fixed NER

app.py

@@ -114,18 +114,34 @@ def run_example(image, model_id="Qwen/Qwen2-VL-7B-Instruct", run_ner=False, ner_
             threshold=0.3
         )
         
-        # Format entities for highlighting
-        entities = []
-        for entity in ner_results:
-            entities.append((
-                entity["start"],
-                entity["end"],
+        # Create a list of tuples (text, label) for highlighting
+        highlighted_text = []
+        last_end = 0
+        
+        # Sort entities by start position
+        sorted_entities = sorted(ner_results, key=lambda x: x["start"])
+        
+        # Process each entity and add non-entity text segments
+        for entity in sorted_entities:
+            # Add non-entity text before the current entity
+            if last_end < entity["start"]:
+                highlighted_text.append((ocr_text[last_end:entity["start"]], None))
+            
+            # Add the entity text with its label
+            highlighted_text.append((
+                ocr_text[entity["start"]:entity["end"]],
                 entity["label"]
             ))
+            last_end = entity["end"]
+        
+        # Add any remaining text after the last entity
+        if last_end < len(ocr_text):
+            highlighted_text.append((ocr_text[last_end:], None))
         
-        return [(ocr_text, entities)]
+        return highlighted_text
     
-    return [(ocr_text, [])]
+    # If NER is disabled, return the text without highlighting
+    return [(ocr_text, None)]
 
 css = """
   /* Overall app styling */