Feedback wanted: an R package and Shiny app for asking questions of your own documents

Hi all! I've been building a small R package and would love your feedback.

You give it your own documents (PDFs, Word files, web pages) and ask questions in a Shiny app. It answers from what it read, and says so when the documents don't cover something. You can also train a model on the same documents, all on your own machine.

On Costco's 76-page annual report it got 12 of 13 questions right.

Write-up: Fine-tune your own model from R, starting from your documents • dragonfarm

What would you try it on? And if you do try it, what felt confusing?

Hey @Algocrat! Thank you so much for sharing! This is super cool, I'll share it out with some folks who may be interested!

Love the logo, too :dragon:

Thanks @ivelasq3 ! The R-Universe version is most up to date one - dragonfarm: Fine-Tune Language Models with LoRA on Your Documents and Data.