Hi all,
I have come across an issue where while self-hosting, the native Extract from PDF is causing my N8N instance to crash. I have found a workaround using Llama Cloud and have found it does a great (better than the N8N native node) of extracting and parsing PDF data and am currently using it for an automation that I have put together for a friend/client.
I put together a step-by-step guide on how to use it as it currently requires the use of a HTTP request and would love to know your thoughts!
Definitely recommend giving it a try, especially for those who are having issues with their local N8N instances!