mirror of
				https://github.com/hwchase17/langchain.git
				synced 2025-10-31 07:41:40 +00:00 
			
		
		
		
	
		
			
				
	
	
		
			105 lines
		
	
	
		
			2.0 KiB
		
	
	
	
		
			Plaintext
		
	
	
	
	
	
			
		
		
	
	
			105 lines
		
	
	
		
			2.0 KiB
		
	
	
	
		
			Plaintext
		
	
	
	
	
	
| {
 | |
|  "cells": [
 | |
|   {
 | |
|    "cell_type": "markdown",
 | |
|    "id": "dd7c3503",
 | |
|    "metadata": {},
 | |
|    "source": [
 | |
|     "# MergeDocLoader\n",
 | |
|     "\n",
 | |
|     "Merge the documents returned from a set of specified data loaders."
 | |
|    ]
 | |
|   },
 | |
|   {
 | |
|    "cell_type": "code",
 | |
|    "execution_count": 1,
 | |
|    "id": "e08dfff1",
 | |
|    "metadata": {},
 | |
|    "outputs": [],
 | |
|    "source": [
 | |
|     "from langchain.document_loaders import WebBaseLoader\n",
 | |
|     "\n",
 | |
|     "loader_web = WebBaseLoader(\n",
 | |
|     "    \"https://github.com/basecamp/handbook/blob/master/37signals-is-you.md\"\n",
 | |
|     ")"
 | |
|    ]
 | |
|   },
 | |
|   {
 | |
|    "cell_type": "code",
 | |
|    "execution_count": 2,
 | |
|    "id": "07b42b2e",
 | |
|    "metadata": {},
 | |
|    "outputs": [],
 | |
|    "source": [
 | |
|     "from langchain.document_loaders import PyPDFLoader\n",
 | |
|     "\n",
 | |
|     "loader_pdf = PyPDFLoader(\"../MachineLearning-Lecture01.pdf\")"
 | |
|    ]
 | |
|   },
 | |
|   {
 | |
|    "cell_type": "code",
 | |
|    "execution_count": 3,
 | |
|    "id": "912ede96",
 | |
|    "metadata": {},
 | |
|    "outputs": [],
 | |
|    "source": [
 | |
|     "from langchain.document_loaders.merge import MergedDataLoader\n",
 | |
|     "\n",
 | |
|     "loader_all = MergedDataLoader(loaders=[loader_web, loader_pdf])"
 | |
|    ]
 | |
|   },
 | |
|   {
 | |
|    "cell_type": "code",
 | |
|    "execution_count": 4,
 | |
|    "id": "9d001311",
 | |
|    "metadata": {},
 | |
|    "outputs": [],
 | |
|    "source": [
 | |
|     "docs_all = loader_all.load()"
 | |
|    ]
 | |
|   },
 | |
|   {
 | |
|    "cell_type": "code",
 | |
|    "execution_count": 8,
 | |
|    "id": "b9097486",
 | |
|    "metadata": {},
 | |
|    "outputs": [
 | |
|     {
 | |
|      "data": {
 | |
|       "text/plain": [
 | |
|        "23"
 | |
|       ]
 | |
|      },
 | |
|      "execution_count": 8,
 | |
|      "metadata": {},
 | |
|      "output_type": "execute_result"
 | |
|     }
 | |
|    ],
 | |
|    "source": [
 | |
|     "len(docs_all)"
 | |
|    ]
 | |
|   }
 | |
|  ],
 | |
|  "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": "3.9.16"
 | |
|   }
 | |
|  },
 | |
|  "nbformat": 4,
 | |
|  "nbformat_minor": 5
 | |
| }
 |