try

app.py

@@ -1,8 +1,17 @@
 import gradio as gr
 import random
+from huggingface_hub import InferenceClient
+
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+
+def respond(message, history):
+    messages: [{"role": "system", "content": "You are a friendly chatbot."}]
+    if history:
+        messages.extend(history)
 def random_message(message, history):
     choices = ["you have 24 hours", "yay ur lucky or whateva", "do not step outside", "try again", "pop quiz days be like", "please tell me you're not asking about a man.", "my sources tell me no", "haha you thought", "Im like 90.9% sure your being watched"]
     random_element = random.choice(choices)
     return random_element
-chatbot = gr.ChatInterface(random_message, type = "messages", description ="<strong><center>Welcome to your 8 ball.</strong><br>Ask Me Anything", title ="Eight Ball"))
-chatbot.launch()
+chatbot = gr.ChatInterface(echo, type="messages", description ="<strong><center>Welcome to your 8 ball.</strong><br>Ask Me Anything", title="Eight Ball")
+
+chatbot.launch()