summaryrefslogtreecommitdiffstats
path: root/phind/__init__.py
blob: 863360cb207157e9807ddfb4f63a4ecb20ee3c61 (plain) (blame)
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
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
from datetime import datetime
from queue import Queue, Empty
from threading import Thread
from time import time
from urllib.parse import quote

from curl_cffi.requests import post

cf_clearance = ''
user_agent = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.0.0 Safari/537.36'


class PhindResponse:
    class Completion:
        class Choices:
            def __init__(self, choice: dict) -> None:
                self.text = choice['text']
                self.content = self.text.encode()
                self.index = choice['index']
                self.logprobs = choice['logprobs']
                self.finish_reason = choice['finish_reason']

            def __repr__(self) -> str:
                return f'''<__main__.APIResponse.Completion.Choices(\n    text           = {self.text.encode()},\n    index          = {self.index},\n    logprobs       = {self.logprobs},\n    finish_reason  = {self.finish_reason})object at 0x1337>'''

        def __init__(self, choices: dict) -> None:
            self.choices = list(map(self.Choices, choices))

    class Usage:
        def __init__(self, usage_dict: dict) -> None:
            self.prompt_tokens = usage_dict['prompt_tokens']
            self.completion_tokens = usage_dict['completion_tokens']
            self.total_tokens = usage_dict['total_tokens']

        def __repr__(self):
            return f'''<__main__.APIResponse.Usage(\n    prompt_tokens      = {self.prompt_tokens},\n    completion_tokens  = {self.completion_tokens},\n    total_tokens       = {self.total_tokens})object at 0x1337>'''

    def __init__(self, response_dict: dict) -> None:
        self.response_dict = response_dict
        self.id = response_dict['id']
        self.object = response_dict['object']
        self.created = response_dict['created']
        self.model = response_dict['model']
        self.completion = self.Completion(response_dict['choices'])
        self.usage = self.Usage(response_dict['usage'])

    def json(self) -> dict:
        return self.response_dict


class Search:
    def create(prompt: str, actualSearch: bool = True, language: str = 'en') -> dict:  # None = no search
        if user_agent == '':
            raise ValueError('user_agent must be set, refer to documentation')
        if cf_clearance == '':
            raise ValueError('cf_clearance must be set, refer to documentation')

        if not actualSearch:
            return {
                '_type': 'SearchResponse',
                'queryContext': {
                    'originalQuery': prompt
                },
                'webPages': {
                    'webSearchUrl': f'https://www.bing.com/search?q={quote(prompt)}',
                    'totalEstimatedMatches': 0,
                    'value': []
                },
                'rankingResponse': {
                    'mainline': {
                        'items': []
                    }
                }
            }

        headers = {
            'authority': 'www.phind.com',
            'accept': '*/*',
            'accept-language': 'en,fr-FR;q=0.9,fr;q=0.8,es-ES;q=0.7,es;q=0.6,en-US;q=0.5,am;q=0.4,de;q=0.3',
            'cookie': f'cf_clearance={cf_clearance}',
            'origin': 'https://www.phind.com',
            'referer': 'https://www.phind.com/search?q=hi&c=&source=searchbox&init=true',
            'sec-ch-ua': '"Chromium";v="112", "Google Chrome";v="112", "Not:A-Brand";v="99"',
            'sec-ch-ua-mobile': '?0',
            'sec-ch-ua-platform': '"macOS"',
            'sec-fetch-dest': 'empty',
            'sec-fetch-mode': 'cors',
            'sec-fetch-site': 'same-origin',
            'user-agent': user_agent
        }

        return post('https://www.phind.com/api/bing/search', headers=headers, json={
            'q': prompt,
            'userRankList': {},
            'browserLanguage': language}).json()['rawBingResults']


class Completion:
    def create(
            model='gpt-4',
            prompt: str = '',
            results: dict = None,
            creative: bool = False,
            detailed: bool = False,
            codeContext: str = '',
            language: str = 'en') -> PhindResponse:

        if user_agent == '':
            raise ValueError('user_agent must be set, refer to documentation')

        if cf_clearance == '':
            raise ValueError('cf_clearance must be set, refer to documentation')

        if results is None:
            results = Search.create(prompt, actualSearch=True)

        if len(codeContext) > 2999:
            raise ValueError('codeContext must be less than 3000 characters')

        models = {
            'gpt-4': 'expert',
            'gpt-3.5-turbo': 'intermediate',
            'gpt-3.5': 'intermediate',
        }

        json_data = {
            'question': prompt,
            'bingResults': results,  # response.json()['rawBingResults'],
            'codeContext': codeContext,
            'options': {
                'skill': models[model],
                'date': datetime.now().strftime("%d/%m/%Y"),
                'language': language,
                'detailed': detailed,
                'creative': creative
            }
        }

        headers = {
            'authority': 'www.phind.com',
            'accept': '*/*',
            'accept-language': 'en,fr-FR;q=0.9,fr;q=0.8,es-ES;q=0.7,es;q=0.6,en-US;q=0.5,am;q=0.4,de;q=0.3',
            'content-type': 'application/json',
            'cookie': f'cf_clearance={cf_clearance}',
            'origin': 'https://www.phind.com',
            'referer': 'https://www.phind.com/search?q=hi&c=&source=searchbox&init=true',
            'sec-ch-ua': '"Chromium";v="112", "Google Chrome";v="112", "Not:A-Brand";v="99"',
            'sec-ch-ua-mobile': '?0',
            'sec-ch-ua-platform': '"macOS"',
            'sec-fetch-dest': 'empty',
            'sec-fetch-mode': 'cors',
            'sec-fetch-site': 'same-origin',
            'user-agent': user_agent
        }

        completion = ''
        response = post('https://www.phind.com/api/infer/answer', headers=headers, json=json_data, timeout=99999,
                        impersonate='chrome110')
        for line in response.text.split('\r\n\r\n'):
            completion += (line.replace('data: ', ''))

        return PhindResponse({
            'id': f'cmpl-1337-{int(time())}',
            'object': 'text_completion',
            'created': int(time()),
            'model': models[model],
            'choices': [{
                'text': completion,
                'index': 0,
                'logprobs': None,
                'finish_reason': 'stop'
            }],
            'usage': {
                'prompt_tokens': len(prompt),
                'completion_tokens': len(completion),
                'total_tokens': len(prompt) + len(completion)
            }
        })


class StreamingCompletion:
    message_queue = Queue()
    stream_completed = False

    def request(model, prompt, results, creative, detailed, codeContext, language) -> None:

        models = {
            'gpt-4': 'expert',
            'gpt-3.5-turbo': 'intermediate',
            'gpt-3.5': 'intermediate',
        }

        json_data = {
            'question': prompt,
            'bingResults': results,
            'codeContext': codeContext,
            'options': {
                'skill': models[model],
                'date': datetime.now().strftime("%d/%m/%Y"),
                'language': language,
                'detailed': detailed,
                'creative': creative
            }
        }

        headers = {
            'authority': 'www.phind.com',
            'accept': '*/*',
            'accept-language': 'en,fr-FR;q=0.9,fr;q=0.8,es-ES;q=0.7,es;q=0.6,en-US;q=0.5,am;q=0.4,de;q=0.3',
            'content-type': 'application/json',
            'cookie': f'cf_clearance={cf_clearance}',
            'origin': 'https://www.phind.com',
            'referer': 'https://www.phind.com/search?q=hi&c=&source=searchbox&init=true',
            'sec-ch-ua': '"Chromium";v="112", "Google Chrome";v="112", "Not:A-Brand";v="99"',
            'sec-ch-ua-mobile': '?0',
            'sec-ch-ua-platform': '"macOS"',
            'sec-fetch-dest': 'empty',
            'sec-fetch-mode': 'cors',
            'sec-fetch-site': 'same-origin',
            'user-agent': user_agent
        }

        response = post('https://www.phind.com/api/infer/answer',
                        headers=headers, json=json_data, timeout=99999, impersonate='chrome110',
                        content_callback=StreamingCompletion.handle_stream_response)

        StreamingCompletion.stream_completed = True

    @staticmethod
    def create(
            model: str = 'gpt-4',
            prompt: str = '',
            results: dict = None,
            creative: bool = False,
            detailed: bool = False,
            codeContext: str = '',
            language: str = 'en'):

        if user_agent == '':
            raise ValueError('user_agent must be set, refer to documentation')
        if cf_clearance == '':
            raise ValueError('cf_clearance must be set, refer to documentation')

        if results is None:
            results = Search.create(prompt, actualSearch=True)

        if len(codeContext) > 2999:
            raise ValueError('codeContext must be less than 3000 characters')

        Thread(target=StreamingCompletion.request, args=[
            model, prompt, results, creative, detailed, codeContext, language]).start()

        while StreamingCompletion.stream_completed != True or not StreamingCompletion.message_queue.empty():
            try:
                chunk = StreamingCompletion.message_queue.get(timeout=0)

                if chunk == b'data:  \r\ndata: \r\ndata: \r\n\r\n':
                    chunk = b'data:  \n\n\r\n\r\n'

                chunk = chunk.decode()

                chunk = chunk.replace('data: \r\n\r\ndata: ', 'data: \n')
                chunk = chunk.replace('\r\ndata: \r\ndata: \r\n\r\n', '\n\n\r\n\r\n')
                chunk = chunk.replace('data: ', '').replace('\r\n\r\n', '')

                yield PhindResponse({
                    'id': f'cmpl-1337-{int(time())}',
                    'object': 'text_completion',
                    'created': int(time()),
                    'model': model,
                    'choices': [{
                        'text': chunk,
                        'index': 0,
                        'logprobs': None,
                        'finish_reason': 'stop'
                    }],
                    'usage': {
                        'prompt_tokens': len(prompt),
                        'completion_tokens': len(chunk),
                        'total_tokens': len(prompt) + len(chunk)
                    }
                })

            except Empty:
                pass

    @staticmethod
    def handle_stream_response(response):
        StreamingCompletion.message_queue.put(response)