forked from Archives/langchain
79 lines
1.7 KiB
Plaintext
79 lines
1.7 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "17812129",
|
|
"metadata": {},
|
|
"source": [
|
|
"# ReadTheDocs Documentation\n",
|
|
"This notebook covers how to load content from html that was generated as part of a Read-The-Docs build.\n",
|
|
"\n",
|
|
"For an example of this in the wild, see [here](https://github.com/hwchase17/chat-langchain).\n",
|
|
"\n",
|
|
"This assumes that the html has already been scraped into a folder. This can be done by uncommenting and running the following command"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "84696e27",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"#!wget -r -A.html -P rtdocs https://langchain.readthedocs.io/en/latest/"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"id": "92dd950b",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.document_loaders import ReadTheDocsLoader"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"id": "494567c3",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"loader = ReadTheDocsLoader(\"rtdocs\", features='html.parser')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "e2e6d6f0",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"docs = loader.load()"
|
|
]
|
|
}
|
|
],
|
|
"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": "3.10.9"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|