import os
import json
import streamlit as st
from langchain_huggingface import HuggingFaceEmbeddings
from langchain_postgres.vectorstores import PGVector
from langchain_groq import ChatGroq
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain

# Load the embeddings function
from vectorize_data_pgvector import embeddings  # Assuming embeddings are imported from your previous script

# Load configuration
working_dir = os.path.dirname(os.path.abspath(__file__))
config_data = json.load(open(f"{working_dir}/config.json"))
GROQ_API_KEY = config_data["GROQ_API_KEY"]
os.environ["GROQ_API_KEY"] = GROQ_API_KEY

# Define the connection string and collection name for PostgreSQL
connection_string = "postgresql+psycopg2://postgres:krishna@localhost:5432/whatsapp_vector_db"
collection_name = "whatsapp_chatbot"

# Set up the PGVector-based vectorstore
def setup_vectorstore():
    embeddings = HuggingFaceEmbeddings()  # Use HuggingFaceEmbeddings
    vectorstore = PGVector(
        embeddings=embeddings,
        connection=connection_string,
        collection_name=collection_name,
        
    )
    return vectorstore

# Set up the conversational chain
def chat_chain(vectorstore):
    llm = ChatGroq(
        model="llama-3.1-70b-versatile",
        temperature=0
    )
    retriever = vectorstore.as_retriever()
    memory = ConversationBufferMemory(
        llm=llm,
        output_key="answer",
        memory_key="chat_history",
        return_messages=True
    )
    chain = ConversationalRetrievalChain.from_llm(
        llm=llm,
        retriever=retriever,
        chain_type="stuff",
        memory=memory,
        verbose=True,
        return_source_documents=True
    )
    return chain

# Streamlit UI setup
st.set_page_config(
    page_title="WhatsApp FAQ AI",
    page_icon="🤖AI",
    layout="centered"
)

st.title("🤖AI WhatsApp FAQ")

# Initialize session state for chat history and vectorstore
if "chat_history" not in st.session_state:
    st.session_state.chat_history = []

if "vectorstore" not in st.session_state:
    st.session_state.vectorstore = setup_vectorstore()

if "conversational_chain" not in st.session_state:
    st.session_state.conversational_chain = chat_chain(st.session_state.vectorstore)

# Display chat history
for message in st.session_state.chat_history:
    with st.chat_message(message["role"]):
        st.markdown(message["content"])

# User input
user_input = st.chat_input("Ask AI....")

if user_input:
    # Append user message to chat history
    st.session_state.chat_history.append({"role": "user", "content": user_input})

    with st.chat_message("user"):
        st.markdown(user_input)

    with st.chat_message("assistant"):
        response = st.session_state.conversational_chain({"question": user_input})
        assistant_response = response["answer"]
        st.markdown(assistant_response)

        # Append assistant response to chat history
        st.session_state.chat_history.append({"role": "assistant", "content": assistant_response})