langchain/docs/extras/modules/data_connection/document_loaders/integrations/psychic.ipynb

{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Psychic\n",
    "This notebook covers how to load documents from `Psychic`. See [here](../../../../ecosystem/psychic.md) for more details.\n",
    "\n",
    "## Prerequisites\n",
    "1. Follow the Quick Start section in [this document](../../../../ecosystem/psychic.md)\n",
    "2. Log into the [Psychic dashboard](https://dashboard.psychic.dev/) and get your secret key\n",
    "3. Install the frontend react library into your web app and have a user authenticate a connection. The connection will be created using the connection id that you specify."
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Loading documents\n",
    "\n",
    "Use the `PsychicLoader` class to load in documents from a connection. Each connection has a connector id (corresponding to the SaaS app that was connected) and a connection id (which you passed in to the frontend library)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.0.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.1.2\u001b[0m\n",
      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n"
     ]
    }
   ],
   "source": [
    "# Uncomment this to install psychicapi if you don't already have it installed\n",
    "!poetry run pip -q install psychicapi"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.document_loaders import PsychicLoader\n",
    "from psychicapi import ConnectorId\n",
    "\n",
    "# Create a document loader for google drive. We can also load from other connectors by setting the connector_id to the appropriate value e.g. ConnectorId.notion.value\n",
    "# This loader uses our test credentials\n",
    "google_drive_loader = PsychicLoader(\n",
    "    api_key=\"7ddb61c1-8b6a-4d31-a58e-30d1c9ea480e\",\n",
    "    connector_id=ConnectorId.gdrive.value,\n",
    "    connection_id=\"google-test\",\n",
    ")\n",
    "\n",
    "documents = google_drive_loader.load()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Converting the docs to embeddings \n",
    "\n",
    "We can now convert these documents into embeddings and store them in a vector database like Chroma"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
    "from langchain.vectorstores import Chroma\n",
    "from langchain.text_splitter import CharacterTextSplitter\n",
    "from langchain.llms import OpenAI\n",
    "from langchain.chains import RetrievalQAWithSourcesChain"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
    "texts = text_splitter.split_documents(documents)\n",
    "\n",
    "embeddings = OpenAIEmbeddings()\n",
    "docsearch = Chroma.from_documents(texts, embeddings)\n",
    "chain = RetrievalQAWithSourcesChain.from_chain_type(\n",
    "    OpenAI(temperature=0), chain_type=\"stuff\", retriever=docsearch.as_retriever()\n",
    ")\n",
    "chain({\"question\": \"what is psychic?\"}, return_only_outputs=True)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.10.8"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "aee8b7b246df8f9039afb4144a1f6fd8d2ca17a180786b69acc140d282b71a49"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}