app.py

import streamlit as st
import os
import faiss
import pickle
import time
from langchain_community.document_loaders import PyPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import FAISS
from dotenv import load_dotenv
from groq import Groq

# Load environment variables
load_dotenv()
GROQ_API_KEY = os.getenv("GROQ_API_KEY")

# Initialize Groq client
client = Groq(api_key=GROQ_API_KEY)

# Streamlit UI
def main():
    st.set_page_config(page_title="AskMyPdf", layout="wide")
    st.title("📄 AskMyPdf - AI-Powered PDF Q&A")
    
    # Sidebar
    with st.sidebar:
        st.header("How to Use")
        st.markdown("1️⃣ Upload a PDF document")
        st.markdown("2️⃣ Ask any question related to the document")
        st.markdown("3️⃣ Get AI-powered answers instantly! 📌")
        
        st.subheader("Settings")
        theme = st.radio("Choose Theme:", ["Light", "Dark"], index=0)
        st.subheader("Language")
        language = st.selectbox("Select Language", ["English", "French", "Spanish", "German"], index=0)
    
    st.subheader("Upload your PDF")
    uploaded_file = st.file_uploader("Choose a PDF file", type=["pdf"])
    
    if uploaded_file is not None:
        st.success(f"Uploaded: {uploaded_file.name}")
        
        # Save the uploaded file locally
        file_path = os.path.join("temp_files", uploaded_file.name)
        os.makedirs("temp_files", exist_ok=True)  # Ensure the directory exists
        
        with open(file_path, "wb") as f:
            f.write(uploaded_file.getbuffer())

        # Verify that the file exists before processing
        if not os.path.exists(file_path):
            st.error("Error: File was not saved properly. Please try again.")
            return

        # Progress Bar
        progress_bar = st.progress(0)
        with st.spinner("Processing your document..."):
            time.sleep(1)  # Simulating file processing
            try:
                loader = PyPDFLoader(file_path)  # Pass the correct file path
                documents = loader.load()
                progress_bar.progress(25)

                text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
                docs = text_splitter.split_documents(documents)
                progress_bar.progress(50)

                embeddings = HuggingFaceEmbeddings()
                vector_db = FAISS.from_documents(docs, embeddings)
                progress_bar.progress(75)

                faiss.write_index(vector_db.index, "faiss_index")
                progress_bar.progress(100)
                st.success("Document processed successfully!")

            except Exception as e:
                st.error(f"Error processing document: {e}")
                return

    st.subheader("Ask a Question")
    query = st.text_input("Enter your question")
    if st.button("Get Answer") and query:
        with st.spinner("Generating response..."):
            try:
                docs = vector_db.similarity_search(query, k=5)
                context = "\n".join([doc.page_content for doc in docs])

                chat_completion = client.chat.completions.create(
                    messages=[{"role": "user", "content": context + "\n" + query}],
                    model="llama-3.3-70b-versatile",
                )

                response = chat_completion.choices[0].message.content
                st.markdown("### Answer")
                st.write(response)

            except Exception as e:
                st.error(f"Error generating response: {e}")

if __name__ == "__main__":
    main()