microsoft--graphrag/packages/graphrag-input/example_notebooks/input_example.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "bfd1803d",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Copyright (c) 2026 Microsoft Corporation.\n",
    "# Licensed under the MIT License."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "077a563b",
   "metadata": {},
   "source": [
    "## Markitdown support example\n",
    "\n",
    "Basic usage with the factory:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "d89952be",
   "metadata": {},
   "outputs": [],
   "source": [
    "from graphrag_input import InputConfig, InputType, create_input_reader\n",
    "from graphrag_storage import StorageConfig, create_storage\n",
    "\n",
    "config = InputConfig(\n",
    "    type=InputType.Csv,\n",
    "    text_column=\"content\",\n",
    "    title_column=\"title\",\n",
    ")\n",
    "storage = create_storage(StorageConfig(base_dir=\"./input\"))\n",
    "reader = create_input_reader(config, storage)\n",
    "documents = await reader.read_files()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "2e87b59d",
   "metadata": {},
   "outputs": [],
   "source": [
    "from graphrag_input import InputConfig, InputType, create_input_reader\n",
    "from graphrag_storage import StorageConfig, create_storage\n",
    "\n",
    "config = InputConfig(type=InputType.MarkItDown, file_pattern=\".*\\\\.pdf$\")\n",
    "storage = create_storage(StorageConfig(base_dir=\"./input\"))\n",
    "reader = create_input_reader(config, storage)\n",
    "documents = await reader.read_files()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "79fdf8cc",
   "metadata": {},
   "source": [
    "Note that when specifying column names for data extraction, we can handle nested objects (e.g., in JSON) with dot notation:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "6c62fd82",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Alice\n"
     ]
    }
   ],
   "source": [
    "from graphrag_input import get_property\n",
    "\n",
    "data = {\"user\": {\"profile\": {\"name\": \"Alice\"}}}\n",
    "name = get_property(data, \"user.profile.name\")  # Returns \"Alice\"\n",
    "\n",
    "print(name)"
   ]
  }
 ],
 "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": "3.12.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}