llm.py

from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("google/flan-t5-base")
model = AutoModelForSeq2SeqLM.from_pretrained("google/flan-t5-base")

def generate_answer(context, question):
    prompt = f"""
You are a helpful AI assistant.

Context:
{context}

Question: {question}

Answer as a helpful paragraph:"""

    inputs = tokenizer(prompt, return_tensors='pt', truncation=True, max_length=512)
    outputs = model.generate(
        **inputs,
        max_new_tokens=100,
        do_sample=False
    )
    return tokenizer.decode(outputs[0], skip_special_tokens=True).strip()