Skip to main content
Amazon Simple Storage Service (Amazon S3) is an object storage service
AWS S3 Directory
This covers how to load document objects from an AWS S3 Directory object. 
pip install -qU  boto3

from langchain_community.document_loaders import S3DirectoryLoader

loader = S3DirectoryLoader("testing-hwc")

loader.load()

​
Specifying a prefix

You can also specify a prefix for more fine-grained control over what files to load. 
loader = S3DirectoryLoader("testing-hwc", prefix="fake")

loader.load()

[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': 's3://testing-hwc/fake.docx'}, lookup_index=0)]

​
Configuring the AWS Boto3 client

You can configure the AWS Boto3 client by passing named arguments when creating the S3DirectoryLoader. This is useful for instance when AWS credentials can’t be set as environment variables. See the list of parameters that can be configured. 
loader = S3DirectoryLoader(
    "testing-hwc", aws_access_key_id="xxxx", aws_secret_access_key="yyyy"
)

loader.load()
Edit this page on GitHub or file an issue.
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.