app.py

import streamlit as st
import os
import random, string

from langchain.chains import LLMChain
from langchain_core.prompts import (
    ChatPromptTemplate,
    HumanMessagePromptTemplate,
    MessagesPlaceholder,
)
from langchain_core.messages import SystemMessage
from langchain.chains.conversation.memory import ConversationBufferWindowMemory
from langchain_groq import ChatGroq

if 'chat_list' not in st.session_state:
    st.session_state.chat_list = []


def arr():
    for c_list in st.session_state.chat_list:
        with st.chat_message("user"):
            st.write("Question : " + c_list["ques"])
        with st.chat_message("machine"):
            st.write("Answer : " + c_list["ans"])

def main():

    """
    This function is the main entry point of the application. It sets up the Groq client, the Streamlit interface, and handles the chat interaction.
    """

    # Get Groq API key
    groq_api_key = st.secrets["Groq_API_key"]
    model = 'llama3-8b-8192'
    # Initialize Groq Langchain chat object and conversation
    groq_chat = ChatGroq(
        groq_api_key=groq_api_key, 
        model_name=model
    )

    st.title('Langchain Chatbot With llama3-8b-8192 model')
    
    # print("Hello! I'm your friendly Groq chatbot. I can help answer your questions, provide information, or just chat. I'm also super fast! Let's start our conversation!")
    st.markdown("Hello! I'm your friendly Groq chatbot, dev by GJ. I can help answer your questions, provide information, or just chat. I'm also super fast! Let's start our conversation!")

    system_prompt = 'You are a friendly conversational chatbot'
    conversational_memory_length = 5 # number of previous messages the chatbot will remember during the conversation

    if 'memory' not in st.session_state:
        st.session_state.memory = ConversationBufferWindowMemory(k=conversational_memory_length, memory_key="chat_history", return_messages=True)
    # st.write(st.session_state.memory)


    # user_question = st.text_input("Ask a question: ")
    user_question = st.chat_input("Ask a question:")
    if user_question:
        # Construct a chat prompt template using various components
        prompt = ChatPromptTemplate.from_messages(
            [
                SystemMessage(
                    content=system_prompt
                ),  # This is the persistent system prompt that is always included at the start of the chat.

                MessagesPlaceholder(
                    variable_name="chat_history"
                ),  # This placeholder will be replaced by the actual chat history during the conversation. It helps in maintaining context.

                HumanMessagePromptTemplate.from_template(
                    "{human_input}"
                ),  # This template is where the user's current input will be injected into the prompt.
            ]
        )

        # Create a conversation chain using the LangChain LLM (Language Learning Model)
        conversation = LLMChain(
            llm=groq_chat,  # The Groq LangChain chat object initialized earlier.
            prompt=prompt,  # The constructed prompt template.
            verbose=False,   # TRUE Enables verbose output, which can be useful for debugging.
            memory=st.session_state.memory,  # The conversational memory object that stores and manages the conversation history.
        )
        # The chatbot's answer is generated by sending the full prompt to the Groq API.
        response = conversation.predict(human_input=user_question)
        # st.text("Question: " + user_question)
        # st.text("Chatbot: " + response)
        result = {"ques":user_question, "ans":response}
        st.session_state.chat_list.append(result)
        arr()
        # st.write(st.session_state.memory)

if __name__ == "__main__":
    main()