# pip install -U gradio huggingface_hub

import os
import gradio as gr
from huggingface_hub import InferenceClient

MODEL_ID = "Qwen/Qwen3-Coder-Next"
client = InferenceClient(model=MODEL_ID, token=os.environ.get("HF_TOKEN"))

def chat(user_msg, history):
    messages = []
    for u, a in history:
        messages += [{"role": "user", "content": u}, {"role": "assistant", "content": a}]
    messages.append({"role": "user", "content": user_msg})

    # Server-side Chat Completions (je nach Backend/Provider)
    resp = client.chat.completions.create(
        messages=messages,
        max_tokens=512,
        temperature=0.2,
    )
    return resp.choices[0].message["content"]

gr.ChatInterface(chat, title="Qwen3-Coder-Next (HF Inference API)").launch()