mirror of
https://github.com/hwchase17/langchain
synced 2024-10-31 15:20:26 +00:00
111 lines
3.0 KiB
Plaintext
111 lines
3.0 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "80f6cd99",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Markdown Text Splitter\n",
|
|
"\n",
|
|
"MarkdownTextSplitter splits text along Markdown headings, code blocks, or horizontal rules. It's implemented as a simple subclass of RecursiveCharacterSplitter with Markdown-specific separators. See the source code to see the Markdown syntax expected by default.\n",
|
|
"\n",
|
|
"1. How the text is split: by list of markdown specific characters\n",
|
|
"2. How the chunk size is measured: by length function passed in (defaults to number of characters)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"id": "96d64839",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.text_splitter import MarkdownTextSplitter"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"id": "cfb0da17",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"markdown_text = \"\"\"\n",
|
|
"# 🦜️🔗 LangChain\n",
|
|
"\n",
|
|
"⚡ Building applications with LLMs through composability ⚡\n",
|
|
"\n",
|
|
"## Quick Install\n",
|
|
"\n",
|
|
"```bash\n",
|
|
"# Hopefully this code block isn't split\n",
|
|
"pip install langchain\n",
|
|
"```\n",
|
|
"\n",
|
|
"As an open source project in a rapidly developing field, we are extremely open to contributions.\n",
|
|
"\"\"\"\n",
|
|
"markdown_splitter = MarkdownTextSplitter(chunk_size=100, chunk_overlap=0)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"id": "d59a4fe8",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"docs = markdown_splitter.create_documents([markdown_text])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"id": "cbb2e100",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"[Document(page_content='# 🦜️🔗 LangChain\\n\\n⚡ Building applications with LLMs through composability ⚡', lookup_str='', metadata={}, lookup_index=0),\n",
|
|
" Document(page_content=\"Quick Install\\n\\n```bash\\n# Hopefully this code block isn't split\\npip install langchain\", lookup_str='', metadata={}, lookup_index=0),\n",
|
|
" Document(page_content='As an open source project in a rapidly developing field, we are extremely open to contributions.', lookup_str='', metadata={}, lookup_index=0)]"
|
|
]
|
|
},
|
|
"execution_count": 7,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"docs"
|
|
]
|
|
}
|
|
],
|
|
"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
|
|
}
|