github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-09 15:03:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

Harrison/sitemap local (#4704)

Browse Source 
Co-authored-by: Lukas Bauer <lukas.bauer@mayflower.de>
This commit is contained in:
Harrison Chase
2023-05-14 22:04:38 -07:00
committed by GitHub
parent 12b4ee1fc7
commit b6e3ac17c4
5 changed files with 127 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
docs/modules/indexes/document_loaders/examples/example_data/sitemap.xml Normal file
View File

@@ -0,0 +1,35 @@
<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
xmlns:xhtml="http://www.w3.org/1999/xhtml">
<url>
<loc>https://python.langchain.com/en/stable/</loc>
<lastmod>2023-05-04T16:15:31.377584+00:00</lastmod>
<changefreq>weekly</changefreq>
<priority>1</priority>
</url>
<url>
<loc>https://python.langchain.com/en/latest/</loc>
<lastmod>2023-05-05T07:52:19.633878+00:00</lastmod>
<changefreq>daily</changefreq>
<priority>0.9</priority>
</url>
<url>
<loc>https://python.langchain.com/en/harrison-docs-refactor-3-24/</loc>
<lastmod>2023-03-27T02:32:55.132916+00:00</lastmod>
<changefreq>monthly</changefreq>
<priority>0.8</priority>
</url>
</urlset>

34
docs/modules/indexes/document_loaders/examples/sitemap.ipynb
View File

@@ -108,7 +108,9 @@
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
@@ -125,6 +127,34 @@
"documents[0]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Local Sitemap\n",
"\n",
"The sitemap loader can also be used to load local files."
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Fetching pages: 100%|####################################################################################################################################| 3/3 [00:00<00:00, 3.91it/s]\n"
]
}
],
"source": [
"sitemap_loader = SitemapLoader(web_path=\"example_data/sitemap.xml\", is_local=True)\n",
"\n",
"docs = sitemap_loader.load()"
]
},
{
"cell_type": "code",
"execution_count": null,
@@ -149,7 +179,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.6"
"version": "3.9.1"
}
},
"nbformat": 4,