Skip to main content
These docs will be deprecated and no longer maintained with the release of LangChain v1.0 in October 2025. Visit the v1.0 alpha docs
Open In ColabOpen on GitHub

AWS S3 File

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 --upgrade --quiet  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 clientโ€‹

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()
Morty Proxy This is a proxified and sanitized view of the page, visit original site.