Update app.py

app.py

@@ -2,6 +2,7 @@ import gradio as gr
 import random
 from huggingface_hub import InferenceClient
 
+
 client = InferenceClient("Qwen/Qwen2.5-72B-Instruct")
 
 def respond(message, history):
@@ -9,7 +10,12 @@ def respond(message, history):
     if history:
         messages.extend(history)
     messages.append({"role" : "user", "content" : message})
-    response = client.chat_completion(messages, max_tokens = 100)
+    response = ""
+    for message in client.chat_completion(
+        messages, 
+        max_tokens = 100, 
+        stream = True,
+    ):
     print(response["choices"][0]["message"]["content"].strip())
     return response["choices"][0]["message"]["content"].strip()
 
@@ -17,7 +23,9 @@ def echo(message, history):
     choices = ["yes", "no", "sure", "absolutely", "of course not", "by no means"]
     chat_answer = random.choice(choices)
     #use random to select ones of those choices
-    return chat_answer
+        token = messages.choices[0].delta.content
+        response += token
+        yield response
 
 chatbot = gr.ChatInterface(respond, type = 'messages')