Update app.py

app.py

@@ -2758,6 +2758,42 @@ def save_pdf_to_generated_dir(pdf_stream: io.BytesIO, project_id: str) -> str:
         logger.error(f"Failed to save PDF to generated dir: {e}", exc_info=True)
         return None
 
+def pdf_to_images_with_size_check(pdf_path, output_dir, size_limit_mb=4):
+    os.makedirs(output_dir, exist_ok=True)
+
+    # Convert PDF to images
+    images = convert_from_path(pdf_path, dpi=300)  # 300 DPI keeps quality
+    saved_files = []
+
+    for i, img in enumerate(images, start=1):
+        output_path = os.path.join(output_dir, f"page_{i}.jpg")
+
+        # Save to memory first to check size
+        img_bytes = io.BytesIO()
+        img.save(img_bytes, format="JPEG", quality=95)  # near-lossless
+        size_mb = len(img_bytes.getvalue()) / (1024 * 1024)
+
+        if size_mb > size_limit_mb:
+            print(f"Page {i}: {size_mb:.2f} MB → compressing...")
+            # Compress until under size limit
+            quality = 95
+            while size_mb > size_limit_mb and quality > 70:  # don't go below 70
+                img_bytes = io.BytesIO()
+                img.save(img_bytes, format="JPEG", quality=quality)
+                size_mb = len(img_bytes.getvalue()) / (1024 * 1024)
+                quality -= 5
+        else:
+            print(f"Page {i}: {size_mb:.2f} MB → no compression needed.")
+
+        # Write final image to disk
+        with open(output_path, "wb") as f:
+            f.write(img_bytes.getvalue())
+
+        saved_files.append(output_path)
+
+    return saved_files
+
+
 @app.route('/')
 def index():
     return render_template('app_index.html')
@@ -2833,7 +2869,8 @@ def process_pdf():
         total_time = time.time() - start_time
         print(f"-----------------------------Execution Time save_pdf_to_generated_dir() : {total_time}-----------------------------\n")
         # }
-
+        compressed_pages = pdf_to_images_with_size_check(pdf_path, "/tmp/compressed_pages", size_limit_mb=4)
+        
         # {
         # Extract & process
         # output_path, result = extract_images_from_pdf(saved_pdf_path)