app.py

import streamlit as st
from transformers import pipeline
from transformers import AutoConfig, pipeline
from langchain_community.llms import Ollama
import time

st.title('*ChatBot clone*')

llm = Ollama(model='llama3:latest')

def response_generator(prompt):
    response = llm.invoke(prompt, stop=['<|eot_id|>'])
    for word in response.split():
        yield word + " "
        time.sleep(0.05)


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

# display chat history
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("What is up?"):
    # add user message to user history
    st.session_state.messages.append({'role':'user','content':prompt})
    # display user message
    with st.chat_message('user'):
        st.markdown(prompt)
    
    # display assistant response
    with st.chat_message('assistant'):
        ans = llm.invoke(prompt, stop=['<|eot_id|>'])
        respose = st.write_stream(response_generator(prompt))
    st.session_state.messages.append({'role':'assistant', 'content':respose})