app.py

import os
import streamlit as st
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 PyPDFLoader
from langchain_google_genai import GoogleGenerativeAIEmbeddings
import tempfile
from dotenv import load_dotenv

load_dotenv()

## Load the GROQ and Google 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="gemma2-9b-it")

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(pdf_files):
    st.session_state.embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
    docs = []
    for pdf_file in pdf_files:
        with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as temp_file:
            temp_file.write(pdf_file.read())
            temp_file_path = temp_file.name
        loader = PyPDFLoader(temp_file_path)
        docs.extend(loader.load())
    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
    final_documents = text_splitter.split_documents(docs[:20])
    st.session_state.vectors = FAISS.from_documents(final_documents, st.session_state.embeddings)

# File uploader
uploaded_files = st.file_uploader("Upload PDF files", accept_multiple_files=True, type=["pdf"])

if uploaded_files and st.button("Process Uploaded Files"):
    vector_embedding(uploaded_files)
    st.write("Vector Store DB is Ready")

prompt1 = st.text_input("What do you want to ask from the documents?")

import time

if prompt1:
    if "vectors" in st.session_state:
        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(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("--------------------------------")
    else:
        st.write("Please upload and process PDF files first.")