GLiNER

NER task

This task uses GliNERPredictor by default. For more details, see:

GLiNERPredictor

Subclass of NERTask.

Module: implementation.tasks

Methods and properties

Main methods and properties

---

__init__

Arguments:

• predictor (Predictor[Any, Any], optional): Predictor that will be used in task. If equals to None, default GliNERPredictor will be used. Defaults to None.

• preprocess (Optional[Component], optional): Component executed before predictor. If equals to None, default component will be used. Defaults to None. Default component: GliNERPreprocessor

• postprocess (Optional[Component], optional): Component executed after predictor. If equals to None, default component will be used. Defaults to None. Default component: GliNERPostprocessor

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

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

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

---

---

---

GliNERInput

Subclass of IOModel.

---

__init__

Arguments:

• text (str): Text to process.

• labels (List[str]): Labels for classification.

---

---

---

GliNEROutput

Subclass of NEROutput. Type of NEROutput[ClassifiedEntity].

---

__init__

Arguments:

• text (str): Input text.

• output (List[ClassifiedEntity]): Classified entities.

---

---

---

GLiNERPreprocessor

Create prompts with providied text. Subclass of Action. Type of Action[Dict[str, Any], Dict[str, Any]].

---

__init__

Arguments:

• sents_batch (int): Chunks size in sentences. Defaults to 10.

• threshold (float): Minimial score to put entities into the output (used by predictor). Defaults to 0.5.

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

---

execute

Arguments:

• input_data (Dict[str, Any]): Expected keys:

  • "text" (str): Text to process;

Returns:

• Dict[str, Any]: Expected keys:

  • "texts" (List[str]): Model inputs;

  • "chunks_starts" (List[int]): Chunks start positions. Used by postprocessor;

  • "threshold" (List[int]): Minimial score to put entities into the output;

---

---

---

GLiNERPostprocessor

Format output. Subclass of Action. Type of Action[Dict[str, Any], Dict[str, Any]].

---

execute

Arguments:

• input_data (Dict[str, Any]): Expected keys:

  • "output" (List[List[Dict[str, Any]]]): Model output;

  • "text" (str): Processed text;

  • "chunks_starts" (List[int]): Chunks starts;

Returns:

• Dict[str, Any]: Expected keys:

  • "text" (str): Processed text;

  • "output" (List[ClassifiedEntity]): Classified entities;

---

---