app.py

import streamlit as st
import os
from langchain_groq import ChatGroq
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.chains.combine_documents import create_stuff_documents_chain
from langchain_core.prompts import ChatPromptTemplate
from langchain.chains import create_retrieval_chain
from langchain_community.vectorstores import FAISS
from langchain_community.document_loaders import PyPDFDirectoryLoader
from langchain_google_genai import GoogleGenerativeAIEmbeddings
from dotenv import load_dotenv
import os
load_dotenv()

# Load the GROQ and OpenAI API KEY
groq_api_key = os.getenv('GROQ_API_KEY')
os.environ["GOOGLE_API_KEY"] = os.getenv("GOOGLE_API_KEY")

st.title("Gemma Model Document Q&A")

llm = ChatGroq(groq_api_key=groq_api_key, model_name="Llama3-8b-8192")

prompt = ChatPromptTemplate.from_template(
"""
Answer the questions based on the provided context only.
Please provide the most accurate response based on the question.
<context>
{context}
<context>
Questions: {input}
"""
)

def vector_embedding(uploaded_files):
    if "vectors" not in st.session_state:
        st.session_state.embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
        
        # Save the uploaded files and load them
        with open("uploaded_files.zip", "wb") as f:
            f.write(uploaded_files.getbuffer())
        
        # Extract the uploaded files
        os.system("unzip -o uploaded_files.zip -d ./uploaded_data")
        
        st.session_state.loader = PyPDFDirectoryLoader("./uploaded_data")  # Data Ingestion
        st.session_state.docs = st.session_state.loader.load()  # Document Loading
        st.session_state.text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)  # Chunk Creation
        st.session_state.final_documents = st.session_state.text_splitter.split_documents(st.session_state.docs)  # Splitting
        st.session_state.vectors = FAISS.from_documents(st.session_state.final_documents, st.session_state.embeddings)  # Vector OpenAI embeddings

uploaded_files = st.file_uploader("Upload Your PDF Files", accept_multiple_files=True, type=["pdf"])

if st.button("Documents Embedding"):
    if uploaded_files:
        vector_embedding(uploaded_files[0])
        st.write("Vector Store DB Is Ready")
    else:
        st.write("Please upload PDF files.")

prompt1 = st.text_input("Enter Your Question From Documents")

import time

if prompt1:
    document_chain = create_stuff_documents_chain(llm, prompt)
    retriever = st.session_state.vectors.as_retriever()
    retrieval_chain = create_retrieval_chain(retriever, document_chain)
    start = time.process_time()
    response = retrieval_chain.invoke({'input': prompt1})
    st.write(f"Response time: {time.process_time() - start} seconds")
    st.write(response['answer'])

    # With a streamlit expander
    with st.expander("Document Similarity Search"):
        # Find the relevant chunks
        for i, doc in enumerate(response["context"]):
            st.write(doc.page_content)
            st.write("--------------------------------")