app.py

import os
import pdfplumber
import gradio as gr
from dotenv import load_dotenv
from groq import Groq

# Load environment variables from a .env file
load_dotenv()
GROQ_API_KEY = os.getenv("GROQ_API_KEY")

# Instantiate the Groq client
client = Groq(api_key=GROQ_API_KEY)

def extract_text_from_pdf(pdf_file):
    text = ""
    with pdfplumber.open(pdf_file.name) 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."


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

    try:
        response = client.chat.completions.create(
            messages=[
                {
                    "role": "user",
                    "content": prompt
                }
            ],
            model="llama3-8b-8192",  # Replace with your desired model ID
        )
        return response.choices[0].message.content.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 Groq",
    description="Upload a PDF and get a summary using Groq's generative AI API."
)

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