intellectronica/generative-learning

Using a reasoning LLM to learn a prompt from data

20
/ 100
Experimental

This project helps data professionals or content managers automatically generate precise instructions for Large Language Models (LLMs) to follow. By providing examples of input text and desired structured output (like YAML), the system learns how to transform new, similar text into the correct format. This is ideal for anyone who needs to consistently convert unstructured content into a structured representation without manually crafting complex prompts.

No commits in the last 6 months.

Use this if you have a dataset of text and its corresponding structured output, and you want an LLM to automatically learn the best way to perform that transformation.

Not ideal if you don't have example data or if your transformation task is highly creative and doesn't follow a clear input-output pattern.

content-structuring data-transformation LLM-prompt-engineering information-extraction text-to-structured-data
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 7 / 25
Community 4 / 25

How are scores calculated?

Stars

25

Forks

1

Language

Jupyter Notebook

License

Last pushed

May 05, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/intellectronica/generative-learning"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.