app.py

import gradio as gr
import random
from huggingface_hub import InferenceClient 

client = InferenceClient("Qwen/Qwen2.5-7B-Instruct")

def respond(message, history):
    messages = [{"role": "system", "content": "You are a travel advisor helping plan a trip to Morocco. Give a week long itinerary. Focus on activities, not food."}]
    if history:
        messages.extend(history)
    messages.append({"role": "user", "content": message})

    # response = client.chat_completion(
    #     messages,
    #     max_tokens=100,
    #     temperature = 1.5,
    #     top_p = 0.34
    # )
    response = ""
    for msg in client.chat_completion(messages, stream=True):
        token = msg.choices[0].delta.content
        if token is not None:
            response += token
            yield response #response.choices[0].message.content.strip()
    
chatbot = gr.ChatInterface(respond, title="my bot")


chatbot.launch(debug=True)