from transformers import AutoModel, AutoModelForSeq2SeqLM, AutoModelForQuestionAnswering, AutoTokenizer, pipeline
import gradio as grad
import ast

# 1. The RoBERTa base model is used, fine-tuned using the SQuAD 2.0 dataset. 
# It’s been trained on question-answer pairs, including unanswerable questions, for the task of question and answering.
# mdl_name = "deepset/roberta-base-squad2"
# my_pipeline = pipeline('question-answering', model=mdl_name, tokenizer=mdl_name)

# 2. Different model.
# mdl_name = "distilbert-base-cased-distilled-squad"
# my_pipeline = pipeline('question-answering', model=mdl_name, tokenizer=mdl_name)

# def answer_question(question,context):
#     text= "{"+"'question': '"+question+"','context': '"+context+"'}"
#     di=ast.literal_eval(text)
#     response = my_pipeline(di)
#     return response

# grad.Interface(answer_question, inputs=["text","text"], outputs="text").launch()

# 3. Different task: language translation.
# First model translates English to German.
# mdl_name = "Helsinki-NLP/opus-mt-en-de"
# opus_translator = pipeline("translation", model=mdl_name)

# def translate(text):
#     response = opus_translator(text)
#     return response

# grad.Interface(translate, inputs=["text",], outputs="text").launch()

# 4. Language translation without pipeline API.
# Second model translates English to French.
mdl_name = "Helsinki-NLP/opus-mt-en-fr"
mdl = AutoModelForSeq2SeqLM.from_pretrained(mdl_name)
my_tkn = AutoTokenizer.from_pretrained(mdl_name)

def translate(text):
    inputs = my_tkn(text, return_tensors="pt")
    trans_output = mdl.generate(**inputs)
    response = my_tkn.decode(trans_output[0], skip_special_tokens=True)
    return response

txt=grad.Textbox(lines=1, label="English", placeholder="English Text here")
out=grad.Textbox(lines=1, label="French")
grad.Interface(translate, inputs=txt, outputs=out).launch()