app.py

import os
import streamlit as st
from PyPDF2 import PdfReader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import FAISS
from groq import Groq
import requests

# Helper function to download and load the PDF from Google Drive
def load_pdf_from_drive(output_path="downloaded_document.pdf"):
    drive_link = "https://drive.google.com/file/d/1SzVEuEdKi4dHeKgDrUbmoq1MShB-hyG4/view?usp=drive_link"
    file_id = drive_link.split("/d/")[1].split("/")[0]
    download_url = f"https://drive.google.com/uc?export=download&id={file_id}"
    response = requests.get(download_url)
    with open(output_path, "wb") as f:
        f.write(response.content)
    return output_path

# Helper function to parse the PDF
def load_pdf_content(pdf_path):
    reader = PdfReader(pdf_path)
    text = ""
    for page in reader.pages:
        text += page.extract_text()
    return text

# Define the Streamlit app
st.title("RAG-Based Application with Groq API")
st.write("Processing a predefined PDF document from Google Drive to create a vector database and interact with it.")

st.write("Downloading and processing the document...")

# Download and load content from the PDF
pdf_path = load_pdf_from_drive()
document_text = load_pdf_content(pdf_path)

# Split the text into manageable chunks
text_splitter = RecursiveCharacterTextSplitter(
    chunk_size=1000, chunk_overlap=200
)
text_chunks = text_splitter.split_text(document_text)

st.write(f"Document split into {len(text_chunks)} chunks.")

# Initialize embedding function
embedding_function = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")

# Create FAISS vector database
faiss_index = FAISS.from_texts(text_chunks, embedding=embedding_function)

st.write("Vector database created successfully.")

# Save the FAISS index
faiss_index.save_local("faiss_index")

# Initialize Groq client for querying
GROQ_API_KEY = "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"
client = Groq(api_key=GROQ_API_KEY)

# Chat interaction setup
st.write("Ask a question related to the document:")
user_query = st.text_input("Your question:")

if user_query:
    query_response = client.chat.completions.create(
        messages=[
            {"role": "user", "content": user_query}
        ],
        model="llama-3.3-70b-versatile",
    )
    st.write("Response:")
    st.write(query_response.choices[0].message.content)