update

app.py

@@ -17,7 +17,7 @@ ner_pipeline = pipeline(
 
 
 def format_entities_as_html(entities):
-    excluded_keys = {"start", "end", "index", "word"}  # Keys to exclude from the output
+    excluded_keys = {"start", "end", "index", "text"}  # Keys to exclude from the output
     html_output = "<div>"
 
     for entity in entities:
@@ -50,7 +50,7 @@ def prepare_entities_for_highlight(text, results):
     print(f"Original text: {text}")
     print("Results:", results)
     # it should look like:
-    # [{'entity': 'org.ent.pressagency.Reuters', 'score': np.float32(98.47), 'index': 78, 'word': 'Reuters', 'start': 440, 'end': 447}]
+    # [{'entity': 'org.ent.pressagency.Reuters', 'score': np.float32(98.47), 'index': 78, 'text': 'Reuters', 'start': 440, 'end': 447}]
     for entity in results:
         entity_span = (entity["start"], entity["end"])
 
@@ -61,7 +61,6 @@ def prepare_entities_for_highlight(text, results):
                 entity["start"] : entity["end"]
             ].strip()  # Ensure we're working with the correct portion of the text
             entity["text"] = entity_text
-            entity.pop("word")
             print(f"Entity text: {entity}")
 
             entities.append(entity)