Update app.py

app.py

@@ -1,7 +1,32 @@
+from huggingface_hub import InferenceClient 
+
 import gradio as gr
 import random
+
+
+# Making requests to the model to generate responses:
+client = InferenceClient('HuggingFaceH4/zephyr-7b-beta') 
+
+
 def respond(message, history):
-    responses = ["Yes", "No"]
-    return random.choice(responses)
+    #responses = ["Yes", "No"]
+    #return random.choice(responses)
+
+
+    messages = [{'role':'system', 'content': 'You are a mean chatbot'}]
+    
+    
+    
+    if history:
+        messages.extend(history)
+    
+    
+    
+    response = client.chat_completion(messages, max_tokens=100)
+
+    return response['choice'][0]['message']['content'].strip()
+
+
+    
 chatbot = gr.ChatInterface(respond, type="messages")
 chatbot.launch()