mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-06 05:25:04 +00:00
add HTMLHeaderTextSplitter (#11039)
Description: Similar in concept to the `MarkdownHeaderTextSplitter`, the `HTMLHeaderTextSplitter` is a "structure-aware" chunker that splits text at the element level and adds metadata for each header "relevant" to any given chunk. It can return chunks element by element or combine elements with the same metadata, with the objectives of (a) keeping related text grouped (more or less) semantically and (b) preserving context-rich information encoded in document structures. It can be used with other text splitters as part of a chunking pipeline. Dependency: lxml python package Maintainer: @hwchase17 Twitter handle: @MartinZirulnik --------- Co-authored-by: PresidioVantage <github@presidiovantage.com> Co-authored-by: Bagatur <baskaryan@gmail.com>
This commit is contained in:
mziru
GitHub
@@ -0,0 +1,241 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "c95fcd15cd52c944",
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"jupyter": {
|
||||
"outputs_hidden": false
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"# HTMLHeaderTextSplitter\n",
|
||||
"## Description and motivation\n",
|
||||
"Similar in concept to the <a href=\"https://python.langchain.com/docs/modules/data_connection/document_transformers/text_splitters/markdown_header_metadata\">`MarkdownHeaderTextSplitter`</a>, the `HTMLHeaderTextSplitter` is a \"structure-aware\" chunker that splits text at the element level and adds metadata for each header \"relevant\" to any given chunk. It can return chunks element by element or combine elements with the same metadata, with the objectives of (a) keeping related text grouped (more or less) semantically and (b) preserving context-rich information encoded in document structures. It can be used with other text splitters as part of a chunking pipeline.\n",
|
||||
"\n",
|
||||
"## Usage examples\n",
|
||||
"#### 1) With an HTML string:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "initial_id",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-10-02T18:57:49.208965400Z",
|
||||
"start_time": "2023-10-02T18:57:48.899756Z"
|
||||
},
|
||||
"collapsed": false,
|
||||
"jupyter": {
|
||||
"outputs_hidden": false
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content='Foo'),\n",
|
||||
" Document(page_content='Some intro text about Foo. \\nBar main section Bar subsection 1 Bar subsection 2', metadata={'Header 1': 'Foo'}),\n",
|
||||
" Document(page_content='Some intro text about Bar.', metadata={'Header 1': 'Foo', 'Header 2': 'Bar main section'}),\n",
|
||||
" Document(page_content='Some text about the first subtopic of Bar.', metadata={'Header 1': 'Foo', 'Header 2': 'Bar main section', 'Header 3': 'Bar subsection 1'}),\n",
|
||||
" Document(page_content='Some text about the second subtopic of Bar.', metadata={'Header 1': 'Foo', 'Header 2': 'Bar main section', 'Header 3': 'Bar subsection 2'}),\n",
|
||||
" Document(page_content='Baz', metadata={'Header 1': 'Foo'}),\n",
|
||||
" Document(page_content='Some text about Baz', metadata={'Header 1': 'Foo', 'Header 2': 'Baz'}),\n",
|
||||
" Document(page_content='Some concluding text about Foo', metadata={'Header 1': 'Foo'})]"
|
||||
]
|
||||
},
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain.text_splitter import HTMLHeaderTextSplitter\n",
|
||||
"\n",
|
||||
"html_string =\"\"\"\n",
|
||||
"<!DOCTYPE html>\n",
|
||||
"<html>\n",
|
||||
"<body>\n",
|
||||
" <div>\n",
|
||||
" <h1>Foo</h1>\n",
|
||||
" <p>Some intro text about Foo.</p>\n",
|
||||
" <div>\n",
|
||||
" <h2>Bar main section</h2>\n",
|
||||
" <p>Some intro text about Bar.</p>\n",
|
||||
" <h3>Bar subsection 1</h3>\n",
|
||||
" <p>Some text about the first subtopic of Bar.</p>\n",
|
||||
" <h3>Bar subsection 2</h3>\n",
|
||||
" <p>Some text about the second subtopic of Bar.</p>\n",
|
||||
" </div>\n",
|
||||
" <div>\n",
|
||||
" <h2>Baz</h2>\n",
|
||||
" <p>Some text about Baz</p>\n",
|
||||
" </div>\n",
|
||||
" <br>\n",
|
||||
" <p>Some concluding text about Foo</p>\n",
|
||||
" </div>\n",
|
||||
"</body>\n",
|
||||
"</html>\n",
|
||||
"\"\"\"\n",
|
||||
"\n",
|
||||
"headers_to_split_on = [\n",
|
||||
" (\"h1\", \"Header 1\"),\n",
|
||||
" (\"h2\", \"Header 2\"),\n",
|
||||
" (\"h3\", \"Header 3\"),\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"html_splitter = HTMLHeaderTextSplitter(headers_to_split_on=headers_to_split_on)\n",
|
||||
"html_header_splits = html_splitter.split_text(html_string)\n",
|
||||
"html_header_splits"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "e29b4aade2a0070c",
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"jupyter": {
|
||||
"outputs_hidden": false
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"#### 2) Pipelined to another splitter, with html loaded from a web URL:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "6ada8ea093ea0475",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-10-02T18:57:51.016141300Z",
|
||||
"start_time": "2023-10-02T18:57:50.647495400Z"
|
||||
},
|
||||
"collapsed": false,
|
||||
"jupyter": {
|
||||
"outputs_hidden": false
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content='We see that Gödel first tried to reduce the consistency problem for analysis to that of arithmetic. This seemed to require a truth definition for arithmetic, which in turn led to paradoxes, such as the Liar paradox (“This sentence is false”) and Berry’s paradox (“The least number not defined by an expression consisting of just fourteen English words”). Gödel then noticed that such paradoxes would not necessarily arise if truth were replaced by provability. But this means that arithmetic truth', metadata={'Header 1': 'Kurt Gödel', 'Header 2': '2. Gödel’s Mathematical Work', 'Header 3': '2.2 The Incompleteness Theorems', 'Header 4': '2.2.1 The First Incompleteness Theorem'}),\n",
|
||||
" Document(page_content='means that arithmetic truth and arithmetic provability are not co-extensive — whence the First Incompleteness Theorem.', metadata={'Header 1': 'Kurt Gödel', 'Header 2': '2. Gödel’s Mathematical Work', 'Header 3': '2.2 The Incompleteness Theorems', 'Header 4': '2.2.1 The First Incompleteness Theorem'}),\n",
|
||||
" Document(page_content='This account of Gödel’s discovery was told to Hao Wang very much after the fact; but in Gödel’s contemporary correspondence with Bernays and Zermelo, essentially the same description of his path to the theorems is given. (See Gödel 2003a and Gödel 2003b respectively.) From those accounts we see that the undefinability of truth in arithmetic, a result credited to Tarski, was likely obtained in some form by Gödel by 1931. But he neither publicized nor published the result; the biases logicians', metadata={'Header 1': 'Kurt Gödel', 'Header 2': '2. Gödel’s Mathematical Work', 'Header 3': '2.2 The Incompleteness Theorems', 'Header 4': '2.2.1 The First Incompleteness Theorem'}),\n",
|
||||
" Document(page_content='result; the biases logicians had expressed at the time concerning the notion of truth, biases which came vehemently to the fore when Tarski announced his results on the undefinability of truth in formal systems 1935, may have served as a deterrent to Gödel’s publication of that theorem.', metadata={'Header 1': 'Kurt Gödel', 'Header 2': '2. Gödel’s Mathematical Work', 'Header 3': '2.2 The Incompleteness Theorems', 'Header 4': '2.2.1 The First Incompleteness Theorem'}),\n",
|
||||
" Document(page_content='We now describe the proof of the two theorems, formulating Gödel’s results in Peano arithmetic. Gödel himself used a system related to that defined in Principia Mathematica, but containing Peano arithmetic. In our presentation of the First and Second Incompleteness Theorems we refer to Peano arithmetic as P, following Gödel’s notation.', metadata={'Header 1': 'Kurt Gödel', 'Header 2': '2. Gödel’s Mathematical Work', 'Header 3': '2.2 The Incompleteness Theorems', 'Header 4': '2.2.2 The proof of the First Incompleteness Theorem'})]"
|
||||
]
|
||||
},
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
|
||||
"\n",
|
||||
"url = \"https://plato.stanford.edu/entries/goedel/\"\n",
|
||||
"\n",
|
||||
"headers_to_split_on = [\n",
|
||||
" (\"h1\", \"Header 1\"),\n",
|
||||
" (\"h2\", \"Header 2\"),\n",
|
||||
" (\"h3\", \"Header 3\"),\n",
|
||||
" (\"h4\", \"Header 4\"),\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"html_splitter = HTMLHeaderTextSplitter(headers_to_split_on=headers_to_split_on)\n",
|
||||
"\n",
|
||||
"#for local file use html_splitter.split_text_from_file(<path_to_file>)\n",
|
||||
"html_header_splits = html_splitter.split_text_from_url(url)\n",
|
||||
"\n",
|
||||
"chunk_size = 500\n",
|
||||
"chunk_overlap = 30\n",
|
||||
"text_splitter = RecursiveCharacterTextSplitter(\n",
|
||||
" chunk_size=chunk_size, chunk_overlap=chunk_overlap\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# Split\n",
|
||||
"splits = text_splitter.split_documents(html_header_splits)\n",
|
||||
"splits[80:85]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "ac0930371d79554a",
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"jupyter": {
|
||||
"outputs_hidden": false
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"## Limitations\n",
|
||||
"\n",
|
||||
"There can be quite a bit of structural variation from one HTML document to another, and while `HTMLHeaderTextSplitter` will attempt to attach all \"relevant\" headers to any given chunk, it can sometimes miss certain headers. For example, the algorithm assumes an informational hierarchy in which headers are always at nodes \"above\" associated text, i.e. prior siblings, ancestors, and combinations thereof. In the following news article (as of the writing of this document), the document is structured such that the text of the top-level headline, while tagged \"h1\", is in a *distinct* subtree from the text elements that we'd expect it to be *\"above\"*—so we can observe that the \"h1\" element and its associated text do not show up in the chunk metadata (but, where applicable, we do see \"h2\" and its associated text): \n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "5a5ec1482171b119",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-10-02T19:03:25.943524300Z",
|
||||
"start_time": "2023-10-02T19:03:25.691641Z"
|
||||
},
|
||||
"collapsed": false,
|
||||
"jupyter": {
|
||||
"outputs_hidden": false
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"No two El Niño winters are the same, but many have temperature and precipitation trends in common. \n",
|
||||
"Average conditions during an El Niño winter across the continental US. \n",
|
||||
"One of the major reasons is the position of the jet stream, which often shifts south during an El Niño winter. This shift typically brings wetter and cooler weather to the South while the North becomes drier and warmer, according to NOAA. \n",
|
||||
"Because the jet stream is essentially a river of air that storms flow through, the\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"url = \"https://www.cnn.com/2023/09/25/weather/el-nino-winter-us-climate/index.html\"\n",
|
||||
"\n",
|
||||
"headers_to_split_on = [\n",
|
||||
" (\"h1\", \"Header 1\"),\n",
|
||||
" (\"h2\", \"Header 2\"),\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"html_splitter = HTMLHeaderTextSplitter(headers_to_split_on=headers_to_split_on)\n",
|
||||
"html_header_splits = html_splitter.split_text_from_url(url)\n",
|
||||
"print(html_header_splits[1].page_content[:500])"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "poetry-venv",
|
||||
"language": "python",
|
||||
"name": "poetry-venv"
|
||||
},
|
||||
"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"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -40,9 +40,14 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"execution_count": 1,
|
||||
"id": "ceb3c1fb",
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-09-25T19:12:27.243781300Z",
|
||||
"start_time": "2023-09-25T19:12:24.943559400Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.text_splitter import MarkdownHeaderTextSplitter"
|
||||
@@ -50,19 +55,20 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"execution_count": 2,
|
||||
"id": "2ae3649b",
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-09-25T19:12:31.917013600Z",
|
||||
"start_time": "2023-09-25T19:12:31.905694500Z"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content='Hi this is Jim \\nHi this is Joe', metadata={'Header 1': 'Foo', 'Header 2': 'Bar'}),\n",
|
||||
" Document(page_content='Hi this is Lance', metadata={'Header 1': 'Foo', 'Header 2': 'Bar', 'Header 3': 'Boo'}),\n",
|
||||
" Document(page_content='Hi this is Molly', metadata={'Header 1': 'Foo', 'Header 2': 'Baz'})]"
|
||||
]
|
||||
"text/plain": "[Document(page_content='Hi this is Jim \\nHi this is Joe', metadata={'Header 1': 'Foo', 'Header 2': 'Bar'}),\n Document(page_content='Hi this is Lance', metadata={'Header 1': 'Foo', 'Header 2': 'Bar', 'Header 3': 'Boo'}),\n Document(page_content='Hi this is Molly', metadata={'Header 1': 'Foo', 'Header 2': 'Baz'})]"
|
||||
},
|
||||
"execution_count": 5,
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@@ -83,17 +89,20 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"execution_count": 3,
|
||||
"id": "aac1738c",
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-09-25T19:12:35.672077100Z",
|
||||
"start_time": "2023-09-25T19:12:35.666731400Z"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"langchain.schema.Document"
|
||||
]
|
||||
"text/plain": "langchain.schema.document.Document"
|
||||
},
|
||||
"execution_count": 4,
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@@ -112,21 +121,20 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"execution_count": 4,
|
||||
"id": "480e0e3a",
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-09-25T19:12:41.337249Z",
|
||||
"start_time": "2023-09-25T19:12:41.326099200Z"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content='Markdown[9] is a lightweight markup language for creating formatted text using a plain-text editor. John Gruber created Markdown in 2004 as a markup language that is appealing to human readers in its source code form.[9]', metadata={'Header 1': 'Intro', 'Header 2': 'History'}),\n",
|
||||
" Document(page_content='Markdown is widely used in blogging, instant messaging, online forums, collaborative software, documentation pages, and readme files.', metadata={'Header 1': 'Intro', 'Header 2': 'History'}),\n",
|
||||
" Document(page_content='As Markdown popularity grew rapidly, many Markdown implementations appeared, driven mostly by the need for \\nadditional features such as tables, footnotes, definition lists,[note 1] and Markdown inside HTML blocks. \\n#### Standardization', metadata={'Header 1': 'Intro', 'Header 2': 'Rise and divergence'}),\n",
|
||||
" Document(page_content='#### Standardization \\nFrom 2012, a group of people, including Jeff Atwood and John MacFarlane, launched what Atwood characterised as a standardisation effort.', metadata={'Header 1': 'Intro', 'Header 2': 'Rise and divergence'}),\n",
|
||||
" Document(page_content='Implementations of Markdown are available for over a dozen programming languages.', metadata={'Header 1': 'Intro', 'Header 2': 'Implementations'})]"
|
||||
]
|
||||
"text/plain": "[Document(page_content='Markdown[9] is a lightweight markup language for creating formatted text using a plain-text editor. John Gruber created Markdown in 2004 as a markup language that is appealing to human readers in its source code form.[9]', metadata={'Header 1': 'Intro', 'Header 2': 'History'}),\n Document(page_content='Markdown is widely used in blogging, instant messaging, online forums, collaborative software, documentation pages, and readme files.', metadata={'Header 1': 'Intro', 'Header 2': 'History'}),\n Document(page_content='As Markdown popularity grew rapidly, many Markdown implementations appeared, driven mostly by the need for \\nadditional features such as tables, footnotes, definition lists,[note 1] and Markdown inside HTML blocks. \\n#### Standardization', metadata={'Header 1': 'Intro', 'Header 2': 'Rise and divergence'}),\n Document(page_content='#### Standardization \\nFrom 2012, a group of people, including Jeff Atwood and John MacFarlane, launched what Atwood characterised as a standardisation effort.', metadata={'Header 1': 'Intro', 'Header 2': 'Rise and divergence'}),\n Document(page_content='Implementations of Markdown are available for over a dozen programming languages.', metadata={'Header 1': 'Intro', 'Header 2': 'Implementations'})]"
|
||||
},
|
||||
"execution_count": 8,
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@@ -156,6 +164,16 @@
|
||||
"splits = text_splitter.split_documents(md_header_splits)\n",
|
||||
"splits"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"outputs": [],
|
||||
"source": [],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"id": "4017f148d414a45c"
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
|
||||
Reference in New Issue
Block a user