langchain/docs/modules/indexes/text_splitters/examples/tiktoken_splitter.ipynb
Harrison Chase 705431aecc
big docs refactor (#1978)
Co-authored-by: Ankush Gola <ankush.gola@gmail.com>
2023-03-26 19:49:46 -07:00

103 lines
2.0 KiB
Plaintext

{
"cells": [
{
"cell_type": "markdown",
"id": "53049ff5",
"metadata": {},
"source": [
"# TiktokenText Splitter\n",
"\n",
"1. How the text is split: by `tiktoken` tokens\n",
"2. How the chunk size is measured: by `tiktoken` tokens"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "8c73186a",
"metadata": {},
"outputs": [],
"source": [
"# This is a long document we can split up.\n",
"with open('../../../state_of_the_union.txt') as f:\n",
" state_of_the_union = f.read()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "a1a118b1",
"metadata": {},
"outputs": [],
"source": [
"from langchain.text_splitter import TokenTextSplitter"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "ef37c5d3",
"metadata": {},
"outputs": [],
"source": [
"text_splitter = TokenTextSplitter(chunk_size=10, chunk_overlap=0)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "5750228a",
"metadata": {
"scrolled": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Madam Speaker, Madam Vice President, our\n"
]
}
],
"source": [
"texts = text_splitter.split_text(state_of_the_union)\n",
"print(texts[0])"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9a87dc30",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.9.1"
},
"vscode": {
"interpreter": {
"hash": "aee8b7b246df8f9039afb4144a1f6fd8d2ca17a180786b69acc140d282b71a49"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}