create static method
Generic API to create the QuestionAnswerer for bert models with metadata populated. The API expects a Bert based TFLite model with metadata containing the following information:
- input_process_units for Wordpiece/Sentencepiece Tokenizer - Wordpiece Tokenizer can be used for a MobileBert model, Sentencepiece Tokenizer Tokenizer can be used for an Albert model.
- 3 input tensors with names "ids", "mask" and "segment_ids".
- 2 output tensors with names "end_logits" and "start_logits".
Creates BertQuestionAnswerer from modelPath
.
modelPath
is the path of the .tflite model loaded on device.
throws FileSystemException If model file fails to load.
Implementation
static BertQuestionAnswerer create(String modelPath) {
final nativePtr = BertQuestionAnswererFromFile(modelPath.toNativeUtf8());
if (nativePtr == nullptr) {
throw FileSystemException(
"Failed to create BertQuestionAnswerer.", modelPath);
}
return BertQuestionAnswerer._(nativePtr);
}