Class that performs Bert question answering on text.
tflite_support.task.text.BertQuestionAnswerer(
options: tflite_support.task.text.BertQuestionAnswererOptions
,
cpp_bert_question_answerer: _CppBertQuestionAnswerer
) -> None
Methods
answer
View source
answer(
context: str, question: str
) -> tflite_support.task.processor.QuestionAnswererResult
Answers question based on the context.
Could be empty if no answer was
found from the given context.
Args |
context
|
Context the question bases on.
|
question
|
Question to ask.
|
Returns |
Question answerer result.
|
Raises |
ValueError
|
If any of the input arguments is invalid.
|
RuntimeError
|
If failed to calculate the embedding vector.
|
create_from_file
View source
@classmethod
create_from_file(
file_path: str
) -> 'BertQuestionAnswerer'
Creates the BertQuestionAnswerer
object from a TensorFlow Lite model.
Args |
file_path
|
Path to the model.
|
Returns |
BertQuestionAnswerer object that's created from the model file.
|
Raises |
ValueError
|
If failed to create BertQuestionAnswerer object from the
provided file such as invalid file.
|
RuntimeError
|
If other types of error occurred.
|
create_from_options
View source
@classmethod
create_from_options(
options: tflite_support.task.text.BertQuestionAnswererOptions
) -> 'BertQuestionAnswerer'
Creates the BertQuestionAnswerer
object from the options.
Args |
options
|
Options for the Bert question answerer task.
|
Returns |
BertQuestionAnswerer object that's created from options .
|
Raises |
ValueError
|
If failed to create BertQuestionAnswerer object from
BertQuestionAnswererOptions such as missing the model.
|
RuntimeError
|
If other types of error occurred.
|