rcarmo/asterisk-embedding-model

A small text embedding model for low-resource hardware

23
/ 100
Experimental

This project helps operations engineers or data analysts working with large volumes of text, like news summaries or personal notes, quickly find similar content or group related documents together. It takes text inputs and converts them into compact numerical representations that can be used for tasks such as semantic search, clustering, or deduplication, all on devices with limited computing power. This is ideal for those needing efficient text analysis without relying on powerful external services.

Use this if you need to perform semantic search, clustering, or deduplication on text data using low-resource hardware, like edge devices or older laptops, and require fast, real-time results.

Not ideal if your primary concern is achieving the absolute highest accuracy on complex, nuanced semantic tasks and you have access to powerful computing resources.

semantic-search text-clustering document-deduplication news-analysis edge-computing
No Package No Dependents
Maintenance 6 / 25
Adoption 4 / 25
Maturity 13 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

Python

License

MIT

Last pushed

Jan 10, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/rcarmo/asterisk-embedding-model"

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