File size: 1,371 Bytes
9008d0c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 |
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()
|