KarelDO/xmc.dspy

In-Context Learning for eXtreme Multi-Label Classification (XMC) using only a handful of examples.

39
/ 100
Emerging

This tool helps you classify documents or content into a very large number of categories (10,000 or more) efficiently. You input text and it outputs relevant category labels, even with just a few examples. It's designed for data scientists or machine learning engineers who need to manage and categorize vast amounts of information.

449 stars. No commits in the last 6 months.

Use this if you need to perform multi-label classification for tasks with an extremely large set of possible categories and want to leverage large language models without extensive fine-tuning.

Not ideal if your classification task involves a small number of categories or if you prefer traditional machine learning methods that require extensive labeled datasets for training.

extreme multi-label classification information retrieval content categorization text classification large language models
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

449

Forks

24

Language

Python

License

MIT

Last pushed

Feb 13, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/KarelDO/xmc.dspy"

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