app.py

import streamlit as st
import os
from dotenv import load_dotenv
from llama_index.readers.web import SimpleWebPageReader
from llama_index.core import VectorStoreIndex
from llama_index.embeddings.gemini import GeminiEmbedding
import google.generativeai as genai
from llama_index.llms.gemini import Gemini
from llama_index.core.node_parser import SentenceSplitter
from llama_index.core import Settings

st.title("LLM-Powered QA System")
load_dotenv()
api_key = os.getenv('GOOGLE_API_KEY')
model = Gemini(model_name="models/gemini-pro")

def validate_api_key():
    if not api_key:
        st.error("GOOGLE_API_KEY environment variable not found!")
        st.stop()
    genai.configure(api_key=api_key)

validate_api_key()
url = st.text_input("Enter Webpage URL to Process:")
question = st.text_input("Enter your question from the webpage:")

if st.button("Process Webpage"):
    if url:
        try:
            st.info("Fetching webpage content...")
            reader = SimpleWebPageReader(html_to_text=True)
            documents = reader.load_data(urls=[url])
            embed_model = GeminiEmbedding(model_name="models/embedding-001")
            Settings.llm = model
            Settings.embed_model = embed_model
            Settings.node_parser = SentenceSplitter(chunk_size=512, chunk_overlap=20)
            Settings.num_output = 512
            Settings.context_window = 3900
            index = VectorStoreIndex.from_documents(documents,settings = Settings)
            query_engine = index.as_query_engine()
            response = query_engine.query(question)
            st.write("Response:" + response.response)
        except Exception as e:
            st.error(f"Error occurred: {str(e)}")