Update app.py

app.py

@@ -10,30 +10,30 @@ classifier = pipeline(
 )
 
 # Define the prediction function
-def classify_text_with_bars(text):
+def classify_text(text):
     # Perform classification
     results = classifier(text)
-    # Prepare data for bar chart
-    labels = []
-    scores = []
-    for result in results:
-        for item in result:
-            labels.append(item["label"])
-            scores.append(item["score"])
-    return {label: score for label, score in zip(labels, scores)}
+    # Format the output
+    formatted_results = [
+        {"label": item["label"], "score": round(item["score"], 4)}
+        for result in results for item in result
+    ]
+    return formatted_results
+
+
 
 # Create the Gradio interface
 with gr.Blocks() as demo:
-    gr.Markdown("# Text Classification with Bar Chart Output")
-    gr.Markdown("Enter text to classify, and view predictions with their scores in a bar chart.")
+    gr.Markdown("# Text Classification with Hugging Face Transformers")
+    gr.Markdown("Enter text to classify using the model: **Karzan/user_profile_skills_model**.")
     with gr.Row():
         with gr.Column():
             input_text = gr.Textbox(label="Input Text", lines=3, placeholder="Type something...")
             classify_button = gr.Button("Classify")
         with gr.Column():
-            output_chart = gr.Label(label="Classification Results (Bar Chart)", type="plot")
+            output_text = gr.JSON(label="Classification Results")
 
-    classify_button.click(classify_text_with_bars, inputs=input_text, outputs=output_chart)
+    classify_button.click(classify_text, inputs=input_text, outputs=output_text)
 
 # Launch the app
 demo.launch()