Stream the response try it

app.py

@@ -4,27 +4,38 @@ from huggingface_hub import InferenceClient
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
 def respond(message, history):
-    messages = [{"role": "system", "content": "You are a friendly chatbot giving advice."}]
+    messages = [{"role": "system", "content": "You are a friendly chatbot."}]
     
     if history:
         messages.extend(history)
         
     messages.append({"role": "user", "content": message})
-    
-    response = client.chat_completion(
+
+    # Initialize the response as an empty string
+    response = ""
+
+    # Stream the response using yield and for loop
+    for message in client.chat_completion(
         messages,
-        max_tokens=150,  # Increased for longer responses
-        temperature=0.7,  # Medium randomness
-        top_p=0.9        # Keeps responses reasonably diverse
-    )
-    
-    return response['choices'][0]['message']['content'].strip()
+        max_tokens=150,
+        temperature=0.7,
+        top_p=0.9,
+        stream=True  # Enable streaming
+    ):
+        # Capture the most recent token
+        token = message['choices'][0]['delta']['content']
+        
+        # Add the token to the response
+        response += token
+        
+        # Yield the response to stream it progressively
+        yield response
 
 chatbot = gr.ChatInterface(
     respond, 
     type="messages",
-    title="Dynamic Chatbot",
-    description="A friendly chatbot with more dynamic and creative responses!"
+    title="Streaming Chatbot",
+    description="This chatbot streams responses as they are generated for a more dynamic experience!"
 )
 
 chatbot.launch()