from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import torch

MODEL_NAME = "google/flan-t5-base"

tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
model = AutoModelForSeq2SeqLM.from_pretrained(MODEL_NAME)
model.eval()

def generate_response(prompt: str) -> str:
    inputs = tokenizer(prompt, return_tensors="pt", truncation=True)
    with torch.no_grad():
        outputs = model.generate(
            **inputs,
            max_new_tokens=160
        )
    return tokenizer.decode(outputs[0], skip_special_tokens=True)