update app.py and requirements

app.py

@@ -1,24 +1,19 @@
 from transformers import pipeline
 import gradio as gr
 
+# Load the NER pipeline
+ner = pipeline(
+    "ner",
+    model='kaiku03/bert-base-NER-finetuned_custom_complain_dataset_NER9',
+    aggregation_strategy="simple"
+)
 
-
-ner = pipeline("ner",
-               model='kaiku03/bert-base-NER-finetuned_custom_complain_dataset_NER9',
-              #  grouped_entities=True,
-               aggregation_strategy="simple"
-               )
-
-
-# function for the gradio app
+# Function for the Gradio app
 def fn_ner(prompt):
     entities = ner(prompt)
-    # Extract recognized entities and concatenate them into a single string
-    entity_string = ", ".join([entity['entity'] for entity in entities])
-    return entity_string
-
+    entity_info = "\n".join([f"{entity['entity_group']}: {entity['word']}" for entity in entities])
+    return entity_info
 
-# gradio app
 # Define example inputs and outputs
 examples = [
     "Subject: Defective Date: 08-13-2023 Product: XXX speaker Location: 456 Sound Avenue, Audiotown",
@@ -26,16 +21,16 @@ examples = [
     "Subject: Missing Parts Date: 08-10-2023 Product: XXX Furniture Set Location: 1800 Antipolo Rizal Furnitown",
 ]
 
+# Create Gradio interface
 iface = gr.Interface(
     fn=fn_ner,
     inputs='text',
-    outputs=gr.Label(label="Name Entity Recognition"),
-    examples=[
-        [ex] for ex in examples
-    ],
-    title='English to Tagalog translator',
-    description='This demo performs language translation from English to Tagalog.',
-    article='All done by Kaiku',
+    outputs='text',
+    examples=[[ex] for ex in examples],
+    title='Named Entity Recognition',
+    description='This demo performs named entity recognition (NER) on the input text.',
+    article='All done by Kaiku'
 )
 
+# Launch the interface
 iface.launch()

requirements.txt

@@ -1,5 +1,5 @@
 transformers
-gradio==3.40
+gradio==3.14
 torch
 seqeval 
 evaluate