Can I use my own pdf/text documents to train to get an article out

My use case is as follows. I would like to generate an article based on a set of text/pdf documents (that belong to a very specific nice topic) that reside on my desktop. Is it possible? I was wondering if someone can help me understand either the limitation in that context or how it can be done. Would appreciate it very much.
Thank you,

1 Like

You would just need to scrape it and prepare a JSONL file, but yeah. Check out fine-tuning in the docs.


To build off @daveshapautomator, you can try following this article if you’re familiar with Python to scrape text from PDFs!


Hi there! There’s a way to use a set of pdf or word documents for teaching GP-3 Davinci? I would use this for make synthesis of paragraphs and extract quote and so on…
Unfortunately the link Medium linked by @daveshapautomator not working!

Thank you

You can use PDFGPT.IO this tool summarize pdf

did you tried ? it seems that is powerful and it provides an API.