Harrison/html splitter (#5468)

Co-authored-by: David Revillas <26328973+r3v1@users.noreply.github.com>
This commit is contained in:
Harrison Chase 2023-05-30 21:06:07 -07:00 committed by GitHub
parent 1671c2afb2
commit f72bb966f8
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 211 additions and 0 deletions

View File

@ -0,0 +1,172 @@
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"id": "80f6cd99",
"metadata": {},
"source": [
"# HTML\n",
"\n",
">[HTML](https://en.wikipedia.org/wiki/HMTL) s the standard markup language for documents designed to be displayed in a web browser.\n",
"\n",
"`HtmlTextSplitter` splits text along Markdown headings, code blocks, or horizontal rules. It's implemented as a simple subclass of `RecursiveCharacterSplitter` with HTML-specific separators. See the source code to see the HTML syntax expected by default.\n",
"\n",
"1. How the text is split: by list of `HTML` specific separators\n",
"2. How the chunk size is measured: by number of characters"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "96d64839",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.text_splitter import HtmlTextSplitter"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "cfb0da17",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"html_text = \"\"\"\n",
"<!DOCTYPE html>\n",
"<html>\n",
" <head>\n",
" <title>🦜️🔗 LangChain</title>\n",
" <style>\n",
" body {\n",
" font-family: Arial, sans-serif;\n",
" }\n",
" h1 {\n",
" color: darkblue;\n",
" }\n",
" </style>\n",
" </head>\n",
" <body>\n",
" <div>\n",
" <h1>🦜️🔗 LangChain</h1>\n",
" <p>⚡ Building applications with LLMs through composability ⚡</p>\n",
" </div>\n",
" <div>\n",
" As an open source project in a rapidly developing field, we are extremely open to contributions.\n",
" </div>\n",
" </body>\n",
"</html>\n",
"\"\"\"\n",
"\n",
"html_splitter = HtmlTextSplitter(chunk_size=175, chunk_overlap=20)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "d59a4fe8",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"docs = html_splitter.create_documents([html_text])"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "cbb2e100",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"[Document(page_content='<!DOCTYPE html>\\n<html>', metadata={}),\n",
" Document(page_content='<title>🦜️🔗 LangChain</title>', metadata={}),\n",
" Document(page_content='body {\\n font-family: Arial, sans-serif;\\n }\\n h1 {\\n color: darkblue;\\n }\\n </style>\\n </head>', metadata={}),\n",
" Document(page_content='/style>\\n </head>', metadata={}),\n",
" Document(page_content='<div>\\n <h1>🦜️🔗 LangChain</h1>\\n <p>⚡ Building applications with LLMs through composability ⚡</p>\\n </div>', metadata={}),\n",
" Document(page_content='As an open source project in a rapidly developing field, we are extremely open to contributions.\\n </div>\\n </body>\\n</html>', metadata={})]"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"docs"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "91b56e7e-b285-4ca4-a786-149544e0e3c6",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"['<!DOCTYPE html>\\n<html>',\n",
" '<title>🦜️🔗 LangChain</title>',\n",
" 'body {\\n font-family: Arial, sans-serif;\\n }\\n h1 {\\n color: darkblue;\\n }\\n </style>\\n </head>',\n",
" '/style>\\n </head>',\n",
" '<div>\\n <h1>🦜️🔗 LangChain</h1>\\n <p>⚡ Building applications with LLMs through composability ⚡</p>\\n </div>',\n",
" 'As an open source project in a rapidly developing field, we are extremely open to contributions.\\n </div>\\n </body>\\n</html>']"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"html_splitter.split_text(html_text)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9bee7858-9175-4d99-bd30-68f2dece8601",
"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": "3.10.10"
},
"vscode": {
"interpreter": {
"hash": "aee8b7b246df8f9039afb4144a1f6fd8d2ca17a180786b69acc140d282b71a49"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}

View File

@ -478,6 +478,45 @@ class PythonCodeTextSplitter(RecursiveCharacterTextSplitter):
super().__init__(separators=separators, **kwargs) super().__init__(separators=separators, **kwargs)
class HtmlTextSplitter(RecursiveCharacterTextSplitter):
"""Attempts to split the text along HTML layout elements."""
def __init__(self, **kwargs: Any):
"""Initialize a HtmlTextSplitter."""
separators = [
# First, try to split along HTML tags
"<body>",
"<div>",
"<p>",
"<br>",
"<li>",
"<h1>",
"<h2>",
"<h3>",
"<h4>",
"<h5>",
"<h6>",
"<span>",
"<table>",
"<tr>",
"<td>",
"<th>",
"<ul>",
"<ol>",
"<header>",
"<footer>",
"<nav>",
# Head
"<head>",
"<style>",
"<script>",
"<meta>",
"<title>",
"",
]
super().__init__(separators=separators, **kwargs)
class Language(str, Enum): class Language(str, Enum):
CPP = "cpp" CPP = "cpp"
GO = "go" GO = "go"