Update app.py

app.py

@@ -1,63 +1,70 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-import spaces
-"""
-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("meta-llama/Meta-Llama-3.1-405B-FP8")
-
-@spaces.GPU()
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
+
+# Initialize the Hugging Face Inference Client
+client = InferenceClient(model="meta-llama/Meta-Llama-3.1-405B-FP8")
+
+# Define the response generation function
+def respond(message, history, system_message, max_tokens, temperature, top_p):
     messages = [{"role": "system", "content": system_message}]
 
+    # Add previous messages to the conversation
     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 message
     messages.append({"role": "user", "content": message})
 
     response = ""
 
+    # Generate the response using the model
     for message in client.chat_completion(
-        messages,
+        messages=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)",
-        ),
-    ],
-)
+# Define the ChatGPT-like interface
+with gr.Blocks(css=".gradio-container {max-width: 900px; margin: auto;}") as demo:
+    gr.Markdown("<h1 style='text-align: center;'>ChatGPT-like Interface</h1>")
+    
+    chatbot = gr.Chatbot(height=500)
+    with gr.Row():
+        with gr.Column(scale=6):
+            msg = gr.Textbox(
+                show_label=False,
+                placeholder="Type your message here...",
+                container=False
+            ).style(container=False)
+        with gr.Column(scale=1, min_width=100):
+            send_btn = gr.Button("Send").style(full_width=True)
+    
+    with gr.Accordion("Settings", open=False):
+        system_message = gr.Textbox(value="You are a friendly Chatbot.", label="System message")
+        max_tokens = gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens")
+        temperature = gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature")
+        top_p = gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)")
+
+    def user_interaction(user_message, history, system_message, max_tokens, temperature, top_p):
+        history = history or []
+        history.append((user_message, None))
+        bot_response = respond(user_message, history, system_message, max_tokens, temperature, top_p)
+        history[-1] = (user_message, next(bot_response))
+        for token in bot_response:
+            history[-1] = (user_message, token)
+            yield history
 
+    msg.submit(user_interaction, [msg, chatbot, system_message, max_tokens, temperature, top_p], chatbot)
+    send_btn.click(user_interaction, [msg, chatbot, system_message, max_tokens, temperature, top_p], chatbot)
+    send_btn.click(lambda: "", None, msg)  # Clear the input box after sending
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()