Spaces:
Sleeping
Sleeping
Create app.py
Browse files
app.py
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import gradio as gr
|
| 2 |
+
from transformers import pipeline
|
| 3 |
+
import PyPDF2
|
| 4 |
+
|
| 5 |
+
# Load the summarization pipeline
|
| 6 |
+
summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
|
| 7 |
+
|
| 8 |
+
def summarize_pdf(pdf_file):
|
| 9 |
+
try:
|
| 10 |
+
# Extract text from the uploaded PDF
|
| 11 |
+
pdf_reader = PyPDF2.PdfReader(pdf_file)
|
| 12 |
+
text = ""
|
| 13 |
+
for page in pdf_reader.pages:
|
| 14 |
+
text += page.extract_text()
|
| 15 |
+
|
| 16 |
+
# Check if text was extracted
|
| 17 |
+
if not text.strip():
|
| 18 |
+
return "❌ Could not extract text from the PDF. Please upload a valid document."
|
| 19 |
+
|
| 20 |
+
# Summarize the extracted text
|
| 21 |
+
summary = summarizer(text, max_length=300, min_length=50, do_sample=False)
|
| 22 |
+
return summary[0]['summary_text']
|
| 23 |
+
|
| 24 |
+
except Exception as e:
|
| 25 |
+
return f"❌ An error occurred: {str(e)}"
|
| 26 |
+
|
| 27 |
+
# Create the Gradio interface
|
| 28 |
+
interface = gr.Interface(
|
| 29 |
+
fn=summarize_pdf,
|
| 30 |
+
inputs=gr.inputs.File(label="Upload PDF"),
|
| 31 |
+
outputs=gr.outputs.Textbox(label="Summary"),
|
| 32 |
+
title="PDF Summarizer",
|
| 33 |
+
description="Upload a PDF file to extract and summarize its content using state-of-the-art AI."
|
| 34 |
+
)
|
| 35 |
+
|
| 36 |
+
interface.launch()
|