PeterGriffinJin/LMIndexer

Language Models as Semantic Indexers (ICML 2024)

18
/ 100
Experimental

This project helps researchers and machine learning engineers transform raw text documents into a structured format called "semantic IDs." These IDs can then be used to improve the performance of recommendation systems and information retrieval tasks. It takes text data (like product descriptions or articles) and outputs numerical semantic IDs, benefiting those building advanced search or recommendation features.

No commits in the last 6 months.

Use this if you are a researcher or ML engineer working to improve the accuracy of recommendation systems or search engines by better understanding and representing text content.

Not ideal if you are a non-technical user looking for a ready-to-use search engine or recommendation system, as this is a framework for building such systems.

information-retrieval recommendation-systems semantic-search natural-language-processing machine-learning-research
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 3 / 25

How are scores calculated?

Stars

40

Forks

1

Language

Python

License

Last pushed

May 02, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/PeterGriffinJin/LMIndexer"

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