chore: import upstream snapshot with attribution

2026-07-13 12:37:31 +08:00
commit 6b7e6b44f1
897 changed files with 94808 additions and 0 deletions
@@ -0,0 +1,60 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a91f3280",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Copyright (c) 2026 Microsoft Corporation.\n",
+    "# Licensed under the MIT License."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3f76dc60",
+   "metadata": {},
+   "source": [
+    "## Basic sentence chunking with nltk\n",
+    "\n",
+    "The SentenceChunker class splits text into individual sentences by identifying sentence boundaries. It takes input text and returns a list where each element is a separate sentence, making it easy to process text at the sentence level."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4c96d3cc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from graphrag_chunking.sentence_chunker import SentenceChunker\n",
+    "\n",
+    "chunker = SentenceChunker()\n",
+    "chunks = chunker.chunk(\"This is a test. Another sentence.\")\n",
+    "print(chunks)  # [\"This is a test.\", \"Another sentence.\"]"
+   ]
+  }
+ ],
+ "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
+}