app.py

import streamlit as st
import PyPDF2
from groq import Groq
import os

# Set up Groq API key
os.environ["GROQ_API_KEY"] = "myKey"

# Initialize Groq client
client = Groq(api_key=os.environ.get("GROQ_API_KEY"))

# Function to extract PDF content
def extract_pdf_content(pdf_file):
    pdf_text = ""
    reader = PyPDF2.PdfReader(pdf_file)
    for page in reader.pages:
        pdf_text += page.extract_text()
    return pdf_text

# Function to chunk text
def chunk_text(text, chunk_size=1000, overlap=200):
    chunks = []
    start = 0
    while start < len(text):
        end = start + chunk_size
        chunk = text[start:end]
        chunks.append(chunk)
        start += chunk_size - overlap
    return chunks

# Function to find relevant chunks
def find_relevant_chunks(chunks, query, num_chunks=3):
    return chunks[:num_chunks]  # Simple retrieval

# Chatbot function
def chatbot_response(user_query, chunks):
    relevant_chunks = find_relevant_chunks(chunks, user_query)
    combined_context = "\n\n".join(relevant_chunks)
    context = f"PDF Content:\n{combined_context}\n\nUser Query: {user_query}"
    chat_completion = client.chat.completions.create(
        messages=[{"role": "user", "content": context}],
        model="llama-3.3-70b-versatile",
    )
    return chat_completion.choices[0].message.content

# Streamlit UI
st.title("PDF Query Chatbot")
st.write("Upload a PDF and ask questions based on its content.")

# File upload
pdf_file = st.file_uploader("Upload a PDF file", type=["pdf"])

if pdf_file:
    with st.spinner("Extracting content..."):
        pdf_content = extract_pdf_content(pdf_file)
        chunks = chunk_text(pdf_content)
        st.success("PDF content loaded successfully!")

    user_query = st.text_input("Ask a question about the PDF:")
    
    if user_query:
        with st.spinner("Fetching response..."):
            response = chatbot_response(user_query, chunks)
            st.write(f"**Chatbot Response:** {response}")