
    "* It then uses MultiON to execute the query"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain import hub\n",
    "from langchain.agents import AgentExecutor, create_openai_functions_agent\n",
    "from langchain_openai import ChatOpenAI"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Prompt\n",
    "instructions = \"\"\"You are an assistant.\"\"\"\n",
    "base_prompt = hub.pull(\"langchain-ai/openai-functions-template\")\n",
    "prompt = base_prompt.partial(instructions=instructions)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "# LLM\n",
    "llm = ChatOpenAI(temperature=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Agent\n",
    "agent = create_openai_functions_agent(llm, toolkit.get_tools(), prompt)\n",
    "agent_executor = AgentExecutor(\n",
    "    agent=agent,\n",
    "    tools=toolkit.get_tools(),\n",
    "    verbose=False,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING: 'new_session' is deprecated and will be removed in a future version. Use 'create_session' instead.\n",
      "WARNING: 'update_session' is deprecated and will be removed in a future version. Use 'step_session' instead.\n",
      "WARNING: 'update_session' is deprecated and will be removed in a future version. Use 'step_session' instead.\n",
      "WARNING: 'update_session' is deprecated and will be removed in a future version. Use 'step_session' instead.\n",
      "WARNING: 'update_session' is deprecated and will be removed in a future version. Use 'step_session' instead.\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'input': 'Use multion to how AlphaCodium works, a recently released code language model.',\n",
       " 'output': 'AlphaCodium is a recently released code language model that is designed to assist developers in writing code more efficiently. It is based on advanced machine learning techniques and natural language processing. AlphaCodium can understand and generate code in multiple programming languages, making it a versatile tool for developers.\\n\\nThe model is trained on a large dataset of code snippets and programming examples, allowing it to learn patterns and best practices in coding. It can provide suggestions and auto-complete code based on the context and the desired outcome.\\n\\nAlphaCodium also has the ability to analyze code and identify potential errors or bugs. It can offer recommendations for improving code quality and performance.\\n\\nOverall, AlphaCodium aims to enhance the coding experience by providing intelligent assistance and reducing the time and effort required to write high-quality code.\\n\\nFor more detailed information, you can visit the official AlphaCodium website or refer to the documentation and resources available online.\\n\\nI hope this helps! Let me know if you have any other questions.'}"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent_executor.invoke(\n",
    "    {\n",
    "        \"input\": \"Use multion to explain how AlphaCodium works, a recently released code language model.\"\n",
    "    }\n",
    ")"
   ]
  }
 ],
 "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": "3.9.16"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}