app

app.py

@@ -16,6 +16,29 @@ ner_pipeline = pipeline(
 )
 
 
+def format_entities_as_html(entities):
+    excluded_keys = {"start", "end", "index", "word"}  # Keys to exclude from the output
+    html_output = "<ul>"
+
+    for entity in entities:
+        html_output += "<li>"
+
+        # Dynamically add all fields except the excluded ones
+        for key, value in entity.items():
+            if key not in excluded_keys:
+                if isinstance(value, float):  # Format score if it's a float
+                    html_output += (
+                        f"<strong>{key.capitalize()}:</strong> {value:.2f}<br>"
+                    )
+                else:
+                    html_output += f"<strong>{key.capitalize()}:</strong> {value}<br>"
+
+        html_output += "</li>"
+
+    html_output += "</ul>"
+    return html_output
+
+
 # Helper function to align entities correctly and debug tokenization
 def prepare_entities_for_highlight(text, results):
     entities = []
@@ -45,7 +68,7 @@ def prepare_entities_for_highlight(text, results):
     # Sort entities by their start position
     entities = sorted(entities, key=lambda x: x["start"])
 
-    return {"text": text, "entities": entities}
+    return format_entities_as_html(entities)
 
 
 # Function to process the sentence and extract entities
@@ -64,7 +87,7 @@ def ner_app_interface():
     input_sentence = gr.Textbox(
         lines=5, label="Input Sentence", placeholder="Enter a sentence for NER..."
     )
-    output_entities = gr.HighlightedText(label="Extracted Entities")
+    output_entities = gr.HTML(label="Extracted Entities")
 
     # Interface definition
     interface = gr.Interface(