import streamlit as st
from llama_cpp import Llama

st.set_page_config(page_title="Chat with AI", page_icon="🤖")

# Custom CSS for better styling
st.markdown("""
<style>
.stTextInput > div > div > input {
    background-color: #f0f2f6;
}
.chat-message {
    padding: 1.5rem; border-radius: 0.5rem; margin-bottom: 1rem; display: flex
}
.chat-message.user {
    background-color: #2b313e
}
.chat-message.bot {
    background-color: #475063
}
.chat-message .avatar {
  width: 20%;
}
.chat-message .avatar img {
  max-width: 78px;
  max-height: 78px;
  border-radius: 50%;
  object-fit: cover;
}
.chat-message .message {
  width: 80%;
  padding: 0 1.5rem;
  color: #fff;
}
</style>
""", unsafe_allow_html=True)

@st.cache_resource
def load_model():
    return Llama.from_pretrained(
        repo_id="Mykes/med_phi3-mini-4k-GGUF",
        filename="*Q4_K_M.gguf",
        verbose=False,
        n_ctx=256,
        n_batch=256,
        n_threads=4
    )

llm = load_model()

basic_prompt = "Q: {question}\nA:"

# 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 is your question?"):
    # 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})

    model_input = basic_prompt.format(question=prompt)
    
    # Display assistant response in chat message container
    with st.chat_message("assistant"):
        message_placeholder = st.empty()
        full_response = ""
        
        for token in llm(
            model_input,
            max_tokens=None,
            stop=["<end_of_turn>"],
            echo=True,
            stream=True
        ):
            full_response += token['choices'][0]['text']
            message_placeholder.markdown(full_response + "▌")
        message_placeholder.markdown(full_response)
    
    # Add assistant response to chat history
    st.session_state.messages.append({"role": "assistant", "content": full_response})

st.sidebar.title("Chat with AI")
st.sidebar.markdown("This is a simple chat interface using Streamlit and an AI model.")