import streamlit as st
from transformers import AutoTokenizer
from transformers import AutoModelForCausalLM

@st.cache_resource
def load_model():
    model_name = "iamthehimansh/3dAiWeb-gguff"
    tokenizer = AutoTokenizer.from_pretrained(model_name)
    model = AutoModelForCausalLM.from_pretrained(model_name, model_type="llama")
    return tokenizer, model

tokenizer, model = load_model()

def generate_response(prompt):
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(**inputs, max_length=100, num_return_sequences=1)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response

st.title("3D AI Web Chat Interface")

# Initialize chat history
if "messages" not in st.session_state:
    st.session_state.messages = []

# Display chat messages from history on app rerun
for message in st.session_state.messages:
    with st.chat_message(message["role"]):
        st.markdown(message["content"])

# React to user input
if prompt := st.chat_input("What would you like to know about 3D scenes?"):
    # Display user message in chat message container
    st.chat_message("user").markdown(prompt)
    # Add user message to chat history
    st.session_state.messages.append({"role": "user", "content": prompt})

    # Generate response
    with st.chat_message("assistant"):
        with st.spinner("Thinking..."):
            response_text = generate_response(prompt)
        st.markdown(response_text)
    
    # Add assistant response to chat history
    st.session_state.messages.append({"role": "assistant", "content": response_text})

st.sidebar.markdown("## About")
st.sidebar.info("This app provides a chat interface to interact with the iamthehimansh/3dAiWeb-gguf model. You can ask questions or discuss topics related to 3D scenes.")