app.py

# app.py
import streamlit as st
from utils.pdf_processing import extract_text_from_pdf, split_into_chunks
from utils.embeddings import generate_embeddings
from utils.database import initialize_faiss, insert_embeddings, search_embeddings

def main():
    st.title("PDF Retrieval-Augmented Generation (RAG) Application")

    # Initialize FAISS index
    faiss_index = initialize_faiss()

    # Upload PDF file
    uploaded_file = st.file_uploader("Upload a PDF file", type="pdf")
    if uploaded_file is not None:
        # Extract text from the uploaded PDF
        with st.spinner("Processing PDF..."):
            text = extract_text_from_pdf(uploaded_file)
            chunks = split_into_chunks(text)

        # Generate embeddings for text chunks
        with st.spinner("Generating embeddings..."):
            embeddings = generate_embeddings(chunks)

        # Insert embeddings into FAISS index
        with st.spinner("Inserting embeddings into FAISS..."):
            insert_embeddings(faiss_index, embeddings, chunks)

        st.success("PDF processed and embeddings stored successfully!")

    # Search functionality
    query = st.text_input("Enter a query to search:")
    if query:
        with st.spinner("Searching..."):
            query_embedding = generate_embeddings([query])[0]
            results = search_embeddings(faiss_index, query_embedding)
            st.write("Results:", results)

if __name__ == "__main__":
    main()