GLiNER2: Unified Schema-Based Information Extraction

adsharma 73 days ago |

Feels like it's written by ML people not following python software engineering practices.

No black, UV or ruff.

Prints messages with emojis to stdout by default.

Makes a connection to hugging face on every import.

https://github.com/fastino-ai/GLiNER2/pull/74

fbilhaut 73 days ago | |

GLiNER is a really great research work. But putting this kind of things in production is just another job. Not trying to do self promotion here, but there are alternatives for this purpose, like gline-rs (https://github.com/fbilhaut/gline-rs). Support of GLiNER 2 models is on the way.

adsharma 72 days ago | | |

Any chance you could wrap this in pyo3? There is a large python market for this.

iwhalen 73 days ago |

Very cool stuff. Love the focus on CPU-first.

Would also love to see some throughput numbers on basic VM setup.

Edit: there are some latency numbers in the paper https://arxiv.org/pdf/2507.18546

deepsquirrelnet 73 days ago |

Zero-shot encoder models are so cool. I'll definitely be checking this out.

If you're looking for a zero-shot classifier, tasksource is in a similar vein.

https://huggingface.co/tasksource/ModernBERT-large-nli

goodlux 72 days ago | |

gliner2 does classification as well as entities and relationships

plaguna 73 days ago |

Is this only for text I guess? What if the documents are in PDF? What is the recommendation to transform PDF to text?

akreal 72 days ago | |

Docling: https://github.com/docling-project/docling

snthpy 73 days ago |

This looks great. Thank you!

hbcondo714 73 days ago |

There is another version at:

https://github.com/urchade/GLiNER

Looks like it’s still being maintained too?

goodlux 72 days ago | |

GLiNER2 is an upgrade that allows for relationship extraction and classification, built on GLiNER, and added additional research / papers, then trained a new model.

adsharma 73 days ago | |

Use Gliner2. Much better model.

hbcondo714 72 days ago | | |

Okay but there is a dependency on gliner1:

https://github.com/fastino-ai/GLiNER2/issues/69

adsharma 70 days ago | | |

Sounds like a great model which is hobbled by a bunch of mundane python programming issues that researchers don't want to deal with. If there is sufficient interest, I can look into maintaining a new wrapper.