mirror of
https://github.com/hwchase17/langchain
synced 2024-10-31 15:20:26 +00:00
d84a3bcf7a
#### Background With the development of [structured tools](https://blog.langchain.dev/structured-tools/), the LangChain team expanded the platform's functionality to meet the needs of new applications. The GMail tool, empowered by structured tools, now supports multiple arguments and powerful search capabilities, demonstrating LangChain's ability to interact with dynamic data sources like email servers. #### Challenge The current GMail tool only supports GMail, while users often utilize other email services like Outlook in Office365. Additionally, the proposed calendar tool in PR https://github.com/hwchase17/langchain/pull/652 only works with Google Calendar, not Outlook. #### Changes This PR implements an Office365 integration for LangChain, enabling seamless email and calendar functionality with a single authentication process. #### Future Work With the core Office365 integration complete, future work could include integrating other Office365 tools such as Tasks and Address Book. #### Who can review? @hwchase17 or @vowelparrot can review this PR #### Appendix @janscas, I utilized your [O365](https://github.com/O365/python-o365) library extensively. Given the rising popularity of LangChain and similar AI frameworks, the convergence of libraries like O365 and tools like this one is likely. So, I wanted to keep you updated on our progress. --------- Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
239 lines
8.6 KiB
Plaintext
239 lines
8.6 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Office365 Toolkit\n",
|
|
"\n",
|
|
"This notebook walks through connecting LangChain to Office365 email and calendar.\n",
|
|
"\n",
|
|
"To use this toolkit, you will need to set up your credentials explained in the [Microsoft Graph authentication and authorization overview](https://learn.microsoft.com/en-us/graph/auth/). Once you've received a CLIENT_ID and CLIENT_SECRET, you can input them as environmental variables below."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"!pip install --upgrade O365 > /dev/null\n",
|
|
"!pip install beautifulsoup4 > /dev/null # This is optional but is useful for parsing HTML messages"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Assign Environmental Variables\n",
|
|
"\n",
|
|
"The toolkit will read the CLIENT_ID and CLIENT_SECRET environmental variables to authenticate the user so you need to set them here. You will also need to set your OPENAI_API_KEY to use the agent later."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Set environmental variables here"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Create the Toolkit and Get Tools\n",
|
|
"\n",
|
|
"To start, you need to create the toolkit, so you can access its tools later."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"[O365SearchEvents(name='events_search', description=\" Use this tool to search for the user's calendar events. The input must be the start and end datetimes for the search query. The output is a JSON list of all the events in the user's calendar between the start and end times. You can assume that the user can not schedule any meeting over existing meetings, and that the user is busy during meetings. Any times without events are free for the user. \", args_schema=<class 'langchain.tools.office365.events_search.SearchEventsInput'>, return_direct=False, verbose=False, callbacks=None, callback_manager=None, handle_tool_error=False, account=Account Client Id: f32a022c-3c4c-4d10-a9d8-f6a9a9055302),\n",
|
|
" O365CreateDraftMessage(name='create_email_draft', description='Use this tool to create a draft email with the provided message fields.', args_schema=<class 'langchain.tools.office365.create_draft_message.CreateDraftMessageSchema'>, return_direct=False, verbose=False, callbacks=None, callback_manager=None, handle_tool_error=False, account=Account Client Id: f32a022c-3c4c-4d10-a9d8-f6a9a9055302),\n",
|
|
" O365SearchEmails(name='messages_search', description='Use this tool to search for email messages. The input must be a valid Microsoft Graph v1.0 $search query. The output is a JSON list of the requested resource.', args_schema=<class 'langchain.tools.office365.messages_search.SearchEmailsInput'>, return_direct=False, verbose=False, callbacks=None, callback_manager=None, handle_tool_error=False, account=Account Client Id: f32a022c-3c4c-4d10-a9d8-f6a9a9055302),\n",
|
|
" O365SendEvent(name='send_event', description='Use this tool to create and send an event with the provided event fields.', args_schema=<class 'langchain.tools.office365.send_event.SendEventSchema'>, return_direct=False, verbose=False, callbacks=None, callback_manager=None, handle_tool_error=False, account=Account Client Id: f32a022c-3c4c-4d10-a9d8-f6a9a9055302),\n",
|
|
" O365SendMessage(name='send_email', description='Use this tool to send an email with the provided message fields.', args_schema=<class 'langchain.tools.office365.send_message.SendMessageSchema'>, return_direct=False, verbose=False, callbacks=None, callback_manager=None, handle_tool_error=False, account=Account Client Id: f32a022c-3c4c-4d10-a9d8-f6a9a9055302)]"
|
|
]
|
|
},
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"from langchain.agents.agent_toolkits import O365Toolkit\n",
|
|
"\n",
|
|
"toolkit = O365Toolkit()\n",
|
|
"tools = toolkit.get_tools()\n",
|
|
"tools"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Use within an Agent"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain import OpenAI\n",
|
|
"from langchain.agents import initialize_agent, AgentType"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"llm = OpenAI(temperature=0)\n",
|
|
"agent = initialize_agent(\n",
|
|
" tools=toolkit.get_tools(),\n",
|
|
" llm=llm,\n",
|
|
" verbose=False,\n",
|
|
" agent=AgentType.STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION,\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'The draft email was created correctly.'"
|
|
]
|
|
},
|
|
"execution_count": 6,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"agent.run(\"Create an email 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": 12,
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"\"I found one draft in your drafts folder about collaboration. It was sent on 2023-06-16T18:22:17+0000 and the subject was 'Collaboration Request'.\""
|
|
]
|
|
},
|
|
"execution_count": 12,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"agent.run(\"Could you search in my drafts folder and let me know if any of them are about collaboration?\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 8,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"/home/vscode/langchain-py-env/lib/python3.11/site-packages/O365/utils/windows_tz.py:639: PytzUsageWarning: The zone attribute is specific to pytz's interface; please migrate to a new time zone provider. For more details on how to do so, see https://pytz-deprecation-shim.readthedocs.io/en/latest/migration.html\n",
|
|
" iana_tz.zone if isinstance(iana_tz, tzinfo) else iana_tz)\n",
|
|
"/home/vscode/langchain-py-env/lib/python3.11/site-packages/O365/utils/utils.py:463: PytzUsageWarning: The zone attribute is specific to pytz's interface; please migrate to a new time zone provider. For more details on how to do so, see https://pytz-deprecation-shim.readthedocs.io/en/latest/migration.html\n",
|
|
" timezone = date_time.tzinfo.zone if date_time.tzinfo is not None else None\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'I have scheduled a meeting with a sentient parrot to discuss research collaborations on October 3, 2023 at 2 pm Easter Time. Please let me know if you need to make any changes.'"
|
|
]
|
|
},
|
|
"execution_count": 8,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"agent.run(\"Can you schedule a 30 minute meeting with a sentient parrot to discuss research collaborations on October 3, 2023 at 2 pm Easter Time?\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 9,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"\"Yes, you have an event on October 3, 2023 with a sentient parrot. The event is titled 'Meeting with sentient parrot' and is scheduled from 6:00 PM to 6:30 PM.\""
|
|
]
|
|
},
|
|
"execution_count": 9,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"agent.run(\"Can you tell me if I have any events on October 3, 2023 in Eastern Time, and if so, tell me if any of them are with a sentient parrot?\")"
|
|
]
|
|
}
|
|
],
|
|
"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": 4
|
|
}
|