app.py

from huggingface_hub import InferenceClient

import gradio as gr
import random

client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")

def respond(message, history):
 #   responses = ["Yes", "No"]
  #  return random.choice(responses)

    messages = [
        
        {"role":"system",
        "content":"act like google, a know it all, nice and concise"
    }
    ]

    if history:
        messages.extend(history)

    messages.append(

        {"role":"user",
        "content":message
        }
        
    )

    response = client.chat_completion(
        messages, max_tokens = 1000,temperature=1.3, top_p = 0.5
    )

    return response['choices'][0]['message']['content'].strip()


chatbot = gr.ChatInterface(respond, type="messages")
#temperature and top_p controls randomness

chatbot.launch()