From 72eb4fa4e89f377fb2e311e2d80bc1777f252bd6 Mon Sep 17 00:00:00 2001 From: Monty Evans Date: Mon, 24 Jul 2023 20:17:49 +0100 Subject: [PATCH] Change WebBaseLoader metadata parsing to set missing metadata to descriptive string instead of `None` (#8175) Solves #8174 & #3542 Co-authored-by: mevans --- libs/langchain/langchain/document_loaders/web_base.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/libs/langchain/langchain/document_loaders/web_base.py b/libs/langchain/langchain/document_loaders/web_base.py index 1d4f0aee23..3cac0cf962 100644 --- a/libs/langchain/langchain/document_loaders/web_base.py +++ b/libs/langchain/langchain/document_loaders/web_base.py @@ -30,9 +30,9 @@ def _build_metadata(soup: Any, url: str) -> dict: if title := soup.find("title"): metadata["title"] = title.get_text() if description := soup.find("meta", attrs={"name": "description"}): - metadata["description"] = description.get("content", None) + metadata["description"] = description.get("content", "No description found.") if html := soup.find("html"): - metadata["language"] = html.get("lang", None) + metadata["language"] = html.get("lang", "No language found.") return metadata