langchain/docs/extras/integrations/document_loaders/aws_s3_directory.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "a634365e",
   "metadata": {},
   "source": [
    "# AWS S3 Directory\n",
    "\n",
    ">[Amazon Simple Storage Service (Amazon S3)](https://docs.aws.amazon.com/AmazonS3/latest/userguide/using-folders.html) is an object storage service\n",
    "\n",
    ">[AWS S3 Directory](https://docs.aws.amazon.com/AmazonS3/latest/userguide/using-folders.html)\n",
    "\n",
    "This covers how to load document objects from an `AWS S3 Directory` object."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "49815096",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "#!pip install boto3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "2f0cd6a5",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "from langchain.document_loaders import S3DirectoryLoader"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "321cc7f1",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "loader = S3DirectoryLoader(\"testing-hwc\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2b11d155",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "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': 's3://testing-hwc/fake.docx'}, lookup_index=0)]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "loader.load()"
   ]
  },
  {
   "cell_type": "markdown",
   "source": [
    "## Configuring the AWS Boto3 client\n",
    "You can configure the AWS [Boto3](https://boto3.amazonaws.com/v1/documentation/api/latest/index.html) client by passing\n",
    "named arguments when creating the S3DirectoryLoader.\n",
    "This is useful for instance when AWS credentials can't be set as environment variables.\n",
    "See the [list of parameters](https://boto3.amazonaws.com/v1/documentation/api/latest/reference/core/session.html#boto3.session.Session) that can be configured."
   ],
   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "loader = S3DirectoryLoader(\"testing-hwc\", aws_access_key_id=\"xxxx\", aws_secret_access_key=\"yyyy\")"
   ],
   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "loader.load()"
   ],
   "metadata": {}
  }
 ],
 "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"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}