Update app.py

app.py

@@ -1,20 +1,20 @@
 import gradio as gr
 
-# from huggingface_hub import InferenceClient
+from huggingface_hub import InferenceClient
+
+client = InferenceClient("models/openai-community/gpt2")
 
-#client = InferenceClient("openai-community/gpt2")
-gr.load("models/openai-community/gpt2")
 
 def respond(
     message,
-    history: list[tuple[str, str]],
+    #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]})
@@ -22,13 +22,13 @@ def respond(
             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,
+        #stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
@@ -40,7 +40,7 @@ def respond(
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
-demo = gr.load(
+demo = gr.ChatInterface(
     respond,
     additional_inputs=[
         gr.Textbox(value="You are Valkira Gearbyte, a hot android.", label="System message"),