model

Unionk:parameters]

Default: "deepset/roberta-base-squad2-distilled"

A Hugging Face transformers question answering model. Can either be a path to a folder containing the model files or an identifier of a model from Hugging Face.
Required.

device

ComponentDevice

Default: None

The device on which the model is loaded. If None, the default device is automatically selected.
Optional.

token

Secret

Default: Secret.from_env_var("HF_API_TOKEN", strict=False)

The API token used to download private models from Hugging Face.
Optional.

top_k

Integer

Default: 20

Number of answers to return per query. It is required even if score_threshold is set. An additional answer with no text is returned if no_answer is set to True (default).
Required.

score_threshold

Float

Default: None

Returns only answers with a probability score above this threshold. ExtractiveReader assigns a probability score to answers. This score ranges from 0 to 1. It indicates how well the answers match the query. A probability score close to 1 means the model has high confidence in the answer's relevance. Answers with the highest probability are listed first.
Optional.

max_seq_length

Integer

Default: 384

Maximum number of tokens of one input text for the model. If a sequence exceeds it, it's is split.
Required.

stride

Integer

Default: 128

Number of tokens that overlap when a sequence is split because it exceeds max_seq_length.
Required.

max_batch_size

Integer

Default: None

Maximum number of samples that are fed through the model at the same time.
Optional.

answers_per_seq

Integer

Default: None

Number of answer candidates to consider per sequence. This is relevant when a document was split into multiple sequences because of max_seq_length.
Optional.

no_answer

Boolean

True, False
Default: True

Whether to return an additional no answer with an empty text and a score representing the probability that the other top_k answers are incorrect. For example, if top_k: 4, the system returns four answers and an additional empty answer. Each returned answer has a probability score assigned. If the empty answer has a probability of 0.5, it means that's the probability that none of the returned answers is correct.
Required.

calibration_factor

Float

Default: 0.1

A factor used for calibrating probabilities.
Required.

overlap_threshold

Float

Default: 0.01

If set, removes duplicate answers if they have an overlap larger than the supplied threshold. If None, then all answers are kept.
Optional.

model_kwargs

Dictionary of string and any

Default: None

Additional keyword arguments passed to AutoModelForQuestionAnswering.from_pretrained when loading the model specified in model. For details on what kwargs you can pass, see the model's documentation.
Optional.