Customize ReferencePredictor using initiation parameters.
YAML Init Parameters
These are the parameters you can pass to this component in the pipeline YAML configuration:
Parameter | Type | Possible values | Description |
---|---|---|---|
| String | Default: | The name identifier of the model from Hugging Face or the path to a local model folder. |
| String | Default: | The revision of the model to be used. Optional. |
| Integer | Default: | The maximum number of tokens that a sequence should be truncated to before inference. |
| Language | Default: | The language of the data that you want to generate references for. Needed to apply the right sentence splitting rules. |
| ComponentDevice | Default: | The device on which the model is loaded. If |
| Integer | Default: | The batch size that should be used for inference. |
| Integer | Default: | The number of sentences of an answer that should be included in one span for inference. |
| Integer | Default: | The stride size for answer window. Required. |
| Integer | Default: | The number of sentences of a document that should be included in one span for inference. |
| Integer | Default: | The stride size for document window. |
| Secret | Default: | The token to use as HTTP bearer authorization for remote files. |
| String |
| The activation function to use on top of the logits. |
| Dictionary | Default: | The minimum prediction score threshold for each corresponding label. |
| Dictionary | Default: | If using a model with a multi label prediction head, pass in a dictionary mapping label names to a float value. |
| Integer | Default: | The minimum score threshold to determine if a prediction should be included as reference or not. |
| String | Default: | A fallback class that should be used if the predicted score doesn't match any threshold. |
| String | Default: | The name identifier of the verifiability model to be used on the Hugging Face hub or the path to a local model folder. |
| String | Default: | The revision of the verifiability model to be used. |
| Integer | Default: | The batch size that should be used for verifiability inference. |
| List of strings | Default: | The class names to be used to determine if a sentence needs verification. |
| Boolean |
| If |
| Boolean |
| If |
| Dictionary | Default: | Additional keyword arguments for the model. |
| Dictionary | Default: | Additional keyword arguments for the verifiability model. |
REST API Runtime Parameters
There are no runtime parameters you can pass to this component when making a request to the Search REST API endpoint.