Update app.py

app.py

@@ -4,15 +4,19 @@ from huggingface_hub import InferenceClient
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta") #change LLM
 
 def respond(message, history):
-    messages = [{"role": "system", "content": "You are a friendly chatbot."}] #change personality
+    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.append({"role": "user", "content": message})
+    response = ""
+    for message in client.chat_completion(
         messages,
-        max_tokens=100 #change response length
-    )
-    return response['choices'][0]['message']['content'].strip()
+        max_tokens=100,
+        stream=True,
+    ):
+        token = messages.choices[0].delta.content
+        response += token
+        yield response
 
 chatbot = gr.ChatInterface(respond, type="messages")