text box

app.py

@@ -6,9 +6,13 @@ qa_pipeline = pipeline(task="question-answering",model="Intel/bert-base-uncased-
 def greet(name):
     return "Hello " + name + "!!"
 
-def predict(question="How many continents are there in the world?",context="There are seven continents in the world."):
+def predict(context="There are seven continents in the world.",question="How many continents are there in the world?"):
+    '''
+    Sample prediction should return a dictionary of the form:
+    {'score': 0.9376363158226013, 'start': 10, 'end': 15, 'answer': 'seven'}
     
-    predictions = qa_pipeline(question=question,context=context)
+    '''
+    predictions = qa_pipeline(context=context,question=question)
     print(f'predictions={predictions}')
     return predictions
 
@@ -21,14 +25,15 @@ Based on the Zafrir et al. (2021) paper: [Prune Once for All: Sparse Pre-Trained
 
 """
 
-predict()
+# predict()
 
-# iface = gr.Interface(
-#     fn=predict, 
-#     inputs="Input your question.", 
-#     outputs="text",
-#     title = "Question & Answer with Sparse BERT using the SQuAD dataset",
-#     description = md
-#     )
+iface = gr.Interface(
+    fn=predict, 
+    inputs=[gr.TextBox('Context'),gr.TextBox('Question')],
+    outputs="text",
+    # examples = 
+    title = "Question & Answer with Sparse BERT using the SQuAD dataset",
+    description = md
+    )
 
-# iface.launch()
+iface.launch()