From b0d4a67863d4c97db98492f180ed82278a704bb7 Mon Sep 17 00:00:00 2001 From: Gabriel Luiz Freitas Almeida Date: Tue, 5 Mar 2024 19:16:57 -0300 Subject: [PATCH] Refactor URLComponent to use WebBaseLoader instead of UnstructuredURLLoader --- src/backend/langflow/components/data/URL.py | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/src/backend/langflow/components/data/URL.py b/src/backend/langflow/components/data/URL.py index 08eafeaa3..d3af63b1c 100644 --- a/src/backend/langflow/components/data/URL.py +++ b/src/backend/langflow/components/data/URL.py @@ -1,6 +1,6 @@ -from typing import Any, Dict, Optional +from typing import Any, Dict -from langchain_community.document_loaders.url import UnstructuredURLLoader +from langchain_community.document_loaders.web_base import WebBaseLoader from langflow import CustomComponent from langflow.schema import Record @@ -8,7 +8,7 @@ from langflow.schema import Record class URLComponent(CustomComponent): display_name = "URL" - description = "Load a URL." + description = "Load URLs and convert them to records." def build_config(self) -> Dict[str, Any]: return { @@ -18,9 +18,9 @@ class URLComponent(CustomComponent): async def build( self, urls: list[str], - ) -> Optional[Record]: + ) -> Record: - loader = UnstructuredURLLoader(urls=urls) + loader = WebBaseLoader(web_paths=urls) docs = loader.load() records = self.to_records(docs) return records