Update app.py

app.py

@@ -1,64 +1,56 @@
+from sklearn.feature_extraction.text import CountVectorizer
+from sklearn.naive_bayes import MultinomialNB
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
 
+# Example data
+train_queries = [
+    "How do I activate my card?",
+    "What is the age limit for opening an account?",
+    "Do you support Apple Pay or Google Pay?",
+]
+train_labels = [0, 1, 2]
+
+responses = {
+    0: "To activate your card, please go to the app's settings.",
+    1: "The age limit for opening an account is 18 years.",
+    2: "Yes, we support Apple Pay and Google Pay.",
+}
+
+label_to_intent = {0: "activate_my_card", 1: "age_limit", 2: "apple_pay_or_google_pay"}
+
+# Prepare the Naive Bayes model
+vectorizer = CountVectorizer()
+X_train = vectorizer.fit_transform(train_queries)
+
+clf = MultinomialNB()
+clf.fit(X_train, train_labels)
+
+# Define the chatbot response function
+def naive_bayes_response(user_input):
+    vectorized_input = vectorizer.transform([user_input])
+    predicted_label = clf.predict(vectorized_input)[0]
+    return responses.get(predicted_label, "Sorry, I couldn't understand your query.")
+
+# Define Gradio interface
+def chatbot_interface(user_input):
+    return naive_bayes_response(user_input)
+
+# UI design with Gradio
+with gr.Blocks() as demo:
+    gr.Markdown("# Naive Bayes Chatbot")
+    gr.Markdown("This is a chatbot powered by Naive Bayes that handles basic queries.")
+    with gr.Row():
+        with gr.Column():
+            user_input = gr.Textbox(
+                label="Your Query",
+                placeholder="Type your question here...",
+                lines=1,
+            )
+            submit_btn = gr.Button("Submit")
+        with gr.Column():
+            response = gr.Textbox(label="Chatbot Response", interactive=False)
+    submit_btn.click(chatbot_interface, inputs=user_input, outputs=response)
+
+# Run the app
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()