app.py

import gradio as gr
import requests
import json
import os
from dotenv import load_dotenv

# 加载.env文件中的环境变量
load_dotenv()

# 从环境变量中读取配置
API_URL = os.getenv("API_URL")
API_TOKEN = os.getenv("API_TOKEN")

# 验证必要的环境变量
if not API_URL or not API_TOKEN:
    raise ValueError("make sure API_URL & API_TOKEN")

print(f"[INFO] starting:")
print(f"[INFO] API_URL: {API_URL[:6]}...{API_URL[-12:]}")
print(f"[INFO] API_TOKEN: {API_TOKEN[:10]}...{API_TOKEN[-10:]}")  # 只显示token的前10位和后10位

"""
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
"""

def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    messages = [{"role": "system", "content": system_message}]

    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})

    messages.append({"role": "user", "content": message})

    headers = {
        "Content-Type": "application/json",
        "Authorization": f"Bearer {API_TOKEN}"
    }

    data = {
        "model": "/data/DMind-1-mini",
        "stream": False,  # 改为非流式模式
        "messages": messages,
        "temperature": temperature,
        "top_p": top_p,
        "top_k": 20,
        "min_p": 0.1,
        "max_tokens": 16384
    }

    print(f"[INFO] process user msg...")
    print(f"[INFO] sysMsg: {system_message}")
    print(f"[INFO] userMsg: {message}")
    print(f"[INFO] modelParam: temperature={temperature}, top_p={top_p}")
    print(f"[INFO] reqData: {data}")

    try:
        with requests.post(API_URL, headers=headers, json=data) as r:
            if r.status_code == 200:
                json_response = r.json()
                if 'choices' in json_response and len(json_response['choices']) > 0:
                    content = json_response['choices'][0].get('message', {}).get('content', '')
                    if content:
                        # if '<think>' in content and '</think>' in content:
                        #     content = content.split('</think>')[-1].strip()
                        print(f"[INFO] response: {content}")
                        return content
            return "Service temporarily unavailable"
    except Exception as e:
        print(f"[ERROR] Request error: {e}")
        return "Service error occurred"


"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
        gr.Slider(minimum=1, maximum=32768, value=16384, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.6, 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(share=True)