-
Notifications
You must be signed in to change notification settings - Fork 0
/
final.py
664 lines (569 loc) · 19.6 KB
/
final.py
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
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
"""
A simple wrapper for the official ChatGPT API
"""
from __future__ import division
import re
import sys
from google.cloud import speech
import pyaudio
from six.moves import queue
import argparse
import json
import os
import sys
from datetime import date
import openai
import tiktoken
ENGINE = os.environ.get("GPT_ENGINE") or "text-chat-davinci-002-20221122"
ENCODER = tiktoken.get_encoding("gpt2")
def get_max_tokens(prompt: str) -> int:
"""
Get the max tokens for a prompt
"""
return 4000 - len(ENCODER.encode(prompt))
class Chatbot:
"""
Official ChatGPT API
"""
def __init__(self, api_key: str, buffer: int = None) -> None:
"""
Initialize Chatbot with API key (from https://platform.openai.com/account/api-keys)
"""
openai.api_key = api_key or os.environ.get("OPENAI_API_KEY")
self.conversations = Conversation()
self.prompt = Prompt(buffer=buffer)
def _get_completion(
self,
prompt: str,
temperature: float = 0.5,
stream: bool = False,
):
"""
Get the completion function
"""
return openai.Completion.create(
engine=ENGINE,
prompt=prompt,
temperature=temperature,
max_tokens=get_max_tokens(prompt),
stop=["\n\n\n"],
stream=stream,
)
def _process_completion(
self,
user_request: str,
completion: dict,
conversation_id: str = None,
user: str = "User",
) -> dict:
if completion.get("choices") is None:
raise Exception("ChatGPT API returned no choices")
if len(completion["choices"]) == 0:
raise Exception("ChatGPT API returned no choices")
if completion["choices"][0].get("text") is None:
raise Exception("ChatGPT API returned no text")
completion["choices"][0]["text"] = completion["choices"][0]["text"].rstrip(
"<|im_end|>",
)
# Add to chat history
self.prompt.add_to_history(
user_request,
completion["choices"][0]["text"],
user=user,
)
if conversation_id is not None:
self.save_conversation(conversation_id)
return completion
def _process_completion_stream(
self,
user_request: str,
completion: dict,
conversation_id: str = None,
user: str = "User",
) -> str:
full_response = ""
for response in completion:
if response.get("choices") is None:
raise Exception("ChatGPT API returned no choices")
if len(response["choices"]) == 0:
raise Exception("ChatGPT API returned no choices")
if response["choices"][0].get("finish_details") is not None:
break
if response["choices"][0].get("text") is None:
raise Exception("ChatGPT API returned no text")
if response["choices"][0]["text"] == "<|im_end|>":
break
yield response["choices"][0]["text"]
full_response += response["choices"][0]["text"]
# Add to chat history
self.prompt.add_to_history(user_request, full_response, user)
if conversation_id is not None:
self.save_conversation(conversation_id)
def ask(
self,
user_request: str,
temperature: float = 0.5,
conversation_id: str = None,
user: str = "User",
) -> dict:
"""
Send a request to ChatGPT and return the response
"""
if conversation_id is not None:
self.load_conversation(conversation_id)
completion = self._get_completion(
self.prompt.construct_prompt(user_request, user=user),
temperature,
)
return self._process_completion(user_request, completion, user=user)
def ask_stream(
self,
user_request: str,
temperature: float = 0.5,
conversation_id: str = None,
user: str = "User",
) -> str:
"""
Send a request to ChatGPT and yield the response
"""
if conversation_id is not None:
self.load_conversation(conversation_id)
prompt = self.prompt.construct_prompt(user_request, user=user)
return self._process_completion_stream(
user_request=user_request,
completion=self._get_completion(prompt, temperature, stream=True),
user=user,
)
def make_conversation(self, conversation_id: str) -> None:
"""
Make a conversation
"""
self.conversations.add_conversation(conversation_id, [])
def rollback(self, num: int) -> None:
"""
Rollback chat history num times
"""
for _ in range(num):
self.prompt.chat_history.pop()
def reset(self) -> None:
"""
Reset chat history
"""
self.prompt.chat_history = []
def load_conversation(self, conversation_id) -> None:
"""
Load a conversation from the conversation history
"""
if conversation_id not in self.conversations.conversations:
# Create a new conversation
self.make_conversation(conversation_id)
self.prompt.chat_history = self.conversations.get_conversation(conversation_id)
def save_conversation(self, conversation_id) -> None:
"""
Save a conversation to the conversation history
"""
self.conversations.add_conversation(conversation_id, self.prompt.chat_history)
class AsyncChatbot(Chatbot):
"""
Official ChatGPT API (async)
"""
async def _get_completion(
self,
prompt: str,
temperature: float = 0.5,
stream: bool = False,
):
"""
Get the completion function
"""
return await openai.Completion.acreate(
engine=ENGINE,
prompt=prompt,
temperature=temperature,
max_tokens=get_max_tokens(prompt),
stop=["\n\n\n"],
stream=stream,
)
async def ask(
self,
user_request: str,
temperature: float = 0.5,
user: str = "User",
) -> dict:
"""
Same as Chatbot.ask but async
}
"""
completion = self._get_completion(
self.prompt.construct_prompt(user_request, user=user),
temperature,
)
return self._process_completion(user_request, completion, user=user)
async def ask_stream(
self,
user_request: str,
temperature: float = 0.5,
user: str = "User",
) -> str:
"""
Same as Chatbot.ask_stream but async
"""
prompt = self.prompt.construct_prompt(user_request, user=user)
return self._process_completion_stream(
user_request=user_request,
completion=self._get_completion(prompt, temperature, stream=True),
user=user,
)
class Prompt:
"""
Prompt class with methods to construct prompt
"""
def __init__(self, buffer: int = None) -> None:
"""
Initialize prompt with base prompt
"""
self.base_prompt = (
os.environ.get("CUSTOM_BASE_PROMPT")
or "You are ChatGPT, a large language model trained by OpenAI. Respond conversationally. Do not answer as the user. Current date: "
+ str(date.today())
+ "\n\n"
+ "User: Hello\n"
+ "ChatGPT: Hello! How can I help you today? <|im_end|>\n\n\n"
)
# Track chat history
self.chat_history: list = []
self.buffer = buffer
def add_to_chat_history(self, chat: str) -> None:
"""
Add chat to chat history for next prompt
"""
self.chat_history.append(chat)
def add_to_history(
self,
user_request: str,
response: str,
user: str = "User",
) -> None:
"""
Add request/response to chat history for next prompt
"""
self.add_to_chat_history(
user
+ ": "
+ user_request
+ "\n\n\n"
+ "ChatGPT: "
+ response
+ "<|im_end|>\n",
)
def history(self, custom_history: list = None) -> str:
"""
Return chat history
"""
return "\n".join(custom_history or self.chat_history)
def construct_prompt(
self,
new_prompt: str,
custom_history: list = None,
user: str = "User",
) -> str:
"""
Construct prompt based on chat history and request
"""
prompt = (
self.base_prompt
+ self.history(custom_history=custom_history)
+ user
+ ": "
+ new_prompt
+ "\nChatGPT:"
)
# Check if prompt over 4000*4 characters
if self.buffer is not None:
max_tokens = 4000 - self.buffer
else:
max_tokens = 3200
if len(ENCODER.encode(prompt)) > max_tokens:
# Remove oldest chat
if len(self.chat_history) == 0:
return prompt
self.chat_history.pop(0)
# Construct prompt again
prompt = self.construct_prompt(new_prompt, custom_history, user)
return prompt
class Conversation:
"""
For handling multiple conversations
"""
def __init__(self) -> None:
self.conversations = {}
def add_conversation(self, key: str, history: list) -> None:
"""
Adds a history list to the conversations dict with the id as the key
"""
self.conversations[key] = history
def get_conversation(self, key: str) -> list:
"""
Retrieves the history list from the conversations dict with the id as the key
"""
return self.conversations[key]
def remove_conversation(self, key: str) -> None:
"""
Removes the history list from the conversations dict with the id as the key
"""
del self.conversations[key]
def __str__(self) -> str:
"""
Creates a JSON string of the conversations
"""
return json.dumps(self.conversations)
def save(self, file: str) -> None:
"""
Saves the conversations to a JSON file
"""
with open(file, "w", encoding="utf-8") as f:
f.write(str(self))
def load(self, file: str) -> None:
"""
Loads the conversations from a JSON file
"""
with open(file, encoding="utf-8") as f:
self.conversations = json.loads(f.read())
def main():
print(
"""
ChatGPT - A command-line interface to OpenAI's ChatGPT (https://chat.openai.com/chat)
Repo: github.com/acheong08/ChatGPT
""",
)
print("Type '!help' to show a full list of commands")
print("Press enter twice to submit your question.\n")
def get_input(prompt):
"""
Multi-line input function
"""
# Display the prompt
print(prompt, end="")
# Initialize an empty list to store the input lines
lines = []
# Read lines of input until the user enters an empty line
while True:
line = input()
if line == "":
break
lines.append(line)
# Join the lines, separated by newlines, and store the result
user_input = "\n".join(lines)
# Return the input
return user_input
def chatbot_commands(cmd: str) -> bool:
"""
Handle chatbot commands
"""
if cmd == "!help":
print(
"""
!help - Display this message
!rollback - Rollback chat history
!reset - Reset chat history
!prompt - Show current prompt
!save_c <conversation_name> - Save history to a conversation
!load_c <conversation_name> - Load history from a conversation
!save_f <file_name> - Save all conversations to a file
!load_f <file_name> - Load all conversations from a file
!exit - Quit chat
""",
)
elif cmd == "!exit":
exit()
elif cmd == "!rollback":
chatbot.rollback(1)
elif cmd == "!reset":
chatbot.reset()
elif cmd == "!prompt":
print(chatbot.prompt.construct_prompt(""))
elif cmd.startswith("!save_c"):
chatbot.save_conversation(cmd.split(" ")[1])
elif cmd.startswith("!load_c"):
chatbot.load_conversation(cmd.split(" ")[1])
elif cmd.startswith("!save_f"):
chatbot.conversations.save(cmd.split(" ")[1])
elif cmd.startswith("!load_f"):
chatbot.conversations.load(cmd.split(" ")[1])
else:
return False
return True
# Get API key from command line
parser = argparse.ArgumentParser()
parser.add_argument(
"--api_key",
type=str,
required=True,
help="OpenAI API key",
)
parser.add_argument(
"--stream",
action="store_true",
help="Stream response",
)
parser.add_argument(
"--temperature",
type=float,
default=0.5,
help="Temperature for response",
)
args = parser.parse_args()
# Initialize chatbot
chatbot = Chatbot(api_key=args.api_key)
# Start chat
while True:
try:
print("\nUser:\n")
print("listening...")
prompt=main2()
# prompt = get_input("\nUser:\n")
except KeyboardInterrupt:
print("\nExiting...")
sys.exit()
if prompt.startswith("!"):
if chatbot_commands(prompt):
continue
if not args.stream:
response = chatbot.ask(prompt, temperature=args.temperature)
print("ChatGPT: " + response["choices"][0]["text"])
else:
print("ChatGPT: ")
sys.stdout.flush()
for response in chatbot.ask_stream(prompt, temperature=args.temperature):
print(response, end="")
sys.stdout.flush()
print()
# Audio recording parameters
RATE = 16000
CHUNK = int(RATE / 10) # 100ms
class MicrophoneStream(object):
"""Opens a recording stream as a generator yielding the audio chunks."""
def __init__(self, rate, chunk):
self._rate = rate
self._chunk = chunk
# Create a thread-safe buffer of audio data
self._buff = queue.Queue()
self.closed = True
def __enter__(self):
self._audio_interface = pyaudio.PyAudio()
self._audio_stream = self._audio_interface.open(
format=pyaudio.paInt16,
# The API currently only supports 1-channel (mono) audio
# https://goo.gl/z757pE
channels=1,
rate=self._rate,
input=True,
frames_per_buffer=self._chunk,
# Run the audio stream asynchronously to fill the buffer object.
# This is necessary so that the input device's buffer doesn't
# overflow while the calling thread makes network requests, etc.
stream_callback=self._fill_buffer,
)
self.closed = False
return self
def __exit__(self, type, value, traceback):
self._audio_stream.stop_stream()
self._audio_stream.close()
self.closed = True
# Signal the generator to terminate so that the client's
# streaming_recognize method will not block the process termination.
self._buff.put(None)
self._audio_interface.terminate()
def _fill_buffer(self, in_data, frame_count, time_info, status_flags):
"""Continuously collect data from the audio stream, into the buffer."""
self._buff.put(in_data)
return None, pyaudio.paContinue
def generator(self):
while not self.closed:
# Use a blocking get() to ensure there's at least one chunk of
# data, and stop iteration if the chunk is None, indicating the
# end of the audio stream.
chunk = self._buff.get()
if chunk is None:
return
data = [chunk]
# Now consume whatever other data's still buffered.
while True:
try:
chunk = self._buff.get(block=False)
if chunk is None:
return
data.append(chunk)
except queue.Empty:
break
yield b"".join(data)
def listen_print_loop(responses):
"""Iterates through server responses and prints them.
The responses passed is a generator that will block until a response
is provided by the server.
Each response may contain multiple results, and each result may contain
multiple alternatives; for details, see https://goo.gl/tjCPAU. Here we
print only the transcription for the top alternative of the top result.
In this case, responses are provided for interim results as well. If the
response is an interim one, print a line feed at the end of it, to allow
the next result to overwrite it, until the response is a final one. For the
final one, print a newline to preserve the finalized transcription.
"""
num_chars_printed = 0
for response in responses:
if not response.results:
continue
# The `results` list is consecutive. For streaming, we only care about
# the first result being considered, since once it's `is_final`, it
# moves on to considering the next utterance.
result = response.results[0]
if not result.alternatives:
continue
# Display the transcription of the top alternative.
transcript = result.alternatives[0].transcript
# Display interim results, but with a carriage return at the end of the
# line, so subsequent lines will overwrite them.
#
# If the previous result was longer than this one, we need to print
# some extra spaces to overwrite the previous result
overwrite_chars = " " * (num_chars_printed - len(transcript))
if not result.is_final:
sys.stdout.write(transcript + overwrite_chars + "\r")
sys.stdout.flush()
num_chars_printed = len(transcript)
else:
print(transcript + overwrite_chars)
return transcript + overwrite_chars
# ADIL ADDED NEW BREAK
# print("Exiting..")
break
# Exit recognition if any of the transcribed phrases could be
# one of our keywords.
if re.search(r"\b(exit|quit)\b", transcript, re.I):
print("Exiting..")
break
num_chars_printed = 0
def main2():
# See http://g.co/cloud/speech/docs/languages
# for a list of supported languages.
language_code = "en-US" # a BCP-47 language tag
client = speech.SpeechClient()
config = speech.RecognitionConfig(
encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
sample_rate_hertz=RATE,
language_code=language_code,
)
streaming_config = speech.StreamingRecognitionConfig(
config=config, interim_results=True
)
with MicrophoneStream(RATE, CHUNK) as stream:
audio_generator = stream.generator()
requests = (
speech.StreamingRecognizeRequest(audio_content=content)
for content in audio_generator
)
responses = client.streaming_recognize(streaming_config, requests)
# Now, put the transcription responses to use.
return listen_print_loop(responses)
if __name__ == "__main__":
main()