update app

app.py

@@ -19,20 +19,25 @@ ner_pipeline = pipeline(
 # Helper function to flatten entities and prepare them for HighlightedText
 def prepare_entities_for_highlight(text, results):
     entities = []
+    seen_spans = set()  # Track the spans we have already added to avoid overlaps
+
     for category, entity_list in results.items():
         for entity in entity_list:
-            # Debugging information to check character positions
-            print(
-                f"Entity: {entity['word']}, Start: {entity['start']}, End: {entity['end']}, Type: {entity['entity']}"
-            )
-            # Append entity with character indices
-            entities.append(
-                {
-                    "start": entity["start"],
-                    "end": entity["end"],
-                    "label": f"{entity['entity']}",  # ({entity['score']:.2f}%)
-                }
-            )
+            entity_span = (entity["start"], entity["end"])
+
+            # Only add non-overlapping entities
+            if entity_span not in seen_spans:
+                seen_spans.add(entity_span)
+                entities.append(
+                    {
+                        "start": entity["start"],
+                        "end": entity["end"],
+                        "label": f"{entity['entity']}",
+                    }
+                )
+
+    # Sort entities by their start position
+    entities = sorted(entities, key=lambda x: x["start"])
 
     return {"text": text, "entities": entities}