Skip to main content
Amazon Simple Storage Service (Amazon S3) is an object storage service.
AWS S3 Buckets
This covers how to load document objects from an AWS S3 File object. 
from langchain_community.document_loaders import S3FileLoader

pip install -qU  boto3

loader = S3FileLoader("testing-hwc", "fake.docx")

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 = S3FileLoader(
    "testing-hwc", "fake.docx", aws_access_key_id="xxxx", aws_secret_access_key="yyyy"
)

loader.load()
Edit the source of this page on GitHub.
Connect these docs programmatically to Claude, VSCode, and more via MCP for real-time answers.
⌘I