app.py

import streamlit as st 
from langchain_community.llms import HuggingFaceTextGenInference
import os
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
from langchain.schema import StrOutputParser
from datetime import datetime

from custom_llm import CustomLLM, custom_chain_with_history

from typing import Optional

from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain_core.chat_history import BaseChatMessageHistory
from langchain.memory import ConversationBufferMemory, PostgresChatMessageHistory




API_TOKEN = os.getenv('HF_INFER_API')
POSTGRE_URL = os.environ('POSTGRE_URL')



if 'memory' not in st.session_state:
    # st.session_state['memory'] = ConversationBufferMemory(return_messages=True)
    
    st.session_state.memory = PostgresChatMessageHistory(connection_string=POSTGRE_URL, session_id=str(datetime.timestamp(datetime.now())))

if 'chain' not in st.session_state:
    st.session_state['chain'] = custom_chain_with_history(
        llm=CustomLLM(repo_id="mistralai/Mixtral-8x7B-Instruct-v0.1", model_type='text-generation', api_token=API_TOKEN, stop=["\n<|","<|"]), 
        # memory=st.session_state.memory.chat_memory,
        memory=st.session_state.memory
    )

st.title("Chat With Me")
st.subheader("by Jonathan Jordan")

# Initialize chat history
if "messages" not in st.session_state:
    st.session_state.messages = [{"role":"assistant", "content":"Hello, My name is Jonathan Jordan. You can call me Jojo. How can I help you today?"}]

# 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("Ask me anything.."):
    # 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})
    
    response = st.session_state.chain.invoke(prompt).split("\n<|")[0]

    # Display assistant response in chat message container
    with st.chat_message("assistant"):
        st.markdown(response)
    st.session_state.memory.save_context({"question":prompt}, {"output":response})
    st.session_state.memory.chat_memory.messages = st.session_state.memory.chat_memory.messages[-15:]
    # Add assistant response to chat history
    st.session_state.messages.append({"role": "assistant", "content": response})