File size: 3,091 Bytes
4e937f5
da03023
 
021e3cd
 
da03023
021e3cd
 
 
 
 
 
 
 
 
ebfa154
021e3cd
e308ec0
ebfa154
021e3cd
4e937f5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
da03023
 
 
 
4e937f5
da03023
 
 
 
 
 
 
 
 
4e937f5
e308ec0
 
 
 
 
ad44100
da03023
 
 
 
 
 
 
 
 
 
ebfa154
 
da03023
 
4e937f5
 
 
 
 
 
 
 
 
 
365ab23
4e937f5
 
 
365ab23
4e937f5
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
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("请确保设置了环境变量 API_URL 和 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": True,
        "messages": messages,
        "temperature": temperature,
        "top_p": top_p,
        "top_k": 20,
        "min_p": 0.1
    }

    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}")

    response = ""
    
    with requests.post(API_URL, headers=headers, json=data, stream=True) as r:
        for line in r.iter_lines():
            if line:
                try:
                    json_response = json.loads(line.decode('utf-8').replace('data: ', ''))
                    if 'choices' in json_response and len(json_response['choices']) > 0:
                        token = json_response['choices'][0].get('delta', {}).get('content', '')
                        if token:
                            response += token
                            yield response
                except json.JSONDecodeError:
                    continue


"""
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=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=0.96,
            step=0.05,
            label="Top-p (nucleus sampling)",
        ),
    ],
)


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