DEV Community

Cover image for K-shot training with LLMs
Anton Loss
Anton Loss

Posted on

K-shot training with LLMs

I built a tool for teaching LLMs how to extract structured data from documents by annotating, not prompt engineering. I’d love your feedback.

How it works:

  • Upload a document (DOCX, PDF, image, etc.)
  • Select and tag parts of it (supports nesting, arrays, custom tag structures)
  • Upload another document → click "predict" → see editable annotations
  • Amend them and save as a new example - Call the API with a third document → get JSON back

Use cases:

  • Identify "important clauses" in contracts
  • Extract "total value" from invoices
  • Anything subjective, like "healthy ingredients" on a label
  • Anything objective, like "postcode" or "phone number"
  • You could even tag things like "good rhymes" in a poem — basically anything an LLM can understand and extrapolate

The key idea: instead of iterating endlessly on prompts (and sometimes regressing), you just iterate on examples. Each example improves accuracy in a concrete way, and you need far fewer than traditional ML approaches.

We’re launching on Product Hunt today (currently #5)
https://www.producthunt.com/products/deeptagger

Top comments (2)

Collapse
 
jess profile image
Jess Lee

Congrats! Good luck on the launch.

Collapse
 
avloss profile image
Anton Loss

Thank you!

Some comments may only be visible to logged-in visitors. Sign in to view all comments.