Encryption mod for kobold
This modification will encrypt any data you send to colab, where it will be decrypted again and fed to the AI like normal. The reverse is true for anything colab sends back to you. This ensures that your ISP and ngrok/cloudflare can't read what you're doing.
Back up your aiserver.py and colab before doing this
You can change the encryption key (the variable "key") but it needs to be exactly 44 characters long. You need to change it in both the colab and aiserver.py
To randomly generate a key (recommended), run the following commands in CMD after you've installed the cryptography package below:
python
- the python environment now opens in your CMD
from cryptography.fernet import Fernet
Fernet.generate_key()
- A key will now be printed to your console. Copy it and paste it over the "key" variables found near the top of the code blocks
aiserver.py
run pip install cryptography
in CMD
Paste the following over your aiserver.py file
modified regions are near the top (line 22) and in the function sendtocolab (line 988)
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 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 | #==================================================================#
# KoboldAI Client
# Version: 1.15.0
# By: KoboldAIDev
# Modified to encrypt outputs
#==================================================================#
# External packages
from os import path, getcwd
import tkinter as tk
from tkinter import messagebox
import json
import requests
# KoboldAI
import fileops
import gensettings
from utils import debounce
import utils
#Encryption
from cryptography.fernet import Fernet
key = b'HmoBK-unJ3HD-cjg9jup51k0RFfS98SuZaZXamvwv5o=' #This string NEEDS to be 44 characters long
f = Fernet(key)
def fenc(var):
return f.encrypt(var.encode("UTF-8")).decode("UTF-8")
def fdec(var):
return f.decrypt(var.encode("UTF-8")).decode("UTF-8")
#==================================================================#
# 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': fenc(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
)
# Deal with the response
if(req.status_code == 200):
js = req.json()["data"]
# Try to be backwards compatible with outdated colab
if("text" in js):
genout = [getnewcontent(js["text"])]
else:
genout = js["seqs"]
if(len(genout) == 1):
genresult(fdec(genout[0]))
else:
# Convert torch output format to transformers
seqs = []
for seq in genout:
seqs.append({"generated_text": fdec(seq)})
genselect(seqs)
# Format output before continuing
#genout = applyoutputformatting(getnewcontent(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)})
set_aibusy(0)
else:
errmsg = "Colab API Error: Failed to get a reply from the server. Please check the colab console."
print("{0}{1}{2}".format(colors.RED, errmsg, colors.END))
emit('from_server', {'cmd': 'errmsg', 'data': errmsg})
set_aibusy(0)
#==================================================================#
# Replaces returns and newlines with HTML breaks
#==================================================================#
def formatforhtml(txt):
return txt.replace("\\r", "<br/>").replace("\\n", "<br/>").replace('\n', '<br/>').replace('\r', '<br/>')
#==================================================================#
# Strips submitted text from the text returned by the AI
#==================================================================#
def getnewcontent(txt):
# If the submitted context was blank, then everything is new
if(vars.lastctx == ""):
return txt
# Tokenize the last context and the generated content
ctxtokens = tokenizer.encode(vars.lastctx)
txttokens = tokenizer.encode(txt)
dif = (len(txttokens) - len(ctxtokens)) * -1
# Remove the context from the returned text
newtokens = txttokens[dif:]
return tokenizer.decode(newtokens)
#==================================================================#
# Applies chosen formatting options to text submitted to AI
#==================================================================#
def applyinputformatting(txt):
# Add sentence spacing
if(vars.formatoptns["frmtadsnsp"]):
txt = utils.addsentencespacing(txt, vars)
return txt
#==================================================================#
# Applies chosen formatting options to text returned from AI
#==================================================================#
def applyoutputformatting(txt):
# Use standard quotes and apostrophes
txt = utils.fixquotes(txt)
# Trim incomplete sentences
if(vars.formatoptns["frmttriminc"]):
txt = utils.trimincompletesentence(txt)
# Replace blank lines
if(vars.formatoptns["frmtrmblln"]):
txt = utils.replaceblanklines(txt)
# Remove special characters
if(vars.formatoptns["frmtrmspch"]):
txt = utils.removespecialchars(txt)
return txt
#==================================================================#
# Sends the current story content to the Game Screen
#==================================================================#
def refresh_story():
text_parts = ['<chunk n="0" id="n0">', vars.prompt, '</chunk>']
for idx, item in enumerate(vars.actions, start=1):
text_parts.extend(('<chunk n="', str(idx), '" id="n', str(idx), '">', item, '</chunk>'))
emit('from_server', {'cmd': 'updatescreen', 'data': formatforhtml(''.join(text_parts))})
#==================================================================#
# Sends the current generator settings to the Game Menu
#==================================================================#
def refresh_settings():
# Suppress toggle change events while loading state
emit('from_server', {'cmd': 'allowtoggle', 'data': False})
if(vars.model != "InferKit"):
emit('from_server', {'cmd': 'updatetemp', 'data': vars.temp})
emit('from_server', {'cmd': 'updatetopp', 'data': vars.top_p})
emit('from_server', {'cmd': 'updatereppen', 'data': vars.rep_pen})
emit('from_server', {'cmd': 'updateoutlen', 'data': vars.genamt})
emit('from_server', {'cmd': 'updatetknmax', 'data': vars.max_length})
emit('from_server', {'cmd': 'updatenumseq', 'data': vars.numseqs})
else:
emit('from_server', {'cmd': 'updatetemp', 'data': vars.temp})
emit('from_server', {'cmd': 'updatetopp', 'data': vars.top_p})
emit('from_server', {'cmd': 'updateikgen', 'data': vars.ikgen})
emit('from_server', {'cmd': 'updateanotedepth', 'data': vars.andepth})
emit('from_server', {'cmd': 'updatewidepth', 'data': vars.widepth})
emit('from_server', {'cmd': 'updateuseprompt', 'data': vars.useprompt})
emit('from_server', {'cmd': 'updatefrmttriminc', 'data': vars.formatoptns["frmttriminc"]})
emit('from_server', {'cmd': 'updatefrmtrmblln', 'data': vars.formatoptns["frmtrmblln"]})
emit('from_server', {'cmd': 'updatefrmtrmspch', 'data': vars.formatoptns["frmtrmspch"]})
emit('from_server', {'cmd': 'updatefrmtadsnsp', 'data': vars.formatoptns["frmtadsnsp"]})
# Allow toggle events again
emit('from_server', {'cmd': 'allowtoggle', 'data': True})
#==================================================================#
# Sets the logical and display states for the AI Busy condition
#==================================================================#
def set_aibusy(state):
if(state):
vars.aibusy = True
emit('from_server', {'cmd': 'setgamestate', 'data': 'wait'})
else:
vars.aibusy = False
emit('from_server', {'cmd': 'setgamestate', 'data': 'ready'})
#==================================================================#
#
#==================================================================#
def editrequest(n):
if(n == 0):
txt = vars.prompt
else:
txt = vars.actions[n-1]
vars.editln = n
emit('from_server', {'cmd': 'setinputtext', 'data': txt})
emit('from_server', {'cmd': 'enablesubmit', 'data': ''})
#==================================================================#
#
#==================================================================#
def editsubmit(data):
if(vars.editln == 0):
vars.prompt = data
else:
vars.actions[vars.editln-1] = data
vars.mode = "play"
refresh_story()
emit('from_server', {'cmd': 'texteffect', 'data': vars.editln})
emit('from_server', {'cmd': 'editmode', 'data': 'false'})
#==================================================================#
#
#==================================================================#
def deleterequest():
# Don't delete prompt
if(vars.editln == 0):
# Send error message
pass
else:
del vars.actions[vars.editln-1]
vars.mode = "play"
refresh_story()
emit('from_server', {'cmd': 'editmode', 'data': 'false'})
#==================================================================#
# Toggles the game mode for memory editing and sends UI commands
#==================================================================#
def togglememorymode():
if(vars.mode == "play"):
vars.mode = "memory"
emit('from_server', {'cmd': 'memmode', 'data': 'true'})
emit('from_server', {'cmd': 'setinputtext', 'data': vars.memory})
emit('from_server', {'cmd': 'setanote', 'data': vars.authornote})
elif(vars.mode == "memory"):
vars.mode = "play"
emit('from_server', {'cmd': 'memmode', 'data': 'false'})
#==================================================================#
# Toggles the game mode for WI editing and sends UI commands
#==================================================================#
def togglewimode():
if(vars.mode == "play"):
vars.mode = "wi"
emit('from_server', {'cmd': 'wimode', 'data': 'true'})
elif(vars.mode == "wi"):
# Commit WI fields first
requestwi()
# Then set UI state back to Play
vars.mode = "play"
emit('from_server', {'cmd': 'wimode', 'data': 'false'})
#==================================================================#
#
#==================================================================#
def addwiitem():
ob = {"key": "", "content": "", "num": len(vars.worldinfo), "init": False}
vars.worldinfo.append(ob);
emit('from_server', {'cmd': 'addwiitem', 'data': ob})
#==================================================================#
#
#==================================================================#
def sendwi():
# Cache len of WI
ln = len(vars.worldinfo)
# Clear contents of WI container
emit('from_server', {'cmd': 'clearwi', 'data': ''})
# If there are no WI entries, send an empty WI object
if(ln == 0):
addwiitem()
else:
# Send contents of WI array
for wi in vars.worldinfo:
ob = wi
emit('from_server', {'cmd': 'addwiitem', 'data': ob})
# Make sure last WI item is uninitialized
if(vars.worldinfo[-1]["init"]):
addwiitem()
#==================================================================#
# Request current contents of all WI HTML elements
#==================================================================#
def requestwi():
list = []
for wi in vars.worldinfo:
list.append(wi["num"])
emit('from_server', {'cmd': 'requestwiitem', 'data': list})
#==================================================================#
# Renumber WI items consecutively
#==================================================================#
def organizewi():
if(len(vars.worldinfo) > 0):
count = 0
for wi in vars.worldinfo:
wi["num"] = count
count += 1
#==================================================================#
# Extract object from server and send it to WI objects
#==================================================================#
def commitwi(ar):
for ob in ar:
vars.worldinfo[ob["num"]]["key"] = ob["key"]
vars.worldinfo[ob["num"]]["content"] = ob["content"]
# Was this a deletion request? If so, remove the requested index
if(vars.deletewi >= 0):
del vars.worldinfo[vars.deletewi]
organizewi()
# Send the new WI array structure
sendwi()
# And reset deletewi index
vars.deletewi = -1
#==================================================================#
#
#==================================================================#
def deletewi(num):
if(num < len(vars.worldinfo)):
# Store index of deletion request
vars.deletewi = num
# Get contents of WI HTML inputs
requestwi()
#==================================================================#
# Look for WI keys in text to generator
#==================================================================#
def checkworldinfo(txt):
# Dont go any further if WI is empty
if(len(vars.worldinfo) == 0):
return
# Cache actions length
ln = len(vars.actions)
# Don't bother calculating action history if widepth is 0
if(vars.widepth > 0):
depth = vars.widepth
# If this is not a continue, add 1 to widepth since submitted
# text is already in action history @ -1
if(txt != "" and vars.prompt != txt):
txt = ""
depth += 1
if(ln >= depth):
txt = "".join(vars.actions[(depth*-1):])
elif(ln > 0):
txt = vars.prompt + "".join(vars.actions[(depth*-1):])
elif(ln == 0):
txt = vars.prompt
# Scan text for matches on WI keys
wimem = ""
for wi in vars.worldinfo:
if(wi["key"] != ""):
# Split comma-separated keys
keys = wi["key"].split(",")
for k in keys:
ky = k
# Remove leading/trailing spaces if the option is enabled
if(vars.wirmvwhtsp):
ky = k.strip()
if ky in txt:
wimem = wimem + wi["content"] + "\n"
break
return wimem
#==================================================================#
# Commit changes to Memory storage
#==================================================================#
def memsubmit(data):
# Maybe check for length at some point
# For now just send it to storage
vars.memory = data
vars.mode = "play"
emit('from_server', {'cmd': 'memmode', 'data': 'false'})
# Ask for contents of Author's Note field
emit('from_server', {'cmd': 'getanote', 'data': ''})
#==================================================================#
# Commit changes to Author's Note
#==================================================================#
def anotesubmit(data):
# Maybe check for length at some point
# For now just send it to storage
vars.authornote = data
#==================================================================#
# Assembles game data into a request to InferKit API
#==================================================================#
def ikrequest(txt):
# Log request to console
print("{0}Len:{1}, Txt:{2}{3}".format(colors.YELLOW, len(txt), txt, colors.END))
# Build request JSON data
reqdata = {
'forceNoEnd': True,
'length': vars.ikgen,
'prompt': {
'isContinuation': False,
'text': txt
},
'startFromBeginning': False,
'streamResponse': False,
'temperature': vars.temp,
'topP': vars.top_p
}
# Create request
req = requests.post(
vars.url,
json = reqdata,
headers = {
'Authorization': 'Bearer '+vars.apikey
}
)
# Deal with the response
if(req.status_code == 200):
genout = req.json()["data"]["text"]
print("{0}{1}{2}".format(colors.CYAN, genout, colors.END))
vars.actions.append(genout)
refresh_story()
emit('from_server', {'cmd': 'texteffect', 'data': len(vars.actions)})
set_aibusy(0)
else:
# Send error message to web client
er = req.json()
if("error" in er):
code = er["error"]["extensions"]["code"]
elif("errors" in er):
code = er["errors"][0]["extensions"]["code"]
errmsg = "InferKit API Error: {0} - {1}".format(req.status_code, code)
emit('from_server', {'cmd': 'errmsg', 'data': errmsg})
set_aibusy(0)
#==================================================================#
# Assembles game data into a request to OpenAI API
#==================================================================#
def oairequest(txt, min, max):
# Log request to console
print("{0}Len:{1}, Txt:{2}{3}".format(colors.YELLOW, len(txt), txt, colors.END))
# Store context in memory to use it for comparison with generated content
vars.lastctx = txt
# Build request JSON data
reqdata = {
'prompt': txt,
'max_tokens': max,
'temperature': vars.temp,
'top_p': vars.top_p,
'n': 1,
'stream': False
}
req = requests.post(
vars.oaiurl,
json = reqdata,
headers = {
'Authorization': 'Bearer '+vars.oaiapikey,
'Content-Type': 'application/json'
}
)
# Deal with the response
if(req.status_code == 200):
genout = req.json()["choices"][0]["text"]
print("{0}{1}{2}".format(colors.CYAN, genout, colors.END))
vars.actions.append(genout)
refresh_story()
emit('from_server', {'cmd': 'texteffect', 'data': len(vars.actions)})
set_aibusy(0)
else:
# Send error message to web client
er = req.json()
if("error" in er):
type = er["error"]["type"]
message = er["error"]["message"]
errmsg = "OpenAI API Error: {0} - {1}".format(type, message)
emit('from_server', {'cmd': 'errmsg', 'data': errmsg})
set_aibusy(0)
#==================================================================#
# Forces UI to Play mode
#==================================================================#
def exitModes():
if(vars.mode == "edit"):
emit('from_server', {'cmd': 'editmode', 'data': 'false'})
elif(vars.mode == "memory"):
emit('from_server', {'cmd': 'memmode', 'data': 'false'})
elif(vars.mode == "wi"):
emit('from_server', {'cmd': 'wimode', 'data': 'false'})
vars.mode = "play"
#==================================================================#
# Launch in-browser save prompt
#==================================================================#
def saveas(name):
# Check if filename exists already
name = utils.cleanfilename(name)
if(not fileops.saveexists(name) or (vars.saveow and vars.svowname == name)):
# All clear to save
saveRequest(getcwd()+"/stories/"+name+".json")
emit('from_server', {'cmd': 'hidesaveas', 'data': ''})
vars.saveow = False
vars.svowname = ""
else:
# File exists, prompt for overwrite
vars.saveow = True
vars.svowname = name
emit('from_server', {'cmd': 'askforoverwrite', 'data': ''})
#==================================================================#
# Save the currently running story
#==================================================================#
def save():
# Check if a file is currently open
if(".json" in vars.savedir):
saveRequest(vars.savedir)
else:
emit('from_server', {'cmd': 'saveas', 'data': ''})
#==================================================================#
# Save the story via file browser
#==================================================================#
def savetofile():
savpath = fileops.getsavepath(vars.savedir, "Save Story As", [("Json", "*.json")])
saveRequest(savpath)
#==================================================================#
# Save the story to specified path
#==================================================================#
def saveRequest(savpath):
if(savpath):
# Leave Edit/Memory mode before continuing
exitModes()
# Save path for future saves
vars.savedir = savpath
# Build json to write
js = {}
js["gamestarted"] = vars.gamestarted
js["prompt"] = vars.prompt
js["memory"] = vars.memory
js["authorsnote"] = vars.authornote
js["actions"] = vars.actions
js["worldinfo"] = []
# Extract only the important bits of WI
for wi in vars.worldinfo:
if(wi["key"] != ""):
js["worldinfo"].append({
"key": wi["key"],
"content": wi["content"]
})
# Write it
file = open(savpath, "w")
try:
file.write(json.dumps(js, indent=3))
finally:
file.close()
print("{0}Story saved to {1}!{2}".format(colors.GREEN, path.basename(savpath), colors.END))
#==================================================================#
# Load a saved story via file browser
#==================================================================#
def getloadlist():
emit('from_server', {'cmd': 'buildload', 'data': fileops.getstoryfiles()})
#==================================================================#
# Load a saved story via file browser
#==================================================================#
def loadfromfile():
loadpath = fileops.getloadpath(vars.savedir, "Select Story File", [("Json", "*.json")])
loadRequest(loadpath)
#==================================================================#
# Load a stored story from a file
#==================================================================#
def loadRequest(loadpath):
if(loadpath):
# Leave Edit/Memory mode before continuing
exitModes()
# Read file contents into JSON object
file = open(loadpath, "r")
js = json.load(file)
# Copy file contents to vars
vars.gamestarted = js["gamestarted"]
vars.prompt = js["prompt"]
vars.memory = js["memory"]
vars.actions = js["actions"]
vars.worldinfo = []
vars.lastact = ""
vars.lastctx = ""
# Try not to break older save files
if("authorsnote" in js):
vars.authornote = js["authorsnote"]
else:
vars.authornote = ""
if("worldinfo" in js):
num = 0
for wi in js["worldinfo"]:
vars.worldinfo.append({
"key": wi["key"],
"content": wi["content"],
"num": num,
"init": True
})
num += 1
file.close()
# Save path for save button
vars.savedir = loadpath
# Clear loadselect var
vars.loadselect = ""
# Refresh game screen
sendwi()
refresh_story()
emit('from_server', {'cmd': 'setgamestate', 'data': 'ready'})
emit('from_server', {'cmd': 'hidegenseqs', 'data': ''})
print("{0}Story loaded from {1}!{2}".format(colors.GREEN, path.basename(loadpath), colors.END))
#==================================================================#
# Import an AIDungon game exported with Mimi's tool
#==================================================================#
def importRequest():
importpath = fileops.getloadpath(vars.savedir, "Select AID CAT File", [("Json", "*.json")])
if(importpath):
# Leave Edit/Memory mode before continuing
exitModes()
# Read file contents into JSON object
file = open(importpath, "rb")
vars.importjs = json.load(file)
# If a bundle file is being imported, select just the Adventures object
if type(vars.importjs) is dict and "stories" in vars.importjs:
vars.importjs = vars.importjs["stories"]
# Clear Popup Contents
emit('from_server', {'cmd': 'clearpopup', 'data': ''})
# Initialize vars
num = 0
vars.importnum = -1
# Get list of stories
for story in vars.importjs:
ob = {}
ob["num"] = num
if(story["title"] != "" and story["title"] != None):
ob["title"] = story["title"]
else:
ob["title"] = "(No Title)"
if(story["description"] != "" and story["description"] != None):
ob["descr"] = story["description"]
else:
ob["descr"] = "(No Description)"
if("actions" in story):
ob["acts"] = len(story["actions"])
elif("actionWindow" in story):
ob["acts"] = len(story["actionWindow"])
emit('from_server', {'cmd': 'addimportline', 'data': ob})
num += 1
# Show Popup
emit('from_server', {'cmd': 'popupshow', 'data': True})
#==================================================================#
# Import an AIDungon game selected in popup
#==================================================================#
def importgame():
if(vars.importnum >= 0):
# Cache reference to selected game
ref = vars.importjs[vars.importnum]
# Copy game contents to vars
vars.gamestarted = True
# Support for different versions of export script
if("actions" in ref):
if(len(ref["actions"]) > 0):
vars.prompt = ref["actions"][0]["text"]
else:
vars.prompt = ""
elif("actionWindow" in ref):
if(len(ref["actionWindow"]) > 0):
vars.prompt = ref["actionWindow"][0]["text"]
else:
vars.prompt = ""
else:
vars.prompt = ""
vars.memory = ref["memory"]
vars.authornote = ref["authorsNote"] if type(ref["authorsNote"]) is str else ""
vars.actions = []
vars.worldinfo = []
vars.lastact = ""
vars.lastctx = ""
# Get all actions except for prompt
if("actions" in ref):
if(len(ref["actions"]) > 1):
for act in ref["actions"][1:]:
vars.actions.append(act["text"])
elif("actionWindow" in ref):
if(len(ref["actionWindow"]) > 1):
for act in ref["actionWindow"][1:]:
vars.actions.append(act["text"])
# Get just the important parts of world info
if(ref["worldInfo"] != None):
if(len(ref["worldInfo"]) > 1):
num = 0
for wi in ref["worldInfo"]:
vars.worldinfo.append({
"key": wi["keys"],
"content": wi["entry"],
"num": num,
"init": True
})
num += 1
# Clear import data
vars.importjs = {}
# Reset current save
vars.savedir = getcwd()+"\stories"
# Refresh game screen
sendwi()
refresh_story()
emit('from_server', {'cmd': 'setgamestate', 'data': 'ready'})
emit('from_server', {'cmd': 'hidegenseqs', 'data': ''})
#==================================================================#
# Import an aidg.club prompt and start a new game with it.
#==================================================================#
def importAidgRequest(id):
exitModes()
urlformat = "https://prompts.aidg.club/api/"
req = requests.get(urlformat+id)
if(req.status_code == 200):
js = req.json()
# Import game state
vars.gamestarted = True
vars.prompt = js["promptContent"]
vars.memory = js["memory"]
vars.authornote = js["authorsNote"]
vars.actions = []
vars.worldinfo = []
vars.lastact = ""
vars.lastctx = ""
num = 0
for wi in js["worldInfos"]:
vars.worldinfo.append({
"key": wi["keys"],
"content": wi["entry"],
"num": num,
"init": True
})
num += 1
# Reset current save
vars.savedir = getcwd()+"\stories"
# Refresh game screen
sendwi()
refresh_story()
emit('from_server', {'cmd': 'setgamestate', 'data': 'ready'})
#==================================================================#
# Import World Info JSON file
#==================================================================#
def wiimportrequest():
importpath = fileops.getloadpath(vars.savedir, "Select World Info File", [("Json", "*.json")])
if(importpath):
file = open(importpath, "rb")
js = json.load(file)
if(len(js) > 0):
# If the most recent WI entry is blank, remove it.
if(not vars.worldinfo[-1]["init"]):
del vars.worldinfo[-1]
# Now grab the new stuff
num = len(vars.worldinfo)
for wi in js:
vars.worldinfo.append({
"key": wi["keys"],
"content": wi["entry"],
"num": num,
"init": True
})
num += 1
print("{0}".format(vars.worldinfo[0]))
# Refresh game screen
sendwi()
#==================================================================#
# Starts a new story
#==================================================================#
def newGameRequest():
# Leave Edit/Memory mode before continuing
exitModes()
# Clear vars values
vars.gamestarted = False
vars.prompt = ""
vars.memory = ""
vars.actions = []
vars.authornote = ""
vars.worldinfo = []
vars.lastact = ""
vars.lastctx = ""
# Reset current save
vars.savedir = getcwd()+"\stories"
# Refresh game screen
sendwi()
setStartState()
#==================================================================#
# Final startup commands to launch Flask app
#==================================================================#
if __name__ == "__main__":
# Load settings from client.settings
loadsettings()
# Start Flask/SocketIO (Blocking, so this must be last method!)
print("{0}Server started!\rYou may now connect with a browser at http://127.0.0.1:5000/{1}".format(colors.GREEN, colors.END))
#socketio.run(app, host='0.0.0.0', port=5000)
socketio.run(app)
|
Colab V2 Step 4
Paste the following over Step 4 in colab:
too much of a pain to say where the modifications are. just look near the top and anywhere it says "text" or "genout"
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 | #@title <b>Step 4 - Run Web Service</b> { display-mode: "form" }
#@markdown Press the Play button. Flask will start and give you a
#@markdown Cloudflare or Ngrok address which looks like this:<br/>
#@markdown <i>https://\<unique id\>.trycloudflare.com/</i><br/>
#@markdown <i>http://\<unique id\>.ngrok.io/</i><br/>
#@markdown You will need to right-click this and copy the address.
#@markdown Start the KoboldAI Client on your computer and choose
#@markdown Google Colab as the model. You will be asked to paste
#@markdown the address into the terminal.<br/><br/>
#@markdown If your session is interrupted, you can just restart
#@markdown this cell to get a new address without reinitializing
#@markdown the model.</br></br>
#@markdown <b>The first generation takes around a minute due to
#@markdown compilation, but after that it should take less than
#@markdown 10 seconds per sample.</b>
!pip install cryptography
from cryptography.fernet import Fernet
key = b'HmoBK-unJ3HD-cjg9jup51k0RFfS98SuZaZXamvwv5o='
f = Fernet(key)
def fenc(var):
return f.encrypt(var.encode("UTF-8")).decode("UTF-8")
def fdec(var):
return f.decrypt(var.encode("UTF-8")).decode("UTF-8")
app = Flask(__name__)
if connect_method == "Cloudflare":
run_with_cloudflared(app)
elif connect_method == "Ngrok":
run_with_ngrok(app)
@app.route("/")
def home():
return "<h1>KoboldAI Colab Service Running!</h1>"
@app.route('/request',methods = ['POST'])
def koboldrequest():
if request.method == 'POST':
try:
clear_output()
js = request.json
#print(js["text"])
txt = fdec(js["text"])
min = js["min"]
max = js["max"]
rep_pen = js["rep_pen"]
temp = js["temperature"]
top_p = js["top_p"]
#print(txt)
# Compatability with un-updated clients
if("numseqs" in js):
numseqs = js["numseqs"]
else:
numseqs = 1
if("retfultxt" in js):
retfultxt = js["retfultxt"]
else:
retfultxt = True
#print(colored("Received Data: {0}".format(txt), "yellow"))
torch.cuda.empty_cache()
print(colored("Generating text, please wait...", "green"))
tokens = tokenizer(txt, return_tensors="pt").input_ids.to("cpu")
ids = tokens.cuda()
gen_tokens = model.generate(
ids.long().cuda(),
do_sample=True,
min_length=min,
max_length=max,
temperature=temp,
top_p = top_p,
repetition_penalty = rep_pen,
use_cache=True,
bad_words_ids=bad_words_ids,
num_return_sequences=numseqs
).long()
genout = []
for tkns in gen_tokens:
if(not retfultxt):
# Strip context tokens out of returned sequences
dif = (len(tkns) - len(tokens[0])) * -1
tkns = tkns[dif:]
tkns = list(filter(lambda a: a != 50256, tkns))
genout.append(fenc(tokenizer.decode(tkns)))
torch.cuda.empty_cache()
if(len(genout) > 0 and genout[0] != ""):
if(retfultxt):
# Outdated client, send old JSON format
#print(colored("Generated Text: {0}".format(genout[0]), "cyan"))
response = app.response_class(
response=json.dumps({"data": {"text": genout[0]}}),
status=200,
mimetype='application/json'
)
else:
# New client format with numseq support
i = 0
for seq in genout:
#print(colored("[Result {0}]\n{1}".format(i, seq), "cyan"))
i += 1
response = app.response_class(
response=json.dumps({"data": {"seqs": genout}}),
status=200,
mimetype='application/json'
)
return response
else:
print(colored("[ERROR] Something went wrong during generation!", "red"))
response = app.response_class(
response=json.dumps({"error": {"extensions": {"code": "Something went wrong during generation!"}}}),
status=400,
mimetype='application/json'
)
js = {}
tokens = []
ids = []
gen_tokens = []
genout = ""
response = {}
except Exception as e:
print(colored("[ERROR] Something went wrong during generation!", "red"))
print(colored("{0}".format(e), "red"))
response = app.response_class(
response=json.dumps({"error": {"extensions": {"code": "Something went wrong during generation! {0}".format(e)}}}),
status=400,
mimetype='application/json'
)
print(colored("Starup complete! Running web service.", "green"))
app.run()
|
Colab V1 Step 4
Paste the following over Step 4 in colab:
Again, look near the top and near "text" and "genout"
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 | #@title <b>Step 4 - Run Web Service</b> { display-mode: "form" }
#@markdown Press the Play button. Flask will start and give you an
#@markdown Ngrok address which looks like this:<br/>
#@markdown <i>https://\<unique id\>.trycloudflare.com/</i><br/>
#@markdown You will need to right-click this and copy the address.
#@markdown Start the KoboldAI Client on your computer and choose
#@markdown Google Colab as the model. You will be asked to paste
#@markdown the Ngrok address into the terminal.<br/><br/>
#@markdown If your session is interrupted, you can just restart
#@markdown this cell to get a new address without reinitializing
#@markdown the model.</br></br>
#@markdown <b>The first generation takes around a minute due to
#@markdown compilation, but after that it should only take about
#@markdown 10 seconds per sample.</b>
!pip install cryptography
from cryptography.fernet import Fernet
key = b'HmoBK-unJ3HD-cjg9jup51k0RFfS98SuZaZXamvwv5o='
f = Fernet(key)
def fenc(var):
return f.encrypt(var.encode("UTF-8")).decode("UTF-8")
def fdec(var):
return f.decrypt(var.encode("UTF-8")).decode("UTF-8")
tenv = maps.ResourceEnv(maps.Mesh(devices, ('dp', 'mp')))
if connect_method == "Cloudflare":
from flask_cloudflared import run_with_cloudflared
elif connect_method == "Ngrok":
from flask_ngrok import run_with_ngrok
app = Flask(__name__)
if connect_method == "Cloudflare":
run_with_cloudflared(app)
elif connect_method == "Ngrok":
run_with_ngrok(app)
@app.route("/")
def home():
return "<h1>KoboldAI Colab Service Running!</h1>"
@app.route('/request',methods = ['POST'])
def koboldrequest():
if request.method == 'POST':
try:
clear_output()
js = request.json
txt = fdec(js["text"])
min = js["min"]
max = js["max"]
rep_pen = js["rep_pen"]
temp = js["temperature"]
top_p = js["top_p"]
gen_len = max - (min - 1)
#print(colored("Received Data: {0}".format(txt), "yellow"))
print(colored("Generating text, please wait...", "green"))
# env has to be redefined with each call for some reason, else a threading error is produced
maps.thread_resources.env = tenv
tokens = tokenizer.encode(txt)
provided_ctx = len(tokens)
pad_amount = seq - provided_ctx
padded_tokens = np.pad(tokens, ((pad_amount, 0),)).astype(np.uint32)
batched_tokens = np.array([padded_tokens] * total_batch)
length = np.ones(total_batch, dtype=np.uint32) * len(tokens)
output = network.generate(batched_tokens, length, gen_len, {"top_p": np.ones(total_batch) * top_p, "temp": np.ones(total_batch) * temp})
samples = []
decoded_tokens = output[1][0]
for o in decoded_tokens[:, :, 0]:
samples.append(fenc(tokenizer.decode(o)))
genout = samples[0]
#print(colored("Generated Text: {0}".format(genout), "cyan"))
response = app.response_class(
response=json.dumps({"data": {"seqs": [genout]}}),
status=200,
mimetype='application/json'
)
js = {}
genout = ""
return response
except Exception as e:
print(colored("[ERROR] Something went wrong during generation!", "red"))
print(colored("{0}".format(e), "red"))
response = app.response_class(
response=json.dumps({"error": {"extensions": {"code": "Something went wrong during generation! {0}".format(e)}}}),
status=400,
mimetype='application/json'
)
print(colored("Starup complete! Running web service.", "green"))
app.run()
|