Update app.py

app.py

@@ -1,5 +1,6 @@
 import gradio as gr
 from transformers import pipeline
+import datetime
 
 # Load your fine-tuned multi-label classification model
 classifier = pipeline(
@@ -15,28 +16,22 @@ label_map = {f"LABEL_{i}": label for i, label in enumerate(labels)}
 
 # Define the prediction function
 def classify_numbers(input1, input2, input3):
-    inputs = {
-        "Input1": input1,
-        "Input2": input2,
-        "Input3": input3
-    }
-    
-    print(f"Received inputs: {inputs}")  # Log inputs
+    inputs = {"Input1": input1, "Input2": input2, "Input3": input3}
+    print(f"[{datetime.datetime.now()}] Received inputs: {inputs}")
     
     results = {}
-
-    for name, value in inputs.items():
-        if value.strip():  # only process non-empty input
-            output = classifier(value)[0]
-            result = {
-                label_map[item["label"]]: round(item["score"], 3)
-                for item in output
-            }
-            results[name] = result
-        else:
-            results[name] = {}
-    
-    print(f"Returning results: {results}")  # Log outputs
+    try:
+        for name, value in inputs.items():
+            if value.strip():
+                output = classifier(value)[0]
+                result = {label_map[item["label"]]: round(item["score"], 3) for item in output}
+                results[name] = result
+            else:
+                results[name] = {}
+        print(f"[{datetime.datetime.now()}] Returning results: {results}")
+    except Exception as e:
+        print(f"[{datetime.datetime.now()}] Error during classification: {e}")
+        raise e
     
     return results