microsoft--graphrag/packages/graphrag-chunking/example_notebooks/factory_helper_util_example.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "cf52b7c7",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Copyright (c) 2026 Microsoft Corporation.\n",
    "# Licensed under the MIT License."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "37a05202",
   "metadata": {},
   "source": [
    "## Using the factory via helper util example\n",
    "\n",
    "\n",
    "The create_chunker factory function provides a configuration-driven approach to instantiate chunkers by accepting a ChunkingConfig object that specifies the chunking strategy and parameters. This allows for more flexible and maintainable code by separating chunker configuration from direct instantiation."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "027e9c45",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[TextChunk(original='This is a', text='This is a', index=0, start_char=0, end_char=8, token_count=3), TextChunk(original=' test. Another', text=' test. Another', index=1, start_char=9, end_char=22, token_count=3), TextChunk(original=' sentence. And', text=' sentence. And', index=2, start_char=23, end_char=36, token_count=3), TextChunk(original=' another one.', text=' another one.', index=3, start_char=37, end_char=49, token_count=3)]\n"
     ]
    }
   ],
   "source": [
    "import tiktoken\n",
    "from graphrag_chunking.chunker_factory import create_chunker\n",
    "from graphrag_chunking.chunking_config import ChunkingConfig\n",
    "\n",
    "tokenizer = tiktoken.get_encoding(\"o200k_base\")\n",
    "config = ChunkingConfig(\n",
    "    strategy=\"tokens\",  # type: ignore\n",
    "    size=3,\n",
    "    overlap=0,\n",
    ")\n",
    "chunker = create_chunker(config, tokenizer.encode, tokenizer.decode)\n",
    "\n",
    "print(chunker.chunk(\"This is a test. Another sentence. And another one.\"))"
   ]
  }
 ],
 "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
}