Update app.py

app.py

@@ -3,7 +3,6 @@ import torch
 from transformers import pipeline
 import os
 import spaces
-import functools
 
 #load_dotenv()
 key=os.environ["HF_KEY"]
@@ -25,7 +24,6 @@ print("[INFO] load model ...")
 pipe=load_model()
 print("[INFO] model loaded")
 
-# Remove the @gr.cache decorator since it's not available
 @spaces.GPU
 def predict(text):
     outputs = pipe(text)
@@ -49,20 +47,19 @@ with gr.Blocks() as demo:
                 clear_btn = gr.Button("Clear")
                 submit_btn = gr.Button("Submit", variant="primary")
             
-            # Examples section with caching
-            gr.Examples(
-                examples=["العاصمة د <mask> هي الرباط","المغرب <mask> زوين","انا سميتي مريم، و كنسكن ف<mask> العاصمة دفلسطين"],
-                inputs=input_text,
-                cache_examples=True,
-                preprocess=True  # Precompute examples
-            )
-        
-        with gr.Column():
             # Output probabilities
             output_labels = gr.Label(
                 label="Prediction Results",
-                show_label=False,
-                num_top_classes=5  # Limit to top 5 predictions
+                show_label=False
+            )
+            
+            # Examples section without caching for now
+            gr.Examples(
+                examples=["العاصمة د <mask> هي الرباط","المغرب <mask> زوين","انا سميتي مريم، و كنسكن ف<mask> العاصمة دفلسطين"],
+                inputs=input_text,
+                fn=predict,  # Add the function to use for examples
+                outputs=output_labels,  # Add the output component
+                cache_examples=True
             )
 
     # Button actions
@@ -70,7 +67,7 @@ with gr.Blocks() as demo:
         predict,
         inputs=input_text,
         outputs=output_labels,
-        show_progress=True  # Show a progress indicator
+        show_progress=True
     )
     
     clear_btn.click(
@@ -79,5 +76,5 @@ with gr.Blocks() as demo:
     )
 
 # Launch the app with queue
-demo.queue(concurrency_count=3)  # Allow 3 concurrent predictions
-demo.launch()  # Remove show_api parameter if it causes issues
+demo.queue(concurrency_count=3)
+demo.launch()