Update app.py

app.py

@@ -1,4 +1,3 @@
-import json
 import pickle
 from sklearn.feature_extraction.text import CountVectorizer
 import gradio as gr
@@ -10,7 +9,7 @@ with open("naive_bayes_model.pkl", "rb") as model_file:
 with open("vectorizer.pkl", "rb") as vectorizer_file:
     vectorizer = pickle.load(vectorizer_file)
 
-# Define the responses dictionary
+# Define responses dictionary
 responses = {
     "activate_my_card": "To activate your card, log in to the app and navigate to the 'Activate Card' section.",
     "age_limit": "The minimum age to use this service is 18 years.",
@@ -40,17 +39,15 @@ def chatbot_response(user_input):
     predicted_label = clf.predict(vectorized_input)[0]
     return responses.get(predicted_label, "Sorry, I couldn't understand your question.")
 
-# Define the Gradio interface
+# Define Gradio interface
 interface = gr.Interface(
     fn=chatbot_response,
-    inputs=gr.Textbox(lines=2, label="Your Question", placeholder="Type your fintech question here..."),
-    outputs=gr.Textbox(label="Chatbot Response"),
-    title="FinTech Chatbot",
-    description="Ask your questions related to financial technology services, and I'll assist you!",
-    theme="huggingface"
+    inputs=gr.Textbox(lines=2, placeholder="Ask your fintech question here..."),
+    outputs="text",
+    title="Banking Chatbot",
+    description="A chatbot to handle banking-related queries using a Naive Bayes model."
 )
 
-
 if __name__ == "__main__":
     # Launch the Gradio app
-    interface.launch()
+    interface.launch()