Generating multiple samples using hugging face QuestionAnsweringPipeline not accept List of strings

Question

I am trying to use a hugging face QA model with Squad2_es.

class QAInferencer:
    def __init__(self, model, tokenizer):
        self.pipeline: QuestionAnsweringPipeline = pipeline(
            model=model,
            tokenizer=(tokenizer, {"use_fast": False}),
            device=0, task="question-answering"
            )

    def response_qas(self, ids, questions, contexts):
        samples = self.pipeline.create_sample(questions, contexts)
        zipped_answers = zip(ids, questions, self.pipeline(samples))
        return [{
            'id': qid,
            "question": question,
            "is_impossible": False,
            "answers": [{
                'answer_start': answer['start'],
                'text': answer['answer']
            }]} for qid, question, answer in zipped_answers]

I pass a to response_qas three list of str's one of ids, one of question and ones contexts. The the create_sample(questions, contexts) call return this error

TypeError: ord() expected a character, but string of length 1542 found

Like the function is expecting only string but the Docs says that it can accept str list, to produce several samples at once.