tool · inferred from evidence
ChromiumLoader
A loader component that now warns on HTTP status >= 400.
- SmartScraperGraph returns NA or blank for all fields even though the content is on the page
Two things came out of the thread. First, check the URL itself: in the reported case the source was a Wikipedia 404 (the article had moved), and FetchNode silently scraped the error page, so the LLM was correctly answering NA on garbage inp