{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a href=\"https://colab.research.google.com/github/run-llama/llama_index/blob/main/docs/examples/data_connectors/GithubRepositoryReaderDemo.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Github Repo Reader"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "If you're opening this Notebook on colab, you will probably need to install LlamaIndex 🦙."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%pip install llama-index-readers-github"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install llama-index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# This is due to the fact that we use asyncio.loop_until_complete in\n",
    "# the DiscordReader. Since the Jupyter kernel itself runs on\n",
    "# an event loop, we need to add some help with nesting\n",
    "import nest_asyncio\n",
    "\n",
    "nest_asyncio.apply()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "env: OPENAI_API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx\n"
     ]
    }
   ],
   "source": [
    "%env OPENAI_API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx\n",
    "from llama_index.core import VectorStoreIndex\n",
    "from llama_index.readers.github import GithubRepositoryReader, GithubClient\n",
    "from IPython.display import Markdown, display\n",
    "import os"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%env GITHUB_TOKEN=github_pat_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx\n",
    "github_token = os.environ.get(\"GITHUB_TOKEN\")\n",
    "owner = \"jerryjliu\"\n",
    "repo = \"llama_index\"\n",
    "branch = \"main\"\n",
    "\n",
    "github_client = GithubClient(github_token=github_token, verbose=True)\n",
    "\n",
    "documents = GithubRepositoryReader(\n",
    "    github_client=github_client,\n",
    "    owner=owner,\n",
    "    repo=repo,\n",
    "    use_parser=False,\n",
    "    verbose=False,\n",
    "    filter_directories=(\n",
    "        [\"docs\"],\n",
    "        GithubRepositoryReader.FilterType.INCLUDE,\n",
    "    ),\n",
    "    filter_file_extensions=(\n",
    "        [\n",
    "            \".png\",\n",
    "            \".jpg\",\n",
    "            \".jpeg\",\n",
    "            \".gif\",\n",
    "            \".svg\",\n",
    "            \".ico\",\n",
    "            \"json\",\n",
    "            \".ipynb\",\n",
    "        ],\n",
    "        GithubRepositoryReader.FilterType.EXCLUDE,\n",
    "    ),\n",
    ").load_data(branch=branch)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "index = VectorStoreIndex.from_documents(documents)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "query_engine = index.as_query_engine()\n",
    "response = query_engine.query(\n",
    "    \"What is the difference between VectorStoreIndex and SummaryIndex?\",\n",
    "    verbose=True,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "display(Markdown(f\"<b>{response}</b>\"))"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "llama_index-github-reader",
   "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"
  },
  "vscode": {
   "interpreter": {
    "hash": "5bc2ab08ee48b6366504a28e3231c27a37c154a347ee8ac6184b716eff7bdbcd"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}