app.py

import os
import streamlit as st
from langchain_huggingface import HuggingFaceEmbeddings
from langchain_chroma import Chroma
from langchain_groq import ChatGroq
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain

# Ensure required environment variables are set
GROQ_API_KEY = os.getenv("GROQ_API_KEY")
if not GROQ_API_KEY:
    st.error("GROQ_API_KEY is not set. Please configure it in Hugging Face Spaces secrets.")
    st.stop()

# Function to set up the vectorstore
def setup_vectorstore():
    working_dir = os.path.dirname(os.path.abspath(__file__))
    persist_directory = f"{working_dir}/vector_db_dir"

    # Initialize HuggingFace Embeddings
    embeddings = HuggingFaceEmbeddings()

    # Initialize Chroma vectorstore
    vectorstore = Chroma(
        persist_directory=persist_directory,
        embedding_function=embeddings
    )
    return vectorstore

# Function to set up the chat chain
def chat_chain(vectorstore):
    llm = ChatGroq(model="llama-3.1-70b-versatile", 
                   temperature=0, 
                   groq_api_key=GROQ_API_KEY)
    
    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 configuration
st.set_page_config(
    page_title="Multi Doc Chat",
    page_icon="📚",
    layout="centered"
)

st.title("📚 Multi Documents Chatbot")

# Initialize session state variables
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:
    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"):
        # Generate response
        response = st.session_state.conversational_chain({"question": user_input})
        assistant_response = response["answer"]
        
        st.markdown(assistant_response)
        st.session_state.chat_history.append({"role": "assistant", "content": assistant_response})