add v4

docs/extras/integrations/document_loaders/jupyter_notebook.ipynb

@@ -0,0 +1,104 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Jupyter Notebook\n",
+    "\n",
+    ">[Jupyter Notebook](https://en.wikipedia.org/wiki/Project_Jupyter#Applications) (formerly `IPython Notebook`) is a web-based interactive computational environment for creating notebook documents.\n",
+    "\n",
+    "This notebook covers how to load data from a `Jupyter notebook (.html)` into a format suitable by LangChain."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import NotebookLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "loader = NotebookLoader(\n",
+    "    \"example_data/notebook.html\",\n",
+    "    include_outputs=True,\n",
+    "    max_output_length=20,\n",
+    "    remove_newline=True,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "`NotebookLoader.load()` loads the `.html` notebook file into a `Document` object.\n",
+    "\n",
+    "**Parameters**:\n",
+    "\n",
+    "* `include_outputs` (bool): whether to include cell outputs in the resulting document (default is False).\n",
+    "* `max_output_length` (int): the maximum number of characters to include from each cell output (default is 10).\n",
+    "* `remove_newline` (bool): whether to remove newline characters from the cell sources and outputs (default is False).\n",
+    "* `traceback` (bool): whether to include full traceback (default is False)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='\\'markdown\\' cell: \\'[\\'# Notebook\\', \\'\\', \\'This notebook covers how to load data from an .html notebook into a format suitable by LangChain.\\']\\'\\n\\n \\'code\\' cell: \\'[\\'from langchain.document_loaders import NotebookLoader\\']\\'\\n\\n \\'code\\' cell: \\'[\\'loader = NotebookLoader(\"example_data/notebook.html\")\\']\\'\\n\\n \\'markdown\\' cell: \\'[\\'`NotebookLoader.load()` loads the `.html` notebook file into a `Document` object.\\', \\'\\', \\'**Parameters**:\\', \\'\\', \\'* `include_outputs` (bool): whether to include cell outputs in the resulting document (default is False).\\', \\'* `max_output_length` (int): the maximum number of characters to include from each cell output (default is 10).\\', \\'* `remove_newline` (bool): whether to remove newline characters from the cell sources and outputs (default is False).\\', \\'* `traceback` (bool): whether to include full traceback (default is False).\\']\\'\\n\\n \\'code\\' cell: \\'[\\'loader.load(include_outputs=True, max_output_length=20, remove_newline=True)\\']\\'\\n\\n', metadata={'source': 'example_data/notebook.html'})]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "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": "3.10.6"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "981b6680a42bdb5eb22187741e1607b3aae2cf73db800d1af1f268d1de6a1f70"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}