pixano_inference.models.ner

NER (Named Entity Recognition) model base class.

The I/O types live in :mod:pixano_inference_client.ner and are re-exported here so from pixano_inference.models.ner import NERInput keeps working.

NERModel(config)

Bases: InferenceModel

Base class for named entity recognition models.

Example

@register_model("my-ner")
class MyNER(NERModel):
    def load_model(self):
        self.model = load_weights(self.config.model_params["path"])

    def predict(self, input: NERInput) -> NEROutput:
        return NEROutput(entities=[...])

Source code in pixano_inference/models/base.py

def __init__(self, config: ModelDeploymentConfig) -> None:
    """Initialize the model with deployment config.

    Args:
        config: Model deployment configuration.
    """
    self._config = config

predict(input) abstractmethod

Run named entity recognition.

Parameters:

Name	Type	Description	Default
input	NERInput	NER input with text to analyse.	required

Returns:

Type	Description
NEROutput	NER output with recognised entities.

Source code in pixano_inference/models/ner.py

@abstractmethod
def predict(self, input: NERInput) -> NEROutput:
    """Run named entity recognition.

    Args:
        input: NER input with text to analyse.

    Returns:
        NER output with recognised entities.
    """