import gradio as gr
from huggingface_hub import InferenceClient
from dotenv import load_dotenv
import os

# โหลดตัวแปรจาก .env
load_dotenv()


# ดึง token จาก environment variable
HF_TOKEN = os.getenv("HF_TOKEN")

# สร้าง InferenceClient ด้วย token
client = InferenceClient("iapp/chinda-qwen3-4b", token=HF_TOKEN)

# ฟังก์ชันสำหรับประมวลผลข้อความสนทนา
def respond(message, history: list[tuple[str, str]], system_message, max_tokens, temperature, top_p):
    # เตรียมข้อความตาม ChatML format
    messages = [{"role": "system", "content": system_message}]
    for user_msg, bot_msg in history:
        if user_msg:
            messages.append({"role": "user", "content": user_msg})
        if bot_msg:
            messages.append({"role": "assistant", "content": bot_msg})
    messages.append({"role": "user", "content": message})

    response = ""
    # เรียกใช้งานแบบ streaming
    for msg in client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        token = msg.choices[0].delta.content
        response += token
        # แยก 🧠 Thinking กับ 💬 Response ถ้ามี </think>
        if "</think>" in response:
            think_split = response.split("</think>", 1)
            thinking = think_split[0].replace("<think>", "").strip()
            content = think_split[1].strip()
            yield f"🧠 Thinking: {thinking}\n\n💬 Response: {content}"
        else:
            yield response

# สร้าง UI ด้วย Gradio
demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
    ],
)

if __name__ == "__main__":
    demo.launch()