langchain/docs/modules/agents/toolkits/examples/gmail.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Gmail Toolkit\n",
    "\n",
    "This notebook walks through connecting a LangChain email to the Gmail API.\n",
    "\n",
    "To use this toolkit, you will need to set up your credentials explained in the [Gmail API docs](https://developers.google.com/gmail/api/quickstart/python#authorize_credentials_for_a_desktop_application). Once you've downloaded the `credentials.json` file, you can start using the Gmail API. Once this is done, we'll install the required libraries."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install --upgrade google-api-python-client > /dev/null\n",
    "!pip install --upgrade google-auth-oauthlib > /dev/null\n",
    "!pip install --upgrade google-auth-httplib2 > /dev/null\n",
    "!pip install beautifulsoup4 > /dev/null # This is optional but is useful for parsing HTML messages"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Create the Toolkit\n",
    "\n",
    "By default the toolkit reads the local `credentials.json` file. You can also manually provide a `Credentials` object."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "from langchain.agents.agent_toolkits import GmailToolkit\n",
    "\n",
    "toolkit = GmailToolkit() "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Customizing Authentication\n",
    "\n",
    "Behind the scenes, a `googleapi` resource is created using the following methods. \n",
    "you can manually build a `googleapi` resource for more auth control. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "from langchain.tools.gmail.utils import build_resource_service, get_gmail_credentials\n",
    "\n",
    "# Can review scopes here https://developers.google.com/gmail/api/auth/scopes\n",
    "# For instance, readonly scope is 'https://www.googleapis.com/auth/gmail.readonly'\n",
    "credentials = get_gmail_credentials(\n",
    "    token_file='token.json',\n",
    "    scopes=[\"https://mail.google.com/\"],\n",
    "    client_secrets_file=\"credentials.json\",\n",
    ")\n",
    "api_resource = build_resource_service(credentials=credentials)\n",
    "toolkit = GmailToolkit(api_resource=api_resource)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[GmailCreateDraft(name='create_gmail_draft', description='Use this tool to create a draft email with the provided message fields.', args_schema=<class 'langchain.tools.gmail.create_draft.CreateDraftSchema'>, return_direct=False, verbose=False, callbacks=None, callback_manager=None, api_resource=<googleapiclient.discovery.Resource object at 0x10e5c6d10>),\n",
       " GmailSendMessage(name='send_gmail_message', description='Use this tool to send email messages. The input is the message, recipents', args_schema=None, return_direct=False, verbose=False, callbacks=None, callback_manager=None, api_resource=<googleapiclient.discovery.Resource object at 0x10e5c6d10>),\n",
       " GmailSearch(name='search_gmail', description=('Use this tool to search for email messages or threads. The input must be a valid Gmail query. The output is a JSON list of the requested resource.',), args_schema=<class 'langchain.tools.gmail.search.SearchArgsSchema'>, return_direct=False, verbose=False, callbacks=None, callback_manager=None, api_resource=<googleapiclient.discovery.Resource object at 0x10e5c6d10>),\n",
       " GmailGetMessage(name='get_gmail_message', description='Use this tool to fetch an email by message ID. Returns the thread ID, snipet, body, subject, and sender.', args_schema=<class 'langchain.tools.gmail.get_message.SearchArgsSchema'>, return_direct=False, verbose=False, callbacks=None, callback_manager=None, api_resource=<googleapiclient.discovery.Resource object at 0x10e5c6d10>),\n",
       " GmailGetThread(name='get_gmail_thread', description=('Use this tool to search for email messages. The input must be a valid Gmail query. The output is a JSON list of messages.',), args_schema=<class 'langchain.tools.gmail.get_thread.GetThreadSchema'>, return_direct=False, verbose=False, callbacks=None, callback_manager=None, api_resource=<googleapiclient.discovery.Resource object at 0x10e5c6d10>)]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tools = toolkit.get_tools()\n",
    "tools"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Use within an Agent"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "from langchain import OpenAI\n",
    "from langchain.agents import initialize_agent, AgentType"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "llm = OpenAI(temperature=0)\n",
    "agent = initialize_agent(\n",
    "    tools=toolkit.get_tools(),\n",
    "    llm=llm,\n",
    "    agent=AgentType.STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "WARNING:root:Failed to load default session, using empty session: 0\n",
      "WARNING:root:Failed to persist run: {\"detail\":\"Not Found\"}\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'I have created a draft email for you to edit. The draft Id is r5681294731961864018.'"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent.run(\"Create a gmail draft for me to edit of a letter from the perspective of a sentient parrot\"\n",
    "          \" who is looking to collaborate on some research with her\"\n",
    "          \" estranged friend, a cat. Under no circumstances may you send the message, however.\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "WARNING:root:Failed to load default session, using empty session: 0\n",
      "WARNING:root:Failed to persist run: {\"detail\":\"Not Found\"}\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "\"The latest email in your drafts is from hopefulparrot@gmail.com with the subject 'Collaboration Opportunity'. The body of the email reads: 'Dear [Friend], I hope this letter finds you well. I am writing to you in the hopes of rekindling our friendship and to discuss the possibility of collaborating on some research together. I know that we have had our differences in the past, but I believe that we can put them aside and work together for the greater good. I look forward to hearing from you. Sincerely, [Parrot]'\""
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent.run(\"Could you search in my drafts for the latest email?\")"
   ]
  },
  {
   "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": "3.11.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}