Create app.py

app.py

@@ -0,0 +1,113 @@
+import fitz  # PyMuPDF
+import pytesseract
+from PIL import Image
+import io
+from fpdf import FPDF
+import gradio as gr
+import os
+from pathlib import Path
+
+GROQ_API_KEY = "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"
+client = Groq(api_key=GROQ_API_KEY)
+
+# Function to summarize text using Groq API
+def summarize_text(text, model="llama-3.1-70b-versatile"):
+    try:
+        chat_completion = client.chat.completions.create(
+            messages=[{"role": "user", "content": "Summarize this page in 15-20 lines under the heading of summary. You have to summarize, even if there are different, unlike topics on that page. (Kindly provide the response in proper paragraphing). However, if there is no text, then print Nothing to summarize. Additionally, after summarizing the text, enlist difficult terms up to 15, along with their single line meaning." + text}],
+            model=model,
+        )
+        return chat_completion.choices[0].message.content
+    except Exception as e:
+        print(f"[ERROR] Error in summarizing text: {e}")
+        return "Error in summarizing text."
+
+# Function to extract text from PDF and generate a summarized PDF
+def extract_text_and_summarize(filepath):
+    try:
+        if not os.path.exists(filepath):
+            print(f"[ERROR] File does not exist: {filepath}")
+            return "File does not exist."
+        
+        doc = fitz.open(filepath)
+        print("[INFO] PDF opened successfully.")
+        
+        # Initialize PDF to store summaries
+        pdf_summary = FPDF()
+        pdf_summary.set_auto_page_break(auto=True, margin=15)
+        
+        # Process up to 50 pages
+        for page_num in range(min(doc.page_count, 50)):
+            data = ""  # Initialize text variable for each page
+            
+            print(f"[INFO] Extracting text from Page {page_num + 1}.")
+            
+            page = doc.load_page(page_num)
+            
+            # Extracting text
+            data += page.get_text()
+            print(f"[DEBUG] Text extracted from Page {page_num + 1}: {data[:100]}...")  # Print first 100 characters
+            
+            # Extracting images and performing OCR
+            image_list = page.get_images(full=True)
+            for img_index, img in enumerate(image_list):
+                try:
+                    xref = img[0]
+                    base_image = doc.extract_image(xref)
+                    image_bytes = base_image["image"]
+                    image_ext = base_image["ext"]
+                    image = Image.open(io.BytesIO(image_bytes))
+
+                    # Performing OCR on the image
+                    ocr_text = pytesseract.image_to_string(image)
+                    data += ocr_text
+                except Exception as e:
+                    print(f"[ERROR] Error processing image on Page {page_num + 1}: {e}")
+
+            # Send the extracted text to LLM for summarization
+            summary = summarize_text(data)
+            
+            # Add the summary to the output PDF
+            pdf_summary.add_page()
+            pdf_summary.set_font("Arial", size=12)
+            pdf_summary.multi_cell(0, 7, f"Summary of Page {page_num + 1}\n\n" + summary.encode('utf-8').decode('latin-1'))
+        
+        # Save the output PDF
+        output_pdf_path = filepath.replace(".pdf", "_summary.pdf")
+        pdf_summary.output(output_pdf_path)
+        print("[INFO] Output PDF saved successfully.")
+        
+        return output_pdf_path
+
+    except Exception as e:
+        print(f"[ERROR] Error processing the PDF: {e}")
+        return "Error processing the PDF."
+
+# Function to handle file upload and initiate processing
+def upload_file(filepath):
+    # Set status message to indicate processing
+    status_message = "Processing, Please wait..."
+    output_pdf_path = extract_text_and_summarize(filepath)
+# Return status message and download button
+    return status_message, gr.update( visible=True, value=output_pdf_path)
+
+def reset_interface(): # Function to reset the interface
+    return "", gr.update(visible=False)
+
+# Create Gradio Interface
+with gr.Blocks(css=".block {max-width: 800px; margin: auto; padding: 20px;}") as demo:
+    gr.Markdown("""
+    <h1 style='text-align: center; color: #4CAF50;'>PDF Summarizer</h1>
+    <p style='text-align: center; font-size: 1.2em; color: #666;'>Upload a PDF document and get a summarized version with page-by-page analysis and difficult term definitions for first 50 pages. Perfect for quick reviews and study aids!</p>
+    """)
+    
+    with gr.Row():
+        u = gr.UploadButton("📁 Upload your PDF", file_count="single")
+        d = gr.DownloadButton("⬇️ Download the summarized PDF", visible=False)
+        status = gr.Textbox(label="Status", placeholder="Status will be displayed here...", visible=True, interactive=False)
+
+    u.upload(upload_file, u, [status, d])
+    d.click(reset_interface, None, [status, d])
+
+if __name__ == "__main__":
+    demo.launch()