GLiNERPredictor

GLiNER predictor

This predictor is specifically build to use GLiNER approach. See more:

GitHub - urchade/GLiNER: Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts) @ NAACL 2024GitHub

Subclass of Predictor.

Module: implementation.predictors

Methods and properties

Main methods and properties

---

__init__

Arguments:

• cfg (GLiNERPredictorConfig, optional): Configuration for predictor. If value equals to None, default GLiNERPredictorConfig configuration will be used. Defaults to None.

• input_class (Type[Input], optional): Class for input validation. Defaults to GLiNERPredictorInput.

• output_class (Type[Output], optional): Class for output validation. Defaults to GLiNERPredictorOutput.

• name (Optional[str], optional): Name for identification. If equals to None, class name will be used. Defaults to None.

---

---

---

GLiNERPredictorConfig

Prebuild configuration that describes default parameters for GLiNER models pipeline. Subclass of Config.

---

__init__

Arguments:

• model_name (str, optional): Model to use. Defaults to "urchade/gliner_small-v2.1".

• device (str): Defaults to "cpu".

---

---

---

GLiNERPredictorInput

Subclass of IOModel.

---

__init__

Arguments:

• texts (List[str])

• labels (List[str])

• threshold (float, optional): Defaults to 0.5.

---

---

---

GLiNERPredictorOutput

Subclass of IOModel.

---

__init__

Arguments:

• output (List[List[Dict[str, Any]]]): Entities of corresponding inputs.

---

---