langchain/docs/extras/integrations/document_loaders/larksuite.ipynb

{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "33205b12",
   "metadata": {},
   "source": [
    "# LarkSuite (FeiShu)\n",
    "\n",
    ">[LarkSuite](https://www.larksuite.com/) is an enterprise collaboration platform developed by ByteDance.\n",
    "\n",
    "This notebook covers how to load data from the `LarkSuite` REST API into a format that can be ingested into LangChain, along with example usage for text summarization.\n",
    "\n",
    "The LarkSuite API requires an access token (tenant_access_token or user_access_token), checkout [LarkSuite open platform document](https://open.larksuite.com/document) for API details."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "90b69c94",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-06-19T10:05:03.645161Z",
     "start_time": "2023-06-19T10:04:49.541968Z"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "from getpass import getpass\n",
    "from langchain.document_loaders.larksuite import LarkSuiteDocLoader\n",
    "\n",
    "DOMAIN = input(\"larksuite domain\")\n",
    "ACCESS_TOKEN = getpass(\"larksuite tenant_access_token or user_access_token\")\n",
    "DOCUMENT_ID = input(\"larksuite document id\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "13deb0f5",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-06-19T10:05:36.016495Z",
     "start_time": "2023-06-19T10:05:35.360884Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[Document(page_content='Test Doc\\nThis is a Test Doc\\n\\n1\\n2\\n3\\n\\n', metadata={'document_id': 'V76kdbd2HoBbYJxdiNNccajunPf', 'revision_id': 11, 'title': 'Test Doc'})]\n"
     ]
    }
   ],
   "source": [
    "from pprint import pprint\n",
    "\n",
    "larksuite_loader = LarkSuiteDocLoader(DOMAIN, ACCESS_TOKEN, DOCUMENT_ID)\n",
    "docs = larksuite_loader.load()\n",
    "\n",
    "pprint(docs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9ccc1e2f",
   "metadata": {},
   "outputs": [],
   "source": [
    "# see https://python.langchain.com/docs/use_cases/summarization for more details\n",
    "from langchain.chains.summarize import load_summarize_chain\n",
    "\n",
    "chain = load_summarize_chain(llm, chain_type=\"map_reduce\")\n",
    "chain.run(docs)"
   ]
  }
 ],
 "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": 5
}