File size: 2,655 Bytes
96e2d26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import os
import time
import json
import random

from g4f import Model, ChatCompletion, Provider
from flask import Flask, request, Response
from flask_cors import CORS

app = Flask(__name__)
CORS(app)

@app.route("/chat/completions", methods=['POST'])
def chat_completions():
    streaming = request.json.get('stream', False)
    model = request.json.get('model', 'gpt-3.5-turbo')
    messages = request.json.get('messages')
    
    response = ChatCompletion.create(model=model, stream=streaming,
                                     messages=messages)
    
    if not streaming:
        while 'curl_cffi.requests.errors.RequestsError' in response:
            response = ChatCompletion.create(model=model, stream=streaming,
                                             messages=messages)

        completion_timestamp = int(time.time())
        completion_id = ''.join(random.choices(
            'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789', k=28))

        return {
            'id': 'chatcmpl-%s' % completion_id,
            'object': 'chat.completion',
            'created': completion_timestamp,
            'model': model,
            'usage': {
                'prompt_tokens': None,
                'completion_tokens': None,
                'total_tokens': None
            },
            'choices': [{
                'message': {
                    'role': 'assistant',
                    'content': response
                },
                'finish_reason': 'stop',
                'index': 0
            }]
        }

    def stream():
        for token in response:
            completion_timestamp = int(time.time())
            completion_id = ''.join(random.choices(
                'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789', k=28))

            completion_data = {
                'id': f'chatcmpl-{completion_id}',
                'object': 'chat.completion.chunk',
                'created': completion_timestamp,
                'model': 'gpt-3.5-turbo-0301',
                'choices': [
                    {
                        'delta': {
                            'content': token
                        },
                        'index': 0,
                        'finish_reason': None
                    }
                ]
            }

            yield 'data: %s\n\n' % json.dumps(completion_data, separators=(',' ':'))
            time.sleep(0.1)

    return app.response_class(stream(), mimetype='text/event-stream')


if __name__ == '__main__':
    config = {
        'host': '0.0.0.0',
        'port': 1337,
        'debug': True
    }

    app.run(**config)