Create app.py

app.py

@@ -0,0 +1,53 @@
+import gradio as gr
+from pdf2image import convert_from_path
+from PIL import Image
+import pytesseract
+from transformers import pipeline
+
+
+
+# Load summarization pipeline
+summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
+
+# Function to split text into chunks within model token limit
+def chunk_text(text, max_tokens=1000):
+    words = text.split()
+    for i in range(0, len(words), max_tokens):
+        yield " ".join(words[i:i+max_tokens])
+
+# Main function to handle PDF upload and summarize
+def summarize_image_pdf(pdf_file):
+    try:
+        # Convert PDF pages to images
+        images = convert_from_path(pdf_file.name, dpi=300)
+
+        # OCR: Extract text from each page
+        extracted_text = ""
+        for i, img in enumerate(images):
+            text = pytesseract.image_to_string(img)
+            extracted_text += f"\n\n--- Page {i+1} ---\n{text}"
+
+        # Summarize in chunks
+        summaries = []
+        for chunk in chunk_text(extracted_text):
+            summary = summarizer(chunk, max_length=130, min_length=30, do_sample=False)[0]['summary_text']
+            summaries.append(summary)
+
+        final_summary = "\n\n".join(summaries)
+        return final_summary
+
+    except Exception as e:
+        return f"❌ Error: {str(e)}"
+
+# Gradio UI
+interface = gr.Interface(
+    fn=summarize_image_pdf,
+    inputs=gr.File(label="📄 Upload Image-based PDF", type="file"),
+    outputs=gr.Textbox(label="📝 Summary"),
+    title="🧠 Image PDF Summarizer with OCR",
+    description="This app extracts text from scanned/image-based PDFs using OCR and summarizes it using Hugging Face's BART model.",
+)
+
+# Launch app
+if __name__ == "__main__":
+    interface.launch()