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
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
@classmethodcreate_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
@classmethodcreate_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.
