forked from KoboldAI/KoboldAI-Client
-
Notifications
You must be signed in to change notification settings - Fork 0
/
aiserver.py
1817 lines (1608 loc) · 69.3 KB
/
aiserver.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
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
#==================================================================#
# KoboldAI Client
# Version: 1.15.0
# By: KoboldAIDev
#==================================================================#
# External packages
from os import path, getcwd
import tkinter as tk
from tkinter import messagebox
import json
import requests
import html
# KoboldAI
import fileops
import gensettings
from utils import debounce
import utils
#==================================================================#
# Variables & Storage
#==================================================================#
# Terminal tags for colored text
class colors:
PURPLE = '\033[95m'
BLUE = '\033[94m'
CYAN = '\033[96m'
GREEN = '\033[92m'
YELLOW = '\033[93m'
RED = '\033[91m'
END = '\033[0m'
UNDERLINE = '\033[4m'
# AI models
modellist = [
["GPT Neo 1.3B", "EleutherAI/gpt-neo-1.3B", "8GB"],
["GPT Neo 2.7B", "EleutherAI/gpt-neo-2.7B", "16GB"],
["GPT-2", "gpt2", "1.2GB"],
["GPT-2 Med", "gpt2-medium", "2GB"],
["GPT-2 Large", "gpt2-large", "16GB"],
["GPT-2 XL", "gpt2-xl", "16GB"],
["InferKit API (requires API key)", "InferKit", ""],
["Custom Neo (eg Neo-horni)", "NeoCustom", ""],
["Custom GPT-2 (eg CloverEdition)", "GPT2Custom", ""],
["Google Colab", "Colab", ""],
["OpenAI API (requires API key)", "OAI", ""],
["Read Only (No AI)", "ReadOnly", ""]
]
# Variables
class vars:
lastact = "" # The last action received from the user
lastctx = "" # The last context submitted to the generator
model = "" # Model ID string chosen at startup
noai = False # Runs the script without starting up the transformers pipeline
aibusy = False # Stops submissions while the AI is working
max_length = 512 # Maximum number of tokens to submit per action
ikmax = 3000 # Maximum number of characters to submit to InferKit
genamt = 60 # Amount of text for each action to generate
ikgen = 200 # Number of characters for InferKit to generate
rep_pen = 1.0 # Default generator repetition_penalty
temp = 1.0 # Default generator temperature
top_p = 1.0 # Default generator top_p
numseqs = 1 # Number of sequences to ask the generator to create
gamestarted = False # Whether the game has started (disables UI elements)
prompt = "" # Prompt
memory = "" # Text submitted to memory field
authornote = "" # Text submitted to Author's Note field
andepth = 3 # How far back in history to append author's note
actions = [] # Array of actions submitted by user and AI
worldinfo = [] # Array of World Info key/value objects
badwords = [] # Array of str/chr values that should be removed from output
badwordsids = [] # Tokenized array of badwords
deletewi = -1 # Temporary storage for index to delete
wirmvwhtsp = False # Whether to remove leading whitespace from WI entries
widepth = 1 # How many historical actions to scan for WI hits
mode = "play" # Whether the interface is in play, memory, or edit mode
editln = 0 # Which line was last selected in Edit Mode
url = "https://api.inferkit.com/v1/models/standard/generate" # InferKit API URL
oaiurl = "" # OpenAI API URL
oaiengines = "https://api.openai.com/v1/engines"
colaburl = "" # Ngrok url for Google Colab mode
apikey = "" # API key to use for InferKit API calls
oaiapikey = "" # API key to use for OpenAI API calls
savedir = getcwd()+"\stories"
hascuda = False # Whether torch has detected CUDA on the system
usegpu = False # Whether to launch pipeline with GPU support
custmodpth = "" # Filesystem location of custom model to run
formatoptns = {} # Container for state of formatting options
importnum = -1 # Selection on import popup list
importjs = {} # Temporary storage for import data
loadselect = "" # Temporary storage for filename to load
svowname = "" # Filename that was flagged for overwrite confirm
saveow = False # Whether or not overwrite confirm has been displayed
genseqs = [] # Temporary storage for generated sequences
useprompt = True # Whether to send the full prompt with every submit action
#==================================================================#
# Function to get model selection at startup
#==================================================================#
def getModelSelection():
print(" # Model V/RAM\n =========================================")
i = 1
for m in modellist:
print(" {0} - {1}\t\t{2}".format("{:<2}".format(i), m[0].ljust(15), m[2]))
i += 1
print(" ");
modelsel = 0
vars.model = ''
while(vars.model == ''):
modelsel = input("Model #> ")
if(modelsel.isnumeric() and int(modelsel) > 0 and int(modelsel) <= len(modellist)):
vars.model = modellist[int(modelsel)-1][1]
else:
print("{0}Please enter a valid selection.{1}".format(colors.RED, colors.END))
# If custom model was selected, get the filesystem location and store it
if(vars.model == "NeoCustom" or vars.model == "GPT2Custom"):
print("{0}Please choose the folder where pytorch_model.bin is located:{1}\n".format(colors.CYAN, colors.END))
modpath = fileops.getdirpath(getcwd(), "Select Model Folder")
if(modpath):
# Save directory to vars
vars.custmodpth = modpath
else:
# Print error and retry model selection
print("{0}Model select cancelled!{1}".format(colors.RED, colors.END))
print("{0}Select an AI model to continue:{1}\n".format(colors.CYAN, colors.END))
getModelSelection()
#==================================================================#
# Return all keys in tokenizer dictionary containing char
#==================================================================#
def gettokenids(char):
keys = []
for key in vocab_keys:
if(key.find(char) != -1):
keys.append(key)
return keys
#==================================================================#
# Startup
#==================================================================#
# Select a model to run
print("{0}Welcome to the KoboldAI Client!\nSelect an AI model to continue:{1}\n".format(colors.CYAN, colors.END))
getModelSelection()
# If transformers model was selected & GPU available, ask to use CPU or GPU
if(not vars.model in ["InferKit", "Colab", "OAI", "ReadOnly"]):
# Test for GPU support
import torch
print("{0}Looking for GPU support...{1}".format(colors.PURPLE, colors.END), end="")
vars.hascuda = torch.cuda.is_available()
if(vars.hascuda):
print("{0}FOUND!{1}".format(colors.GREEN, colors.END))
else:
print("{0}NOT FOUND!{1}".format(colors.YELLOW, colors.END))
if(vars.hascuda):
print("{0}Use GPU or CPU for generation?: (Default GPU){1}\n".format(colors.CYAN, colors.END))
print(" 1 - GPU\n 2 - CPU\n")
genselected = False
while(genselected == False):
genselect = input("Mode> ")
if(genselect == ""):
vars.usegpu = True
genselected = True
elif(genselect.isnumeric() and int(genselect) == 1):
vars.usegpu = True
genselected = True
elif(genselect.isnumeric() and int(genselect) == 2):
vars.usegpu = False
genselected = True
else:
print("{0}Please enter a valid selection.{1}".format(colors.RED, colors.END))
# Ask for API key if InferKit was selected
if(vars.model == "InferKit"):
if(not path.exists("client.settings")):
# If the client settings file doesn't exist, create it
print("{0}Please enter your InferKit API key:{1}\n".format(colors.CYAN, colors.END))
vars.apikey = input("Key> ")
# Write API key to file
file = open("client.settings", "w")
try:
js = {"apikey": vars.apikey}
file.write(json.dumps(js, indent=3))
finally:
file.close()
else:
# Otherwise open it up
file = open("client.settings", "r")
# Check if API key exists
js = json.load(file)
if("apikey" in js and js["apikey"] != ""):
# API key exists, grab it and close the file
vars.apikey = js["apikey"]
file.close()
else:
# Get API key, add it to settings object, and write it to disk
print("{0}Please enter your InferKit API key:{1}\n".format(colors.CYAN, colors.END))
vars.apikey = input("Key> ")
js["apikey"] = vars.apikey
# Write API key to file
file = open("client.settings", "w")
try:
file.write(json.dumps(js, indent=3))
finally:
file.close()
# Ask for API key if OpenAI was selected
if(vars.model == "OAI"):
if(not path.exists("client.settings")):
# If the client settings file doesn't exist, create it
print("{0}Please enter your OpenAI API key:{1}\n".format(colors.CYAN, colors.END))
vars.oaiapikey = input("Key> ")
# Write API key to file
file = open("client.settings", "w")
try:
js = {"oaiapikey": vars.oaiapikey}
file.write(json.dumps(js, indent=3))
finally:
file.close()
else:
# Otherwise open it up
file = open("client.settings", "r")
# Check if API key exists
js = json.load(file)
if("oaiapikey" in js and js["oaiapikey"] != ""):
# API key exists, grab it and close the file
vars.oaiapikey = js["oaiapikey"]
file.close()
else:
# Get API key, add it to settings object, and write it to disk
print("{0}Please enter your OpenAI API key:{1}\n".format(colors.CYAN, colors.END))
vars.oaiapikey = input("Key> ")
js["oaiapikey"] = vars.oaiapikey
# Write API key to file
file = open("client.settings", "w")
try:
file.write(json.dumps(js, indent=3))
finally:
file.close()
# Get list of models from OAI
print("{0}Retrieving engine list...{1}".format(colors.PURPLE, colors.END), end="")
req = requests.get(
vars.oaiengines,
headers = {
'Authorization': 'Bearer '+vars.oaiapikey
}
)
if(req.status_code == 200):
print("{0}OK!{1}".format(colors.GREEN, colors.END))
print("{0}Please select an engine to use:{1}\n".format(colors.CYAN, colors.END))
engines = req.json()["data"]
# Print list of engines
i = 0
for en in engines:
print(" {0} - {1} ({2})".format(i, en["id"], "\033[92mready\033[0m" if en["ready"] == True else "\033[91mnot ready\033[0m"))
i += 1
# Get engine to use
print("")
engselected = False
while(engselected == False):
engine = input("Engine #> ")
if(engine.isnumeric() and int(engine) < len(engines)):
vars.oaiurl = "https://api.openai.com/v1/engines/{0}/completions".format(engines[int(engine)]["id"])
engselected = True
else:
print("{0}Please enter a valid selection.{1}".format(colors.RED, colors.END))
else:
# Something went wrong, print the message and quit since we can't initialize an engine
print("{0}ERROR!{1}".format(colors.RED, colors.END))
print(req.json())
quit()
# Ask for ngrok url if Google Colab was selected
if(vars.model == "Colab"):
print("{0}Please enter the ngrok.io or trycloudflare.com URL displayed in Google Colab:{1}\n".format(colors.CYAN, colors.END))
vars.colaburl = input("URL> ") + "/request"
if(vars.model == "ReadOnly"):
vars.noai = True
# Set logging level to reduce chatter from Flask
import logging
log = logging.getLogger('werkzeug')
log.setLevel(logging.ERROR)
# Start flask & SocketIO
print("{0}Initializing Flask... {1}".format(colors.PURPLE, colors.END), end="")
from flask import Flask, render_template
from flask_socketio import SocketIO, emit
app = Flask(__name__)
app.config['SECRET KEY'] = 'secret!'
socketio = SocketIO(app)
print("{0}OK!{1}".format(colors.GREEN, colors.END))
# Start transformers and create pipeline
if(not vars.model in ["InferKit", "Colab", "OAI", "ReadOnly"]):
if(not vars.noai):
print("{0}Initializing transformers, please wait...{1}".format(colors.PURPLE, colors.END))
from transformers import pipeline, GPT2Tokenizer, GPT2LMHeadModel, GPTNeoForCausalLM
# If custom GPT Neo model was chosen
if(vars.model == "NeoCustom"):
model = GPTNeoForCausalLM.from_pretrained(vars.custmodpth)
tokenizer = GPT2Tokenizer.from_pretrained(vars.custmodpth)
# Is CUDA available? If so, use GPU, otherwise fall back to CPU
if(vars.hascuda and vars.usegpu):
generator = pipeline('text-generation', model=model, tokenizer=tokenizer, device=0)
else:
generator = pipeline('text-generation', model=model, tokenizer=tokenizer)
# If custom GPT2 model was chosen
elif(vars.model == "GPT2Custom"):
model = GPT2LMHeadModel.from_pretrained(vars.custmodpth)
tokenizer = GPT2Tokenizer.from_pretrained(vars.custmodpth)
# Is CUDA available? If so, use GPU, otherwise fall back to CPU
if(vars.hascuda and vars.usegpu):
generator = pipeline('text-generation', model=model, tokenizer=tokenizer, device=0)
else:
generator = pipeline('text-generation', model=model, tokenizer=tokenizer)
# If base HuggingFace model was chosen
else:
# Is CUDA available? If so, use GPU, otherwise fall back to CPU
tokenizer = GPT2Tokenizer.from_pretrained(vars.model)
if(vars.hascuda and vars.usegpu):
generator = pipeline('text-generation', model=vars.model, device=0)
else:
generator = pipeline('text-generation', model=vars.model)
# Suppress Author's Note by flagging square brackets
vocab = tokenizer.get_vocab()
vocab_keys = vocab.keys()
vars.badwords = gettokenids("[")
for key in vars.badwords:
vars.badwordsids.append([vocab[key]])
print("{0}OK! {1} pipeline created!{2}".format(colors.GREEN, vars.model, colors.END))
else:
# If we're running Colab or OAI, we still need a tokenizer.
if(vars.model == "Colab"):
from transformers import GPT2Tokenizer
tokenizer = GPT2Tokenizer.from_pretrained("EleutherAI/gpt-neo-2.7B")
elif(vars.model == "OAI"):
from transformers import GPT2Tokenizer
tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
# Set up Flask routes
@app.route('/')
@app.route('/index')
def index():
return render_template('index.html')
#============================ METHODS =============================#
#==================================================================#
# Event triggered when browser SocketIO is loaded and connects to server
#==================================================================#
@socketio.on('connect')
def do_connect():
print("{0}Client connected!{1}".format(colors.GREEN, colors.END))
emit('from_server', {'cmd': 'connected'})
if(not vars.gamestarted):
setStartState()
sendsettings()
refresh_settings()
sendwi()
vars.mode = "play"
else:
# Game in session, send current game data and ready state to browser
refresh_story()
sendsettings()
refresh_settings()
sendwi()
if(vars.mode == "play"):
if(not vars.aibusy):
emit('from_server', {'cmd': 'setgamestate', 'data': 'ready'})
else:
emit('from_server', {'cmd': 'setgamestate', 'data': 'wait'})
elif(vars.mode == "edit"):
emit('from_server', {'cmd': 'editmode', 'data': 'true'})
elif(vars.mode == "memory"):
emit('from_server', {'cmd': 'memmode', 'data': 'true'})
elif(vars.mode == "wi"):
emit('from_server', {'cmd': 'wimode', 'data': 'true'})
#==================================================================#
# Event triggered when browser SocketIO sends data to the server
#==================================================================#
@socketio.on('message')
def get_message(msg):
print("{0}Data recieved:{1}{2}".format(colors.GREEN, msg, colors.END))
# Submit action
if(msg['cmd'] == 'submit'):
if(vars.mode == "play"):
actionsubmit(msg['data'])
elif(vars.mode == "edit"):
editsubmit(msg['data'])
elif(vars.mode == "memory"):
memsubmit(msg['data'])
# Retry Action
elif(msg['cmd'] == 'retry'):
actionretry(msg['data'])
# Back/Undo Action
elif(msg['cmd'] == 'back'):
actionback()
# EditMode Action
elif(msg['cmd'] == 'edit'):
if(vars.mode == "play"):
vars.mode = "edit"
emit('from_server', {'cmd': 'editmode', 'data': 'true'})
elif(vars.mode == "edit"):
vars.mode = "play"
emit('from_server', {'cmd': 'editmode', 'data': 'false'})
# EditLine Action
elif(msg['cmd'] == 'editline'):
editrequest(int(msg['data']))
# DeleteLine Action
elif(msg['cmd'] == 'delete'):
deleterequest()
elif(msg['cmd'] == 'memory'):
togglememorymode()
elif(msg['cmd'] == 'savetofile'):
savetofile()
elif(msg['cmd'] == 'loadfromfile'):
loadfromfile()
elif(msg['cmd'] == 'import'):
importRequest()
elif(msg['cmd'] == 'newgame'):
newGameRequest()
elif(msg['cmd'] == 'settemp'):
vars.temp = float(msg['data'])
emit('from_server', {'cmd': 'setlabeltemp', 'data': msg['data']})
settingschanged()
elif(msg['cmd'] == 'settopp'):
vars.top_p = float(msg['data'])
emit('from_server', {'cmd': 'setlabeltopp', 'data': msg['data']})
settingschanged()
elif(msg['cmd'] == 'setreppen'):
vars.rep_pen = float(msg['data'])
emit('from_server', {'cmd': 'setlabelreppen', 'data': msg['data']})
settingschanged()
elif(msg['cmd'] == 'setoutput'):
vars.genamt = int(msg['data'])
emit('from_server', {'cmd': 'setlabeloutput', 'data': msg['data']})
settingschanged()
elif(msg['cmd'] == 'settknmax'):
vars.max_length = int(msg['data'])
emit('from_server', {'cmd': 'setlabeltknmax', 'data': msg['data']})
settingschanged()
elif(msg['cmd'] == 'setikgen'):
vars.ikgen = int(msg['data'])
emit('from_server', {'cmd': 'setlabelikgen', 'data': msg['data']})
settingschanged()
# Author's Note field update
elif(msg['cmd'] == 'anote'):
anotesubmit(msg['data'])
# Author's Note depth update
elif(msg['cmd'] == 'anotedepth'):
vars.andepth = int(msg['data'])
emit('from_server', {'cmd': 'setlabelanotedepth', 'data': msg['data']})
settingschanged()
# Format - Trim incomplete sentences
elif(msg['cmd'] == 'frmttriminc'):
if('frmttriminc' in vars.formatoptns):
vars.formatoptns["frmttriminc"] = msg['data']
settingschanged()
elif(msg['cmd'] == 'frmtrmblln'):
if('frmtrmblln' in vars.formatoptns):
vars.formatoptns["frmtrmblln"] = msg['data']
settingschanged()
elif(msg['cmd'] == 'frmtrmspch'):
if('frmtrmspch' in vars.formatoptns):
vars.formatoptns["frmtrmspch"] = msg['data']
settingschanged()
elif(msg['cmd'] == 'frmtadsnsp'):
if('frmtadsnsp' in vars.formatoptns):
vars.formatoptns["frmtadsnsp"] = msg['data']
settingschanged()
elif(msg['cmd'] == 'importselect'):
vars.importnum = int(msg["data"].replace("import", ""))
elif(msg['cmd'] == 'importcancel'):
emit('from_server', {'cmd': 'popupshow', 'data': False})
vars.importjs = {}
elif(msg['cmd'] == 'importaccept'):
emit('from_server', {'cmd': 'popupshow', 'data': False})
importgame()
elif(msg['cmd'] == 'wi'):
togglewimode()
elif(msg['cmd'] == 'wiinit'):
if(int(msg['data']) < len(vars.worldinfo)):
vars.worldinfo[msg['data']]["init"] = True
addwiitem()
elif(msg['cmd'] == 'widelete'):
deletewi(msg['data'])
elif(msg['cmd'] == 'sendwilist'):
commitwi(msg['data'])
elif(msg['cmd'] == 'aidgimport'):
importAidgRequest(msg['data'])
elif(msg['cmd'] == 'saveasrequest'):
saveas(msg['data'])
elif(msg['cmd'] == 'saverequest'):
save()
elif(msg['cmd'] == 'loadlistrequest'):
getloadlist()
elif(msg['cmd'] == 'loadselect'):
vars.loadselect = msg["data"]
elif(msg['cmd'] == 'loadrequest'):
loadRequest(getcwd()+"/stories/"+vars.loadselect+".json")
elif(msg['cmd'] == 'clearoverwrite'):
vars.svowname = ""
vars.saveow = False
elif(msg['cmd'] == 'seqsel'):
selectsequence(msg['data'])
elif(msg['cmd'] == 'setnumseq'):
vars.numseqs = int(msg['data'])
emit('from_server', {'cmd': 'setlabelnumseq', 'data': msg['data']})
settingschanged()
elif(msg['cmd'] == 'setwidepth'):
vars.widepth = int(msg['data'])
emit('from_server', {'cmd': 'setlabelwidepth', 'data': msg['data']})
settingschanged()
elif(msg['cmd'] == 'setuseprompt'):
vars.useprompt = msg['data']
settingschanged()
elif(msg['cmd'] == 'importwi'):
wiimportrequest()
#==================================================================#
# Send start message and tell Javascript to set UI state
#==================================================================#
def setStartState():
txt = "<span>Welcome to <span class=\"color_cyan\">KoboldAI Client</span>! You are running <span class=\"color_green\">"+vars.model+"</span>.<br/>"
if(not vars.noai):
txt = txt + "Please load a game or enter a prompt below to begin!</span>"
else:
txt = txt + "Please load or import a story to read. There is no AI in this mode."
emit('from_server', {'cmd': 'updatescreen', 'data': txt})
emit('from_server', {'cmd': 'setgamestate', 'data': 'start'})
#==================================================================#
# Transmit applicable settings to SocketIO to build UI sliders/toggles
#==================================================================#
def sendsettings():
# Send settings for selected AI type
if(vars.model != "InferKit"):
for set in gensettings.gensettingstf:
emit('from_server', {'cmd': 'addsetting', 'data': set})
else:
for set in gensettings.gensettingsik:
emit('from_server', {'cmd': 'addsetting', 'data': set})
# Send formatting options
for frm in gensettings.formatcontrols:
emit('from_server', {'cmd': 'addformat', 'data': frm})
# Add format key to vars if it wasn't loaded with client.settings
if(not frm["id"] in vars.formatoptns):
vars.formatoptns[frm["id"]] = False;
#==================================================================#
# Take settings from vars and write them to client settings file
#==================================================================#
def savesettings():
# Build json to write
js = {}
js["apikey"] = vars.apikey
js["andepth"] = vars.andepth
js["temp"] = vars.temp
js["top_p"] = vars.top_p
js["rep_pen"] = vars.rep_pen
js["genamt"] = vars.genamt
js["max_length"] = vars.max_length
js["ikgen"] = vars.ikgen
js["formatoptns"] = vars.formatoptns
js["numseqs"] = vars.numseqs
js["widepth"] = vars.widepth
js["useprompt"] = vars.useprompt
# Write it
file = open("client.settings", "w")
try:
file.write(json.dumps(js, indent=3))
finally:
file.close()
#==================================================================#
# Read settings from client file JSON and send to vars
#==================================================================#
def loadsettings():
if(path.exists("client.settings")):
# Read file contents into JSON object
file = open("client.settings", "r")
js = json.load(file)
# Copy file contents to vars
if("apikey" in js):
vars.apikey = js["apikey"]
if("andepth" in js):
vars.andepth = js["andepth"]
if("temp" in js):
vars.temp = js["temp"]
if("top_p" in js):
vars.top_p = js["top_p"]
if("rep_pen" in js):
vars.rep_pen = js["rep_pen"]
if("genamt" in js):
vars.genamt = js["genamt"]
if("max_length" in js):
vars.max_length = js["max_length"]
if("ikgen" in js):
vars.ikgen = js["ikgen"]
if("formatoptns" in js):
vars.formatoptns = js["formatoptns"]
if("numseqs" in js):
vars.numseqs = js["numseqs"]
if("widepth" in js):
vars.widepth = js["widepth"]
if("useprompt" in js):
vars.useprompt = js["useprompt"]
file.close()
#==================================================================#
# Don't save settings unless 2 seconds have passed without modification
#==================================================================#
@debounce(2)
def settingschanged():
print("{0}Saving settings!{1}".format(colors.GREEN, colors.END))
savesettings()
#==================================================================#
# Take input text from SocketIO and decide what to do with it
#==================================================================#
def actionsubmit(data):
# Ignore new submissions if the AI is currently busy
if(vars.aibusy):
return
set_aibusy(1)
# If we're not continuing, store a copy of the raw input
if(data != ""):
vars.lastact = data
if(not vars.gamestarted):
# Start the game
vars.gamestarted = True
# Save this first action as the prompt
vars.prompt = data
if(not vars.noai):
# Clear the startup text from game screen
emit('from_server', {'cmd': 'updatescreen', 'data': 'Please wait, generating story...'})
calcsubmit(data) # Run the first action through the generator
else:
refresh_story()
set_aibusy(0)
else:
# Dont append submission if it's a blank/continue action
if(data != ""):
# Apply input formatting & scripts before sending to tokenizer
data = applyinputformatting(data)
# Store the result in the Action log
vars.actions.append(data)
if(not vars.noai):
# Off to the tokenizer!
calcsubmit(data)
else:
refresh_story()
set_aibusy(0)
#==================================================================#
#
#==================================================================#
def actionretry(data):
if(vars.noai):
emit('from_server', {'cmd': 'errmsg', 'data': "Retry function unavailable in Read Only mode."})
return
if(vars.aibusy):
return
set_aibusy(1)
# Remove last action if possible and resubmit
if(len(vars.actions) > 0):
vars.actions.pop()
refresh_story()
calcsubmit('')
#==================================================================#
#
#==================================================================#
def actionback():
if(vars.aibusy):
return
# Remove last index of actions and refresh game screen
if(len(vars.actions) > 0):
vars.actions.pop()
refresh_story()
#==================================================================#
# Take submitted text and build the text to be given to generator
#==================================================================#
def calcsubmit(txt):
anotetxt = "" # Placeholder for Author's Note text
lnanote = 0 # Placeholder for Author's Note length
forceanote = False # In case we don't have enough actions to hit A.N. depth
anoteadded = False # In case our budget runs out before we hit A.N. depth
actionlen = len(vars.actions)
# Scan for WorldInfo matches
winfo = checkworldinfo(txt)
# Add a newline to the end of memory
if(vars.memory != "" and vars.memory[-1] != "\n"):
mem = vars.memory + "\n"
else:
mem = vars.memory
# Build Author's Note if set
if(vars.authornote != ""):
anotetxt = "\n[Author's note: "+vars.authornote+"]\n"
# For all transformers models
if(vars.model != "InferKit"):
anotetkns = [] # Placeholder for Author's Note tokens
# Calculate token budget
prompttkns = tokenizer.encode(vars.prompt)
lnprompt = len(prompttkns)
memtokens = tokenizer.encode(mem)
lnmem = len(memtokens)
witokens = tokenizer.encode(winfo)
lnwi = len(witokens)
if(anotetxt != ""):
anotetkns = tokenizer.encode(anotetxt)
lnanote = len(anotetkns)
if(vars.useprompt):
budget = vars.max_length - lnprompt - lnmem - lnanote - lnwi - vars.genamt
else:
budget = vars.max_length - lnmem - lnanote - lnwi - vars.genamt
if(actionlen == 0):
# First/Prompt action
subtxt = vars.memory + winfo + anotetxt + vars.prompt
lnsub = lnmem + lnwi + lnprompt + lnanote
if(not vars.model in ["Colab", "OAI"]):
generate(subtxt, lnsub+1, lnsub+vars.genamt)
elif(vars.model == "Colab"):
sendtocolab(subtxt, lnsub+1, lnsub+vars.genamt)
elif(vars.model == "OAI"):
oairequest(subtxt, lnsub+1, lnsub+vars.genamt)
else:
tokens = []
# Check if we have the action depth to hit our A.N. depth
if(anotetxt != "" and actionlen < vars.andepth):
forceanote = True
# Get most recent action tokens up to our budget
for n in range(actionlen):
if(budget <= 0):
break
acttkns = tokenizer.encode(vars.actions[(-1-n)])
tknlen = len(acttkns)
if(tknlen < budget):
tokens = acttkns + tokens
budget -= tknlen
else:
count = budget * -1
tokens = acttkns[count:] + tokens
budget = 0
break
# Inject Author's Note if we've reached the desired depth
if(n == vars.andepth-1):
if(anotetxt != ""):
tokens = anotetkns + tokens # A.N. len already taken from bdgt
anoteadded = True
# If we're not using the prompt every time and there's still budget left,
# add some prompt.
if(not vars.useprompt):
if(budget > 0):
prompttkns = prompttkns[-budget:]
else:
prompttkns = []
# Did we get to add the A.N.? If not, do it here
if(anotetxt != ""):
if((not anoteadded) or forceanote):
tokens = memtokens + witokens + anotetkns + prompttkns + tokens
else:
tokens = memtokens + witokens + prompttkns + tokens
else:
# Prepend Memory, WI, and Prompt before action tokens
tokens = memtokens + witokens + prompttkns + tokens
# Send completed bundle to generator
ln = len(tokens)
if(not vars.model in ["Colab", "OAI"]):
generate (
tokenizer.decode(tokens),
ln+1,
ln+vars.genamt
)
elif(vars.model == "Colab"):
sendtocolab(
tokenizer.decode(tokens),
ln+1,
ln+vars.genamt
)
elif(vars.model == "OAI"):
oairequest(
tokenizer.decode(tokens),
ln+1,
ln+vars.genamt
)
# For InferKit web API
else:
# Check if we have the action depth to hit our A.N. depth
if(anotetxt != "" and actionlen < vars.andepth):
forceanote = True
if(vars.useprompt):
budget = vars.ikmax - len(vars.prompt) - len(anotetxt) - len(mem) - len(winfo) - 1
else:
budget = vars.ikmax - len(anotetxt) - len(mem) - len(winfo) - 1
subtxt = ""
prompt = vars.prompt
for n in range(actionlen):
if(budget <= 0):
break
actlen = len(vars.actions[(-1-n)])
if(actlen < budget):
subtxt = vars.actions[(-1-n)] + subtxt
budget -= actlen
else:
count = budget * -1
subtxt = vars.actions[(-1-n)][count:] + subtxt
budget = 0
break
# If we're not using the prompt every time and there's still budget left,
# add some prompt.
if(not vars.useprompt):
if(budget > 0):
prompt = vars.prompt[-budget:]
else:
prompt = ""
# Inject Author's Note if we've reached the desired depth
if(n == vars.andepth-1):
if(anotetxt != ""):
subtxt = anotetxt + subtxt # A.N. len already taken from bdgt
anoteadded = True
# Did we get to add the A.N.? If not, do it here
if(anotetxt != ""):
if((not anoteadded) or forceanote):
subtxt = mem + winfo + anotetxt + prompt + subtxt
else:
subtxt = mem + winfo + prompt + subtxt
else:
subtxt = mem + winfo + prompt + subtxt
# Send it!
ikrequest(subtxt)
#==================================================================#
# Send text to generator and deal with output
#==================================================================#
def generate(txt, min, max):
print("{0}Min:{1}, Max:{2}, Txt:{3}{4}".format(colors.YELLOW, min, max, txt, colors.END))
# Store context in memory to use it for comparison with generated content
vars.lastctx = txt
# Clear CUDA cache if using GPU
if(vars.hascuda and vars.usegpu):
torch.cuda.empty_cache()
# Submit input text to generator
try:
genout = generator(
txt,
do_sample=True,
min_length=min,
max_length=max,
repetition_penalty=vars.rep_pen,
top_p=vars.top_p,
temperature=vars.temp,
bad_words_ids=vars.badwordsids,
use_cache=True,
return_full_text=False,
num_return_sequences=vars.numseqs
)
except Exception as e:
emit('from_server', {'cmd': 'errmsg', 'data': 'Error occured during generator call, please check console.'})
print("{0}{1}{2}".format(colors.RED, e, colors.END))
set_aibusy(0)
return
if(len(genout) == 1):
genresult(genout[0]["generated_text"])
else:
genselect(genout)
# Clear CUDA cache again if using GPU
if(vars.hascuda and vars.usegpu):
torch.cuda.empty_cache()
set_aibusy(0)
#==================================================================#
# Deal with a single return sequence from generate()
#==================================================================#
def genresult(genout):
print("{0}{1}{2}".format(colors.CYAN, genout, colors.END))
# Format output before continuing
genout = applyoutputformatting(genout)
# Add formatted text to Actions array and refresh the game screen
vars.actions.append(genout)
refresh_story()
emit('from_server', {'cmd': 'texteffect', 'data': len(vars.actions)})
#==================================================================#
# Send generator sequences to the UI for selection
#==================================================================#
def genselect(genout):
i = 0
for result in genout:
# Apply output formatting rules to sequences
result["generated_text"] = applyoutputformatting(result["generated_text"])
print("{0}[Result {1}]\n{2}{3}".format(colors.CYAN, i, result["generated_text"], colors.END))
i += 1
# Store sequences in memory until selection is made
vars.genseqs = genout
# Send sequences to UI for selection
emit('from_server', {'cmd': 'genseqs', 'data': genout})
# Refresh story for any input text
refresh_story()
#==================================================================#
# Send selected sequence to action log and refresh UI
#==================================================================#
def selectsequence(n):
if(len(vars.genseqs) == 0):
return
vars.actions.append(vars.genseqs[int(n)]["generated_text"])
refresh_story()
emit('from_server', {'cmd': 'texteffect', 'data': len(vars.actions)})
emit('from_server', {'cmd': 'hidegenseqs', 'data': ''})
vars.genseqs = []
#==================================================================#
# Send transformers-style request to ngrok/colab host
#==================================================================#
def sendtocolab(txt, min, max):
# Log request to console
print("{0}Tokens:{1}, Txt:{2}{3}".format(colors.YELLOW, min-1, txt, colors.END))
# Store context in memory to use it for comparison with generated content
vars.lastctx = txt
# Build request JSON data
reqdata = {
'text': txt,
'min': min,
'max': max,
'rep_pen': vars.rep_pen,
'temperature': vars.temp,
'top_p': vars.top_p,
'numseqs': vars.numseqs,
'retfultxt': False
}
# Create request
req = requests.post(
vars.colaburl,
json = reqdata
)