Update app.py

app.py

@@ -2,32 +2,25 @@ import gradio as gr
 import asyncio
 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("microsoft/Phi-3.5-mini-instruct")
 
 
 async def respond(
     message,
-    history: list[tuple[str, str]],
+    history: list[dict],
     system_message,
     max_tokens,
     temperature,
     top_p,
 ):
+    # Ensure history is in OpenAI-style 'role' and 'content' format
     messages = [{"role": "system", "content": system_message}]
+    messages.extend(history)  # Add existing 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 user's latest message
     messages.append({"role": "user", "content": message})
 
     response = ""
-
     async for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
@@ -36,16 +29,12 @@ async def respond(
         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,
+    fn=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"),
@@ -58,8 +47,8 @@ demo = gr.ChatInterface(
             label="Top-p (nucleus sampling)",
         ),
     ],
+    chatbot=gr.Chatbot(type="messages"),  # Specify the 'messages' format
 )
 
-# Launch the app with concurrency for 4 users
 if __name__ == "__main__":
-    demo.queue(concurrency_count=4).launch()
+    demo.queue().launch()  # Simply call queue without `concurrency_count`