From 7ee8b2d1bf7a58a21b2bee8d5e45fb3835c3a3c5 Mon Sep 17 00:00:00 2001 From: Bagatur <22008038+baskaryan@users.noreply.github.com> Date: Tue, 26 Sep 2023 09:59:04 -0700 Subject: [PATCH] exclude dirs in async recursive loading (#11077) --- .../langchain/langchain/document_loaders/recursive_url_loader.py | 1 + 1 file changed, 1 insertion(+) diff --git a/libs/langchain/langchain/document_loaders/recursive_url_loader.py b/libs/langchain/langchain/document_loaders/recursive_url_loader.py index 5bb2350c5c..a3fdbbcfcc 100644 --- a/libs/langchain/langchain/document_loaders/recursive_url_loader.py +++ b/libs/langchain/langchain/document_loaders/recursive_url_loader.py @@ -233,6 +233,7 @@ class RecursiveUrlLoader(BaseLoader): base_url=self.url, pattern=self.link_regex, prevent_outside=self.prevent_outside, + exclude_prefixes=self.exclude_dirs, ) # Recursively call the function to get the children of the children