Added token and connected inference client

app.py

@@ -1,12 +1,26 @@
 import gradio as gr
 import random
+import InferenceClient
+
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
 def random_message(message, history):
     choices = ["yes", "no"]
-    #use random to select one of those choices
+    # use random to select one of those choices
     chat_answer = random.choice(choices)
     return chat_answer
+
+def respond(message, history):
+    messages = [{"role": "system", "content": "You are a friendly chatbot."}]
+    if history:
+        messages.extend(history)
+
+    messages.append({"role": "user", "content" : message})
+
+    response = client.chat_completion(messages, max_tokens=100)
+    return response["choices"][0]["message"]["content"].strip()
+        
     
-chatbot = gr.ChatInterface(random_message, type = "messages", title = "ChatBot for KWK")
+chatbot = gr.ChatInterface(respond, type = "messages", title = "ChatBot for KWK")
 
 chatbot.launch()