app.py

import gradio as gr
import requests
import os
import json

# ACCESS_TOKEN = os.getenv("HF_TOKEN")

def respond_with_prefix(message, history, max_tokens=512, temperature=0.7, top_p=0.95):
    system_prefix = "SYSTEM: "  # 시스템 프리픽스 추가
    modified_message = system_prefix + message  # 사용자 메시지에 프리픽스 적용
    
    data = {
        "model": "jinjavis:latest",
        "prompt": modified_message,
        "max_tokens": max_tokens,
        "temperature": temperature,
        "top_p": top_p
    }
    
    # API 요청
    response = requests.post("http://hugpu.ai:7877/api/generate", json=data, stream=True)
    
    partial_message = ""
    for line in response.iter_lines():
        if line:
            try:
                result = json.loads(line)
                if result.get("done", False):
                    break
                new_text = result.get('response', '')
                partial_message += new_text
                yield partial_message
            except json.JSONDecodeError as e:
                print(f"Failed to decode JSON: {e}")
                yield "An error occurred while processing your request."

demo = gr.ChatInterface(
    fn=respond_with_prefix,
    additional_inputs=[
        gr.Slider(minimum=1, maximum=2048, value=512, label="Max Tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, label="Temperature"),
        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, label="Top-P")
    ],
    theme="Nymbo/Nymbo_Theme"
)

if __name__ == "__main__":
    demo.queue(max_size=4).launch()