bizreach-inc/light-splade

Provides a minimal PyTorch implementation of SPLADE

40
/ 100
Emerging

This tool helps information retrieval practitioners train models to convert text into 'sparse vectors.' These vectors are highly interpretable and efficient for search engines like Lucene or Elasticsearch. You can feed in a collection of documents or queries and get back these specialized sparse representations, making it easier to build powerful and understandable search systems.

Available on PyPI.

Use this if you need to train a custom SPLADE model for your specific text data, want to experiment with sparse lexical expansion, or are researching advanced information retrieval techniques.

Not ideal if you are looking for a pre-trained model for immediate use without any customization or training.

information-retrieval search-engine-optimization text-analytics document-ranking
Maintenance 10 / 25
Adoption 6 / 25
Maturity 24 / 25
Community 0 / 25

How are scores calculated?

Stars

15

Forks

Language

Python

License

Apache-2.0

Last pushed

Mar 11, 2026

Commits (30d)

0

Dependencies

17

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/bizreach-inc/light-splade"

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