health_multimodal.text.data.io
Classes
|
Text input class that can be used for inference and deployment. |
- class health_multimodal.text.data.io.TextInput(tokenizer)[source]
Text input class that can be used for inference and deployment.
Implements tokenizer related operations and ensure that input strings conform with the standards expected from a BERT model.
- Parameters
tokenizer (
BertTokenizer
) – A BertTokenizer object.
- assert_special_tokens_not_present(prompt)[source]
Check if the input prompts contain special tokens.
- Return type
None
- tokenize_input_prompts(prompts, verbose)[source]
Tokenizes the input sentence(s) and adds special tokens as defined by the tokenizer. :type prompts:
Union
[str
,List
[str
]] :param prompts: Either a string containing a single sentence, or a list of strings each containinga single sentence. Note that this method will not correctly tokenize multiple sentences if they are input as a single string.
- Parameters
verbose (
bool
) – If set to True, will log the sentence after tokenization.- Return type
Any
- Returns
A 2D tensor containing the tokenized sentences