|
|
|
@ -1,7 +1,6 @@
|
|
|
|
|
{
|
|
|
|
|
"cells": [
|
|
|
|
|
{
|
|
|
|
|
"attachments": {},
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"id": "b118c9dc",
|
|
|
|
|
"metadata": {},
|
|
|
|
@ -476,18 +475,67 @@
|
|
|
|
|
"print(texts[0])"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"id": "53049ff5",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"## Token Text Splitter"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
"execution_count": null,
|
|
|
|
|
"execution_count": 2,
|
|
|
|
|
"id": "a1a118b1",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"from langchain.text_splitter import TokenTextSplitter"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
"execution_count": 6,
|
|
|
|
|
"id": "ef37c5d3",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"text_splitter = TokenTextSplitter(chunk_size=10, chunk_overlap=0)"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
"execution_count": 7,
|
|
|
|
|
"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": "0905c1de",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": []
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"metadata": {
|
|
|
|
|
"kernelspec": {
|
|
|
|
|
"display_name": "Python 3",
|
|
|
|
|
"display_name": "Python 3 (ipykernel)",
|
|
|
|
|
"language": "python",
|
|
|
|
|
"name": "python3"
|
|
|
|
|
},
|
|
|
|
@ -501,7 +549,7 @@
|
|
|
|
|
"name": "python",
|
|
|
|
|
"nbconvert_exporter": "python",
|
|
|
|
|
"pygments_lexer": "ipython3",
|
|
|
|
|
"version": "3.9.12 (main, Mar 26 2022, 15:51:15) \n[Clang 13.1.6 (clang-1316.0.21.2)]"
|
|
|
|
|
"version": "3.10.9"
|
|
|
|
|
},
|
|
|
|
|
"vscode": {
|
|
|
|
|
"interpreter": {
|
|
|
|
|