import os
os.environ["HUGGINGFACEHUB_API_TOKEN"] = ""

from langchain_community.llms import HuggingFaceHub

llm = HuggingFaceHub(
    repo_id="meta-llama/Llama-2-7b-chat-hf",
    task="text-generation",
    model_kwargs={
        "max_new_tokens": 512,
        "temperature": 0.1,
        "seed": 42,
    },
)

from langchain.schema import (
    HumanMessage,
    SystemMessage,
    AIMessage,
)
from langchain_community.chat_models.huggingface import ChatHuggingFace

messages = [
    SystemMessage(content="You're a helpful assistant"),
]

chat_model = ChatHuggingFace(llm=llm)


while True:
    question = input("You: ")
    messages.append(HumanMessage(content=question))
    response = chat_model.invoke(messages)
    print(response)
    response = response.content
    messages.append(AIMessage(content=response))
    print(f"Bot: {response}")