import streamlit as st
import random
import time
from inference import main
import torch
import gc
import os
import json

# Function to clear GPU memory
def clear_gpu_memory():
    if torch.cuda.is_available():
        torch.cuda.empty_cache()

# Function to clear CPU memory and run garbage collection
def clear_cpu_memory():
    gc.collect()  # Run garbage collection to clean up unused objects

def response_generator(prompt):
    history = []
    if os.path.exists('history.json'):
        with open('history.json', "r") as f:
            history = json.load(f)

    bot_response, history = main(prompt,history)
    with open('history.json', "w") as f:
        json.dump(history, f, indent=4)
    clear_gpu_memory()
    clear_cpu_memory()
    response = random.choice(
        [
            bot_response
        ]
    ) 
    yield response

st.title("Clinical Trial Information Bot")

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

for message in st.session_state.messages:
    with st.chat_message(message["role"]):
        st.markdown(message["content"])


# Accept user input
if prompt := st.chat_input("You can ask your question's here!!"):
    # Add user message to chat history
    st.session_state.messages.append({"role": "user", "content": prompt})
    # Display user message in chat message container
    with st.chat_message("user"):
        st.markdown(prompt)

    with st.chat_message("assistant"):
        response = st.write_stream(response_generator(prompt))
    st.session_state.messages.append({"role": "assistant", "content": response})