The community member suggests using BeautifulSoup to extract text from a markdown document and then parse it. Another community member responds that their documents are already in markdown format, so they thought using a markdown node parser would be best for splitting the documents.
You could try to extract the text from the markdowned document into just plain text as a pre-processor and then parse it? BeautifulSoup can do that https://stackoverflow.com/a/761847/1819550
@ariel17 my documents are already in markdown format so I thought using the markdown node parser would be best for splitting the docs but I see what you’re saying
