from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

class Llama2Chatbot:
    def __init__(self):
        self.tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-hf")
        self.model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf")
        self.device = "cuda" if torch.cuda.is_available() else "cpu"
        self.model.to(self.device)

    def generate_response(self, prompt, max_length=100):
        inputs = self.tokenizer(prompt, return_tensors="pt").to(self.device)
        outputs = self.model.generate(**inputs, max_length=max_length)
        response = self.tokenizer.decode(outputs[0], skip_special_tokens=True)
        return response

def initialize_chatbot():
    return Llama2Chatbot()

def get_chatbot_response(chatbot, prompt):
    return chatbot.generate_response(prompt)