urchade/GLiNER

Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts) @ NAACL 2024

79
/ 100
Verified

This project helps you automatically identify specific types of information, like names, dates, or organizations, within any text. You provide the text and tell it what categories of information you're looking for, and it will extract those details for you. It's designed for data analysts, researchers, or content managers who need to quickly pull structured data from unstructured text without extensive setup.

2,909 stars. Used by 13 other packages. Actively maintained with 21 commits in the last 30 days. Available on PyPI.

Use this if you need to extract specific categories of information from various texts, like articles, reports, or customer feedback, and want a flexible tool that can identify almost any entity type you define.

Not ideal if your primary goal is to perform complex text classification or structured data extraction from highly formatted documents, as GLiNER2 might be a better fit for those broader tasks.

text-analysis information-extraction content-categorization data-mining document-processing
Maintenance 20 / 25
Adoption 15 / 25
Maturity 25 / 25
Community 19 / 25

How are scores calculated?

Stars

2,909

Forks

252

Language

Python

License

Apache-2.0

Last pushed

Mar 13, 2026

Commits (30d)

21

Dependencies

6

Reverse dependents

13

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/urchade/GLiNER"

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