So I am desperately trying to figure out how to keep the original formatting for my book by the time it gets to my output (generate file). But the problem with my Interface → File Reader is it flattens the books formatting (bolds, italics, paragraph indents disappear etc…).
I’m at a complete loss for what to do. My workflow is doing perfectly EXCEPT it cannot keep my original books formatting which is a major issue.
Please help. Im desperate.
Here is the name of the workflow sheet Im talking about: GPT5.0 Copy - In-Line Annotation (WORKING Claude Version_Professional_Best Version)
Hey @BlackPen! If you’re reporting an issue with a flow or an error in a run, please include the run link and make sure it’s shareable so we can take a look.
Find your run link on the history page. Format: https://www.gumloop.com/pipeline?run_id={{your_run_id}}&workbook_id={{workbook_id}}
Make it shareable by clicking “Share” → ‘Anyone with the link can view’ in the top-left corner of the flow screen.
Provide details about the issue—more context helps us troubleshoot faster.
The File Reader node reads files as plain text, so it strips out all formatting like bold, italics, and indents. That’s why your book ends up losing its original style.
To keep the formatting, a good approach is to convert your book into HTML or Markdown first. These formats preserve styling, so when you process and output them, your formatting stays intact.
This is a feature we definitely want to improve. For now, passing HTML files through your workflow is the best way to keep the original look in your final output.
Hm, so there is no work around for this outside of uploading your work as an HTML?
I was hoping to use this service in the future for a bunch of indie authors and most indie authors have books in pdfs or docx formats. So you’d suggest telling everyone to upload their books as htmls? That may be problematic… hmmm
So I just tried uploading the book as an html and running it through the workflow I mentioned in my original post, and it still lost all formatting (specifically bold and italics).
Hey @BlackPen – Just to fully understand the issue, you want to pass the exact formatting from the input .DOCX file correct? I saw your HTML output and it did include all the formatting as requested in the AI prompt so I’m wondering what the blocker is.
If you want to pass exact formatting from the .DOCX file, we can add support for that in the File Reader node as Rithen suggested, however if you want to be unblocked immediately, I just shared a custom node with you that should output the Doc’s content with proper formatting. You can look it up in the node library and it would be a 1:1 replacement for the File Reader node.
