Update app.py

app.py

@@ -1,23 +1,10 @@
 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
-"""
+# ✅ Set up Hugging Face Inference API with the correct model
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
-import gradio as gr
-import requests
-
-def chat_with_mistral(user_input):
-    return "Hello! This is Bandar AI responding."
-
-# ✅ Fix: Enable API mode in Gradio
-iface = gr.Interface(fn=chat_with_mistral, inputs="text", outputs="text")
-
-iface.launch(share=True)
-
-
+# ✅ Define the response function
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -28,16 +15,19 @@ def respond(
 ):
     messages = [{"role": "system", "content": system_message}]
 
+    # Add chat history
     for val in history:
         if val[0]:
             messages.append({"role": "user", "content": val[0]})
         if val[1]:
             messages.append({"role": "assistant", "content": val[1]})
 
+    # Add the new user input
     messages.append({"role": "user", "content": message})
 
     response = ""
 
+    # ✅ Stream responses from Hugging Face API
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
@@ -46,18 +36,15 @@ def respond(
         top_p=top_p,
     ):
         token = message.choices[0].delta.content
-
         response += token
-        yield response
+        yield response  # Stream output in real-time
 
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# ✅ Improved Chatbot UI
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(value="You are Bandar AI, 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(
@@ -68,8 +55,10 @@ demo = gr.ChatInterface(
             label="Top-p (nucleus sampling)",
         ),
     ],
+    title="🤖 Bandar AI Chatbot",
+    description="🚀 Chat with Bandar AI, powered by Zephyr-7B."
 )
 
-
+# ✅ Run the chatbot
 if __name__ == "__main__":
     demo.launch()