From dedd780825ebde01e19948b0b6520ef882a0f299 Mon Sep 17 00:00:00 2001
From: "E. Evstafiev" <ee345@cam.ac.uk>
Date: Sat, 4 Jan 2025 09:31:11 +0000
Subject: [PATCH] feat: add langchain-pull-md document loader documentation

---
 .../document_loaders/pull_md.ipynb            | 131 ++++++++++++++++++
 libs/packages.yml                             |   4 +
 2 files changed, 135 insertions(+)
 create mode 100644 docs/docs/integrations/document_loaders/pull_md.ipynb

diff --git a/docs/docs/integrations/document_loaders/pull_md.ipynb b/docs/docs/integrations/document_loaders/pull_md.ipynb
new file mode 100644
index 0000000000000..401719c4aa6f5
--- /dev/null
+++ b/docs/docs/integrations/document_loaders/pull_md.ipynb
@@ -0,0 +1,131 @@
+{
+  "cells": [
+    {
+      "cell_type": "raw",
+      "metadata": {},
+      "source": [
+        "---\n",
+        "sidebar_label: PullMdLoader\n",
+        "---"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# PullMdLoader\n",
+        "\n",
+        "Loader for converting URLs into Markdown using the pull.md service.\n",
+        "\n",
+        "This package implements a [document loader](/docs/concepts/document_loaders/) for web content. Unlike traditional web scrapers, PullMdLoader can handle web pages built with dynamic JavaScript frameworks like React, Angular, or Vue.js, converting them into Markdown without local rendering.\n",
+        "\n",
+        "## Overview\n",
+        "### Integration details\n",
+        "\n",
+        "| Class | Package | Local | Serializable | JS Support |\n",
+        "| :--- | :--- | :---: | :---: | :---: |\n",
+        "| PullMdLoader | langchain-pull-md | ✅ | ✅ | ❌ |\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Setup\n",
+        "\n",
+        "### Installation\n",
+        "\n",
+        "```bash\n",
+        "pip install langchain-pull-md\n",
+        "```"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Initialization"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 10,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from langchain_pull_md.markdown_loader import PullMdLoader\n",
+        "\n",
+        "# Instantiate the loader with a URL\n",
+        "loader = PullMdLoader(url='https://example.com')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Load"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 11,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "documents = loader.load()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 12,
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "{'source': 'https://example.com',\n",
+              " 'page_content': '# Example Domain\\nThis domain is used for illustrative examples in documents. You may use this domain in literature without prior coordination or asking for permission.'}"
+            ]
+          },
+          "execution_count": 12,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "documents[0].metadata"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## API Reference:\n",
+        "\n",
+        "- [GitHub](https://github.com/chigwell/langchain-pull-md)\n",
+        "- [PyPi](https://pypi.org/project/langchain-pull-md/)"
+      ]
+    }
+  ],
+  "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": "3.10.12"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 5
+}
diff --git a/libs/packages.yml b/libs/packages.yml
index 34d8184fad178..5fd27064a365f 100644
--- a/libs/packages.yml
+++ b/libs/packages.yml
@@ -320,4 +320,8 @@ packages:
 - name: langchain-dappier
   path: .
   repo: DappierAI/langchain-dappier
+  downloads: 0
+- name: langchain-pull-md
+  path: .
+  repo: chigwell/langchain-pull-md
   downloads: 0
\ No newline at end of file