mirror of
				https://github.com/hwchase17/langchain.git
				synced 2025-10-31 16:08:59 +00:00 
			
		
		
		
	
		
			
				
	
	
		
			135 lines
		
	
	
		
			2.7 KiB
		
	
	
	
		
			Plaintext
		
	
	
	
	
	
			
		
		
	
	
			135 lines
		
	
	
		
			2.7 KiB
		
	
	
	
		
			Plaintext
		
	
	
	
	
	
| {
 | |
|  "cells": [
 | |
|   {
 | |
|    "cell_type": "markdown",
 | |
|    "id": "a634365e",
 | |
|    "metadata": {},
 | |
|    "source": [
 | |
|     "# s3 Directory\n",
 | |
|     "\n",
 | |
|     "This covers how to load document objects from an s3 directory object."
 | |
|    ]
 | |
|   },
 | |
|   {
 | |
|    "cell_type": "code",
 | |
|    "execution_count": 1,
 | |
|    "id": "2f0cd6a5",
 | |
|    "metadata": {},
 | |
|    "outputs": [],
 | |
|    "source": [
 | |
|     "from langchain.document_loaders import S3DirectoryLoader"
 | |
|    ]
 | |
|   },
 | |
|   {
 | |
|    "cell_type": "code",
 | |
|    "execution_count": 2,
 | |
|    "id": "49815096",
 | |
|    "metadata": {},
 | |
|    "outputs": [],
 | |
|    "source": [
 | |
|     "#!pip install boto3"
 | |
|    ]
 | |
|   },
 | |
|   {
 | |
|    "cell_type": "code",
 | |
|    "execution_count": 3,
 | |
|    "id": "321cc7f1",
 | |
|    "metadata": {},
 | |
|    "outputs": [],
 | |
|    "source": [
 | |
|     "loader = S3DirectoryLoader(\"testing-hwc\")"
 | |
|    ]
 | |
|   },
 | |
|   {
 | |
|    "cell_type": "code",
 | |
|    "execution_count": 4,
 | |
|    "id": "2b11d155",
 | |
|    "metadata": {},
 | |
|    "outputs": [
 | |
|     {
 | |
|      "data": {
 | |
|       "text/plain": [
 | |
|        "[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': '/var/folders/y6/8_bzdg295ld6s1_97_12m4lr0000gn/T/tmpaa9xl6ch/fake.docx'}, lookup_index=0)]"
 | |
|       ]
 | |
|      },
 | |
|      "execution_count": 4,
 | |
|      "metadata": {},
 | |
|      "output_type": "execute_result"
 | |
|     }
 | |
|    ],
 | |
|    "source": [
 | |
|     "loader.load()"
 | |
|    ]
 | |
|   },
 | |
|   {
 | |
|    "cell_type": "markdown",
 | |
|    "id": "0690c40a",
 | |
|    "metadata": {},
 | |
|    "source": [
 | |
|     "## Specifying a prefix\n",
 | |
|     "You can also specify a prefix for more finegrained control over what files to load."
 | |
|    ]
 | |
|   },
 | |
|   {
 | |
|    "cell_type": "code",
 | |
|    "execution_count": 5,
 | |
|    "id": "72d44781",
 | |
|    "metadata": {},
 | |
|    "outputs": [],
 | |
|    "source": [
 | |
|     "loader = S3DirectoryLoader(\"testing-hwc\", prefix=\"fake\")"
 | |
|    ]
 | |
|   },
 | |
|   {
 | |
|    "cell_type": "code",
 | |
|    "execution_count": 6,
 | |
|    "id": "2d3c32db",
 | |
|    "metadata": {},
 | |
|    "outputs": [
 | |
|     {
 | |
|      "data": {
 | |
|       "text/plain": [
 | |
|        "[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': '/var/folders/y6/8_bzdg295ld6s1_97_12m4lr0000gn/T/tmpujbkzf_l/fake.docx'}, lookup_index=0)]"
 | |
|       ]
 | |
|      },
 | |
|      "execution_count": 6,
 | |
|      "metadata": {},
 | |
|      "output_type": "execute_result"
 | |
|     }
 | |
|    ],
 | |
|    "source": [
 | |
|     "loader.load()"
 | |
|    ]
 | |
|   },
 | |
|   {
 | |
|    "cell_type": "code",
 | |
|    "execution_count": null,
 | |
|    "id": "885dc280",
 | |
|    "metadata": {},
 | |
|    "outputs": [],
 | |
|    "source": []
 | |
|   }
 | |
|  ],
 | |
|  "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
 | |
| }
 |