app.py

import google.generativeai as genai
import pdfplumber
import gradio as gr
import os
from dotenv import python_dotenv

python_dotenv()

# Replace with your API key
GOOGLE_API_KEY = os.getenv("GEMINI_API_KEY")
genai.configure(api_key=GOOGLE_API_KEY)

# Load Gemini Pro model
model = genai.GenerativeModel('gemini-pro')

def extract_text_from_pdf(pdf_file):
    text = ""
    with pdfplumber.open(pdf_file) as pdf:
        for page in pdf.pages:
            page_text = page.extract_text()
            if page_text:
                text += page_text
    return text

def summarize_pdf(pdf_file):
    text = extract_text_from_pdf(pdf_file)
    if not text.strip():
        return "No extractable text found in the PDF."

    # Limit text size if needed (Gemini handles long input, but it's safer)
    text = text[:15000]

    prompt = f"Summarize the following PDF content:\n\n{text}"

    try:
        response = model.generate_content(prompt)
        return response.text.strip()
    except Exception as e:
        return f"Error during summarization: {e}"

# Gradio interface
iface = gr.Interface(
    fn=summarize_pdf,
    inputs=gr.File(label="Upload PDF", file_types=[".pdf"]),
    outputs="text",
    title="PDF Summarizer with Gemini",
    description="Upload a PDF and get a summary using Google's Gemini Pro model."
)

if __name__ == "__main__":
    iface.launch()