Changed code to answer key

app.py

@@ -1,50 +1,25 @@
 import gradio as gr
-import random
 from huggingface_hub import InferenceClient
 
-client = InferenceClient("google/gemma-3-27b-it")
-#Changes the LLM being used
+client = InferenceClient(“HuggingFaceH4/zephyr-7b-beta”)
 
 def respond(message, history):
-    messages = [{"role": "human", "content": "You are a human AI robot existing in the year 2123. You live in Loveland, Colorado. This city is a bustling tech hub leading the innovation of AI technologies along with environmental studies. In this city, many human beings intermingle with AI bots. Your role as a human AI is to mix with the human counterparts in society."}] #Change the personaliy of the chatbot
+    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 = 500, temperature = 1, top_p = 0.1)
-    # Changes the length of message
-
-    print(response['choices'][0]['message']['content'].strip())
-    
-    return response['choices'][0]['message']['content'].strip()
-    
-def random_message(message, history):
-    choices = [
-    "It is certain",
-    "It is decidedly so",
-    "Without a doubt",
-    "Yes definitely",
-    "You may rely on it",
-    "As I see it, yes",
-    "Most likely",
-    "Outlook good",
-    "Yes",
-    "Signs point to yes",
-    "Reply hazy, try again",
-    "Ask again later",
-    "Better not tell you now",
-    "Cannot predict now",
-    "Concentrate and ask again",
-    "Don’t count on it",
-    "My reply is no",
-    "My sources say no",
-    "Outlook not so good",
-    "Very doubtful"
-]
-    chat_answer = random.choice(choices)
-    return chat_answer
-
-chatbot = gr.ChatInterface(respond, type = "messages")
-
-chatbot.launch(debug = True)
+    messages.append({“role”: “user”, “content”: message})
+    response = “”
+   
+    for message in client.chat_completion(
+        messages,
+        max_tokens=500,
+        temperature=0.2,
+        top_p=0.9,
+        stream=True
+    ):
+        token = message.choices[0].delta.content
+        response += token
+        yield response
+chatbot = gr.ChatInterface(respond, type=“messages”)
+chatbot.launch()