langchain/docs/modules/indexes/document_loaders/examples/s3_directory.ipynb

s3 Directory

This covers how to load document objects from an s3 directory object.

In [1]:

from langchain.document_loaders import S3DirectoryLoader

In [2]:

#!pip install boto3

In [3]:

loader = S3DirectoryLoader("testing-hwc")

In [4]:

loader.load()

Out [4]:

[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)]

Specifying a prefix

You can also specify a prefix for more finegrained control over what files to load.

In [5]:

loader = S3DirectoryLoader("testing-hwc", prefix="fake")

In [6]:

loader.load()

Out [6]:

[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)]

In [ ]: