q_generator1.py

from transformers import T5Tokenizer, AutoModelForSeq2SeqLM, pipeline

class QGenerator:
    def __init__(self):
        tokenizer = T5Tokenizer.from_pretrained("valhalla/t5-small-qg-hl", use_fast=False)
        model = AutoModelForSeq2SeqLM.from_pretrained("valhalla/t5-small-qg-hl")
        self.qg = pipeline("text2text-generation", model=model, tokenizer=tokenizer)

    def split_sentences(self, text):
        # Simple sentence splitting (for better results, use nltk or spacy)
        return [s.strip() for s in text.split('.') if s.strip()]

    def chunk_text(self, text, chunk_size=512):
        return [text[i:i+chunk_size] for i in range(0, len(text), chunk_size)]

    def generate(self, text, max_questions=5):
        questions = []
        sentences = self.split_sentences(text)

        for sentence in sentences:
            if len(questions) >= max_questions:
                break

            input_text = f"generate question: {sentence} </s>"
            try:
                result = self.qg(input_text, max_length=64, num_return_sequences=1)[0]
                question = result["generated_text"]
                if question and question not in questions:
                    questions.append(question)
            except Exception as e:
                print("Error generating question:", e)
                continue

        return questions