app.py

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

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

def generate_response(prompt):
    inputs = tokenizer(prompt, return_tensors="pt")
    output = model.generate(**inputs, max_new_tokens=150)
    return tokenizer.decode(output[0], skip_special_tokens=True)