from transformers import AutoModelForSeq2SeqLM, AutoTokenizer, pipeline
import requests

class MachineLearningNLG:
    def __init__(self):
        self.model_name = "./nlg_model"  # Ścieżka do wytrenowanego modelu
        self.tokenizer = AutoTokenizer.from_pretrained(self.model_name)
        self.model = AutoModelForSeq2SeqLM.from_pretrained(self.model_name)
        self.generator = pipeline('text2text-generation', model=self.model, tokenizer=self.tokenizer)

    def translate_text(self, text, target_language='pl'):
        url = 'https://translate.googleapis.com/translate_a/single?client=gtx&sl=auto&tl={}&dt=t&q={}'.format(target_language, text)
        response = requests.get(url)
        if response.status_code == 200:
            translated_text = response.json()[0][0][0]
            return translated_text
        else:
            return text  # Zwracamy oryginalny tekst w razie problemów z tłumaczeniem

    def nlg(self, system_act):
        input_text = f"generate text: {system_act}"
        result = self.generator(input_text)
        response = result[0]['generated_text']
        translated_response = self.translate_text(response, target_language='pl')
        return translated_response


if __name__ == "__main__":
    nlg = MachineLearningNLG()
    system_act = "inform(date.from=15.07, date.to=22.07)"
    print(nlg.nlg(system_act))