From 342e3a43be274de58250769ca43c246a688ca88f Mon Sep 17 00:00:00 2001
From: Theo LEBRUN <mib.ftw@gmail.com>
Date: Tue, 20 Feb 2024 18:09:54 -0500
Subject: [PATCH] Skip nested directories when using S3DirectoryLoader

---
 .../langchain_community/document_loaders/s3_directory.py       | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/libs/community/langchain_community/document_loaders/s3_directory.py b/libs/community/langchain_community/document_loaders/s3_directory.py
index 9885418ec8ae2..545d2059b43ae 100644
--- a/libs/community/langchain_community/document_loaders/s3_directory.py
+++ b/libs/community/langchain_community/document_loaders/s3_directory.py
@@ -120,6 +120,9 @@ def load(self) -> List[Document]:
         bucket = s3.Bucket(self.bucket)
         docs = []
         for obj in bucket.objects.filter(Prefix=self.prefix):
+            # Skip directories
+            if obj.size == 0 and obj.key.endswith('/'):
+                continue
             loader = S3FileLoader(
                 self.bucket,
                 obj.key,