from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
import torch

def load_model_and_tokenizer(model_name: str):
    """Load a model and tokenizer for inference."""
    tokenizer = AutoTokenizer.from_pretrained(model_name)
    model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
    return model, tokenizer

def generate_answer(model, tokenizer, prompt: str, max_tokens: int = 256):
    """Generate text output from a model given a prompt."""
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    with torch.no_grad():
        outputs = model.generate(**inputs, max_new_tokens=max_tokens)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

def build_pipeline(model_name: str, task="text2text-generation"):
    """Return a Hugging Face pipeline for inference."""
    return pipeline(task, model=model_name)