File size: 55,869 Bytes
395201c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import sys, os
import traceback
from dotenv import load_dotenv

load_dotenv()
import os, io

sys.path.insert(
    0, os.path.abspath("../..")
)  # Adds the parent directory to the system path 
import pytest
import litellm
from litellm import embedding, completion, completion_cost, Timeout
from litellm import RateLimitError
litellm.num_retries = 3
litellm.cache = None
user_message = "Write a short poem about the sky"
messages = [{"content": user_message, "role": "user"}]

def logger_fn(user_model_dict):
    print(f"user_model_dict: {user_model_dict}")


def test_completion_custom_provider_model_name():
    try:
        litellm.cache = None
        response = completion(
            model="together_ai/togethercomputer/llama-2-70b-chat",
            messages=messages,
            logger_fn=logger_fn,
        )
        # Add any assertions here to check the response
        print(response)
        print(response['choices'][0]['finish_reason'])
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")


# test_completion_custom_provider_model_name()


def test_completion_claude():
    litellm.set_verbose = True
    litellm.cache = None
    litellm.AnthropicConfig(max_tokens_to_sample=200, metadata={"user_id": "1224"})
    messages = [{"role": "system", "content": """You are an upbeat, enthusiastic personal fitness coach named Sam. Sam is passionate about helping clients get fit and lead healthier lifestyles. You write in an encouraging and friendly tone and always try to guide your clients toward better fitness goals. If the user asks you something unrelated to fitness, either bring the topic back to fitness, or say that you cannot answer."""},{"content": user_message, "role": "user"}]
    try:
        # test without max tokens
        response = completion(
            model="claude-instant-1", messages=messages, request_timeout=10,
        )
        # Add any assertions here to check the response
        print(response)
        print(response.usage)
        print(response.usage.completion_tokens)
        print(response["usage"]["completion_tokens"])
        # print("new cost tracking")
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")

# test_completion_claude()

def test_completion_claude2_1():
    try:
        print("claude2.1 test request")
        # test without max tokens
        response = completion(
            model="claude-2.1", 
            messages=messages, 
            request_timeout=10,
            max_tokens=10
        )
        # Add any assertions here to check the response
        print(response)
        print(response.usage)
        print(response.usage.completion_tokens)
        print(response["usage"]["completion_tokens"])
        # print("new cost tracking")
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")
# test_completion_claude2_1()

# def test_completion_oobabooga():
#     try:
#         response = completion(
#             model="oobabooga/vicuna-1.3b", messages=messages, api_base="http://127.0.0.1:5000"
#         )
#         # Add any assertions here to check the response
#         print(response)
#     except Exception as e:
#         pytest.fail(f"Error occurred: {e}")

# test_completion_oobabooga()
# aleph alpha
# def test_completion_aleph_alpha():
#     try:
#         response = completion(
#             model="luminous-base", messages=messages, logger_fn=logger_fn
#         )
#         # Add any assertions here to check the response
#         print(response)
#     except Exception as e:
#         pytest.fail(f"Error occurred: {e}")
# test_completion_aleph_alpha()


# def test_completion_aleph_alpha_control_models():
#     try:
#         response = completion(
#             model="luminous-base-control", messages=messages, logger_fn=logger_fn
#         )
#         # Add any assertions here to check the response
#         print(response)
#     except Exception as e:
#         pytest.fail(f"Error occurred: {e}")
# test_completion_aleph_alpha_control_models()

import openai
def test_completion_gpt4_turbo():
    try:
        response = completion(
            model="gpt-4-1106-preview", 
            messages=messages,
            max_tokens=10,
        )
        print(response)
    except openai.RateLimitError:
        print("got a rate liimt error")
        pass
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")
# test_completion_gpt4_turbo()

def test_completion_gpt4_vision():
    try:
        litellm.set_verbose=True
        response = completion(
            model="gpt-4-vision-preview", 
            messages=[
                {
                    "role": "user",
                    "content": [
                                    {
                                        "type": "text",
                                        "text": "Whats in this image?"
                                    },
                                    {
                                        "type": "image_url",
                                        "image_url": {
                                        "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
                                        }
                                    }
                                ]
                }
            ],
        )
        print(response)
    except openai.RateLimitError:
        print("got a rate liimt error")
        pass
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")
# test_completion_gpt4_vision()

def test_completion_perplexity_api():
    try:
        # litellm.set_verbose=True
        messages=[{
            "role": "system", 
            "content": "You're a good bot"
        },{
            "role": "user", 
            "content": "Hey", 
        },{
            "role": "user", 
            "content": "Hey", 
        }]
        response = completion(
            model="mistral-7b-instruct", 
            messages=messages,
            api_base="https://api.perplexity.ai")
        print(response)
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")

# test_completion_perplexity_api()

def test_completion_perplexity_api_2():
    try:
        # litellm.set_verbose=True
        messages=[{
            "role": "system", 
            "content": "You're a good bot"
        },{
            "role": "user", 
            "content": "Hey", 
        },{
            "role": "user", 
            "content": "Hey", 
        }]
        response = completion(
            model="perplexity/mistral-7b-instruct", 
            messages=messages
        )
        print(response)
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")
# test_completion_perplexity_api_2()

# commenting out as this is a flaky test on circle ci
# def test_completion_nlp_cloud():
#     try:
#         messages = [
#             {"role": "system", "content": "You are a helpful assistant."},
#             {
#                 "role": "user",
#                 "content": "how does a court case get to the Supreme Court?",
#             },
#         ]
#         response = completion(model="dolphin", messages=messages, logger_fn=logger_fn)
#         print(response)
#     except Exception as e:
#         pytest.fail(f"Error occurred: {e}")

# test_completion_nlp_cloud()

######### HUGGING FACE TESTS ########################
#####################################################
"""
HF Tests we should pass 
- TGI: 
    - Pro Inference API 
    - Deployed Endpoint 
- Coversational 
    - Free Inference API 
    - Deployed Endpoint 
- Neither TGI or Coversational
    - Free Inference API 
    - Deployed Endpoint 
"""
#####################################################
#####################################################
# Test util to sort models to TGI, conv, None
def test_get_hf_task_for_model():
    model = "glaiveai/glaive-coder-7b"
    model_type = litellm.llms.huggingface_restapi.get_hf_task_for_model(model)
    print(f"model:{model}, model type: {model_type}")
    assert(model_type == "text-generation-inference")

    model = "meta-llama/Llama-2-7b-hf"
    model_type = litellm.llms.huggingface_restapi.get_hf_task_for_model(model)
    print(f"model:{model}, model type: {model_type}")
    assert(model_type == "text-generation-inference")

    model = "facebook/blenderbot-400M-distill"
    model_type = litellm.llms.huggingface_restapi.get_hf_task_for_model(model)
    print(f"model:{model}, model type: {model_type}")
    assert(model_type == "conversational")

    model = "facebook/blenderbot-3B"
    model_type = litellm.llms.huggingface_restapi.get_hf_task_for_model(model)
    print(f"model:{model}, model type: {model_type}")
    assert(model_type == "conversational")

    # neither Conv or None
    model = "roneneldan/TinyStories-3M"
    model_type = litellm.llms.huggingface_restapi.get_hf_task_for_model(model)
    print(f"model:{model}, model type: {model_type}")
    assert(model_type == None)

# test_get_hf_task_for_model()
# litellm.set_verbose=False
# ################### Hugging Face TGI models ########################
# # TGI model
# # this is a TGI model https://huggingface.co/glaiveai/glaive-coder-7b
def hf_test_completion_tgi():
    # litellm.set_verbose=True
    try:
        response = completion(
            model = 'huggingface/HuggingFaceH4/zephyr-7b-beta', 
            messages = [{ "content": "Hello, how are you?","role": "user"}],
        )
        # Add any assertions here to check the response
        print(response)
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")
# hf_test_completion_tgi()

# ################### Hugging Face Conversational models ########################
# def hf_test_completion_conv():
#     try:
#         response = litellm.completion(
#             model="huggingface/facebook/blenderbot-3B",
#             messages=[{ "content": "Hello, how are you?","role": "user"}],
#         )
#         # Add any assertions here to check the response
#         print(response)
#     except Exception as e:
#         pytest.fail(f"Error occurred: {e}")
# hf_test_completion_conv()

# ################### Hugging Face Neither TGI or Conversational models ########################
# # Neither TGI or Conversational
# def hf_test_completion_none_task():
#     try:
#         user_message = "My name is Merve and my favorite"
#         messages = [{ "content": user_message,"role": "user"}]
#         response = completion(
#             model="huggingface/roneneldan/TinyStories-3M", 
#             messages=messages,
#             api_base="https://p69xlsj6rpno5drq.us-east-1.aws.endpoints.huggingface.cloud",
#         )
#         # Add any assertions here to check the response
#         print(response)
#     except Exception as e:
#         pytest.fail(f"Error occurred: {e}")
# hf_test_completion_none_task()
########################### End of Hugging Face Tests ##############################################
# def test_completion_hf_api():
# # failing on circle ci commenting out
#     try:
#         user_message = "write some code to find the sum of two numbers"
#         messages = [{ "content": user_message,"role": "user"}]
#         api_base = "https://a8l9e3ucxinyl3oj.us-east-1.aws.endpoints.huggingface.cloud"
#         response = completion(model="huggingface/meta-llama/Llama-2-7b-chat-hf", messages=messages, api_base=api_base)
#         # Add any assertions here to check the response
#         print(response)
#     except Exception as e:
#         if "loading" in str(e):
#             pass
#         pytest.fail(f"Error occurred: {e}")

# test_completion_hf_api()

# def test_completion_hf_api_best_of():
# # failing on circle ci commenting out
#     try:
#         user_message = "write some code to find the sum of two numbers"
#         messages = [{ "content": user_message,"role": "user"}]
#         api_base = "https://a8l9e3ucxinyl3oj.us-east-1.aws.endpoints.huggingface.cloud"
#         response = completion(model="huggingface/meta-llama/Llama-2-7b-chat-hf", messages=messages, api_base=api_base, n=2)
#         # Add any assertions here to check the response
#         print(response)
#     except Exception as e:
#         if "loading" in str(e):
#             pass
#         pytest.fail(f"Error occurred: {e}")

# test_completion_hf_api_best_of()

# def test_completion_hf_deployed_api():
#     try:
#         user_message = "There's a llama in my garden 😱 What should I do?"
#         messages = [{ "content": user_message,"role": "user"}]
#         response = completion(model="huggingface/https://ji16r2iys9a8rjk2.us-east-1.aws.endpoints.huggingface.cloud", messages=messages, logger_fn=logger_fn)
#         # Add any assertions here to check the response
#         print(response)
#     except Exception as e:
#         pytest.fail(f"Error occurred: {e}")


# this should throw an exception, to trigger https://logs.litellm.ai/
# def hf_test_error_logs():
#     try:
#         litellm.set_verbose=True
#         user_message = "My name is Merve and my favorite"
#         messages = [{ "content": user_message,"role": "user"}]
#         response = completion(
#             model="huggingface/roneneldan/TinyStories-3M", 
#             messages=messages,
#             api_base="https://p69xlsj6rpno5drq.us-east-1.aws.endpoints.huggingface.cloud",

#         )
#         # Add any assertions here to check the response
#         print(response)

#     except Exception as e:
#         pytest.fail(f"Error occurred: {e}")

# hf_test_error_logs()

def test_completion_cohere(): # commenting for now as the cohere endpoint is being flaky
    try:
        litellm.CohereConfig(max_tokens=1000, stop_sequences=["a"])
        response = completion(
            model="command-nightly",
            messages=messages,
            logger_fn=logger_fn
        )
        # Add any assertions here to check the response
        print(response)
        response_str = response["choices"][0]["message"]["content"]
        response_str_2 = response.choices[0].message.content
        if type(response_str) != str:
            pytest.fail(f"Error occurred: {e}")
        if type(response_str_2) != str:
            pytest.fail(f"Error occurred: {e}")
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")

# test_completion_cohere() 


def test_completion_openai():
    try:
        litellm.set_verbose=True
        print(f"api key: {os.environ['OPENAI_API_KEY']}")
        litellm.api_key = os.environ['OPENAI_API_KEY']
        response = completion(
            model="gpt-3.5-turbo", 
            messages=messages, 
            max_tokens=10, 
            request_timeout=1,
            metadata = {"hi": "bye"}
        )
        print("This is the response object\n", response)

        
        response_str = response["choices"][0]["message"]["content"]
        response_str_2 = response.choices[0].message.content

        cost = completion_cost(completion_response=response)
        print("Cost for completion call with gpt-3.5-turbo: ", f"${float(cost):.10f}")
        assert response_str == response_str_2
        assert type(response_str) == str
        assert len(response_str) > 1

        litellm.api_key = None
    except Timeout as e:
        pass
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")
# test_completion_openai()

def test_completion_text_openai():
    try:
        # litellm.set_verbose = True
        response = completion(model="gpt-3.5-turbo-instruct", messages=messages)
        print(response["choices"][0]["message"]["content"])
    except Exception as e:
        print(e)
        pytest.fail(f"Error occurred: {e}")
# test_completion_text_openai()

def custom_callback(
    kwargs,                 # kwargs to completion
    completion_response,    # response from completion
    start_time, end_time    # start/end time
):
    # Your custom code here
    try:
        print("LITELLM: in custom callback function")
        print("\nkwargs\n", kwargs)
        model = kwargs["model"]
        messages = kwargs["messages"]
        user = kwargs.get("user")

        #################################################

        print(
            f"""
                Model: {model},
                Messages: {messages},
                User: {user},
                Seed: {kwargs["seed"]},
                temperature: {kwargs["temperature"]},
            """
        )

        assert kwargs["user"] == "ishaans app"
        assert kwargs["model"] == "gpt-3.5-turbo-1106"
        assert kwargs["seed"] == 12
        assert kwargs["temperature"] == 0.5
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")

def test_completion_openai_with_optional_params():
    # [Proxy PROD TEST] WARNING: DO NOT DELETE THIS TEST
    # assert that `user` gets passed to the completion call
    # Note: This tests that we actually send the optional params to the completion call
    # We use custom callbacks to test this 
    try:
        litellm.set_verbose = True
        litellm.success_callback = [custom_callback]
        response = completion(
            model="gpt-3.5-turbo-1106",
            messages=[
                {
                    "role": "user",
                    "content": "respond in valid, json - what is the day"
                }
            ],
            temperature=0.5,
            top_p=0.1,
            seed=12,
            response_format={ "type": "json_object" },
            logit_bias=None,
            user = "ishaans app"
        )
        # Add any assertions here to check the response

        print(response)
        litellm.success_callback = [] # unset callbacks

    except Exception as e:
        pytest.fail(f"Error occurred: {e}")

# test_completion_openai_with_optional_params()

def test_completion_openai_litellm_key():
    try:
        litellm.set_verbose = True
        litellm.num_retries = 0
        litellm.api_key = os.environ['OPENAI_API_KEY']

        # ensure key is set to None in .env and in openai.api_key
        os.environ['OPENAI_API_KEY'] = ""
        import openai
        openai.api_key = ""
        ##########################################################

        response = completion(
            model="gpt-3.5-turbo",
            messages=messages,
            temperature=0.5,
            top_p=0.1,
            max_tokens=10,
            user="ishaan_dev@berri.ai",
        )
        # Add any assertions here to check the response
        print(response)

        ###### reset environ key
        os.environ['OPENAI_API_KEY'] = litellm.api_key

        ##### unset litellm var
        litellm.api_key = None
    except Timeout as e: 
        pass
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")

# test_completion_openai_litellm_key()

def test_completion_openrouter1():
    try:
        response = completion(
            model="openrouter/google/palm-2-chat-bison",
            messages=messages,
            max_tokens=5,
        )
        # Add any assertions here to check the response
        print(response)
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")
# test_completion_openrouter1() 

def test_completion_hf_model_no_provider():
    try:
        response = completion(
            model="WizardLM/WizardLM-70B-V1.0",
            messages=messages,
            max_tokens=5,
        )
        # Add any assertions here to check the response
        print(response)
        pytest.fail(f"Error occurred: {e}")
    except Exception as e:
        pass

# test_completion_hf_model_no_provider()

# def test_completion_openai_azure_with_functions():
#     function1 = [
#         {
#             "name": "get_current_weather",
#             "description": "Get the current weather in a given location",
#             "parameters": {
#                 "type": "object",
#                 "properties": {
#                     "location": {
#                         "type": "string",
#                         "description": "The city and state, e.g. San Francisco, CA",
#                     },
#                     "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
#                 },
#                 "required": ["location"],
#             },
#         }
#     ]
#     try:
#         messages = [{"role": "user", "content": "What is the weather like in Boston?"}]
#         response = completion(
#             model="azure/chatgpt-functioncalling", messages=messages, functions=function1
#         )
#         # Add any assertions here to check the response
#         print(response)
#     except Exception as e:
#         pytest.fail(f"Error occurred: {e}")
# test_completion_openai_azure_with_functions()

def test_completion_azure_key_completion_arg():
    # this tests if we can pass api_key to completion, when it's not in the env 
    # DO NOT REMOVE THIS TEST. No MATTER WHAT Happens. 
    # If you want to remove it, speak to Ishaan! 
    # Ishaan will be very disappointed if this test is removed -> this is a standard way to pass api_key + the router + proxy use this
    old_key = os.environ["AZURE_API_KEY"]
    os.environ.pop("AZURE_API_KEY", None)
    try:
        print("azure gpt-3.5 test\n\n")
        litellm.set_verbose=False
        ## Test azure call
        response = completion(
            model="azure/chatgpt-v-2",
            messages=messages,
            api_key=old_key,
            max_tokens=10,
        )
        print(f"response: {response}")
        os.environ["AZURE_API_KEY"] = old_key
    except Exception as e:
        os.environ["AZURE_API_KEY"] = old_key
        pytest.fail(f"Error occurred: {e}")
# test_completion_azure_key_completion_arg()


async def test_re_use_azure_async_client():
    try:
        print("azure gpt-3.5 ASYNC with clie nttest\n\n")
        litellm.set_verbose=True
        import openai
        client = openai.AsyncAzureOpenAI(
                azure_endpoint=os.environ['AZURE_API_BASE'],
                api_key=os.environ["AZURE_API_KEY"],
                api_version="2023-07-01-preview",
        )
        ## Test azure call
        for _ in range(3):
            response = await litellm.acompletion(
                model="azure/chatgpt-v-2",
                messages=messages,
                client=client
            )
            print(f"response: {response}")
    except Exception as e:
        pytest.fail("got Exception", e)

# import asyncio
# asyncio.run(
#     test_re_use_azure_async_client()
# )


def test_re_use_openaiClient():
    try:
        print("gpt-3.5  with client test\n\n")
        litellm.set_verbose=True
        import openai
        client = openai.OpenAI(
                api_key=os.environ["OPENAI_API_KEY"],
        )
        ## Test OpenAI call
        for _ in range(2):
            response = litellm.completion(
                model="gpt-3.5-turbo",
                messages=messages,
                client=client
            )
            print(f"response: {response}")
    except Exception as e:
        pytest.fail("got Exception", e)
# test_re_use_openaiClient()

def test_completion_azure():
    try:
        print("azure gpt-3.5 test\n\n")
        litellm.set_verbose=False
        ## Test azure call
        response = completion(
            model="azure/chatgpt-v-2",
            messages=messages,
            api_key="os.environ/AZURE_API_KEY"
        )
        print(f"response: {response}")
        ## Test azure flag for backwards compatibility
        # response = completion(
        #     model="chatgpt-v-2",
        #     messages=messages,
        #     azure=True,
        #     max_tokens=10
        # )
        # Add any assertions here to check the response
        print(response)

        cost = completion_cost(completion_response=response)
        print("Cost for azure completion request", cost)
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")

# test_completion_azure()

def test_azure_openai_ad_token():
    # this tests if the azure ad token is set in the request header
    # the request can fail since azure ad tokens expire after 30 mins, but the header MUST have the azure ad token
    # we use litellm.input_callbacks for this test
    def tester(    
        kwargs,                 # kwargs to completion
    ):
        print(kwargs["additional_args"])
        if kwargs["additional_args"]["headers"]["Authorization"] != 'Bearer gm':
            pytest.fail("AZURE AD TOKEN Passed but not set in request header")
        return
    litellm.input_callback = [tester]
    try:
        response = litellm.completion(
            model="azure/chatgpt-v-2",  # e.g. gpt-35-instant
            messages=[
                {
                    "role": "user",
                    "content": "what is your name",
                },
            ],
            azure_ad_token="gm"
        )
        print("azure ad token respoonse\n")
        print(response)
        litellm.input_callback = []
    except:
        litellm.input_callback = []
        pass
# test_azure_openai_ad_token()


# test_completion_azure()
def test_completion_azure2():
    # test if we can pass api_base, api_version and api_key in compleition()
    try:
        print("azure gpt-3.5 test\n\n")
        litellm.set_verbose=False
        api_base = os.environ["AZURE_API_BASE"]
        api_key = os.environ["AZURE_API_KEY"]
        api_version = os.environ["AZURE_API_VERSION"]

        os.environ["AZURE_API_BASE"] = ""
        os.environ["AZURE_API_VERSION"] = ""
        os.environ["AZURE_API_KEY"] = ""


        ## Test azure call
        response = completion(
            model="azure/chatgpt-v-2",
            messages=messages,
            api_base = api_base,
            api_key = api_key,
            api_version = api_version,
            max_tokens=10,
        )

        # Add any assertions here to check the response
        print(response)

        os.environ["AZURE_API_BASE"] = api_base
        os.environ["AZURE_API_VERSION"] = api_version
        os.environ["AZURE_API_KEY"] = api_key

    except Exception as e:
        pytest.fail(f"Error occurred: {e}")

# test_completion_azure2()

def test_completion_azure3():
    # test if we can pass api_base, api_version and api_key in compleition()
    try:
        print("azure gpt-3.5 test\n\n")
        litellm.set_verbose=True
        litellm.api_base = os.environ["AZURE_API_BASE"]
        litellm.api_key = os.environ["AZURE_API_KEY"]
        litellm.api_version = os.environ["AZURE_API_VERSION"]

        os.environ["AZURE_API_BASE"] = ""
        os.environ["AZURE_API_VERSION"] = ""
        os.environ["AZURE_API_KEY"] = ""


        ## Test azure call
        response = completion(
            model="azure/chatgpt-v-2",
            messages=messages,
            max_tokens=10,
        )

        # Add any assertions here to check the response
        print(response)

        os.environ["AZURE_API_BASE"] = litellm.api_base
        os.environ["AZURE_API_VERSION"] = litellm.api_version
        os.environ["AZURE_API_KEY"] = litellm.api_key

    except Exception as e:
        pytest.fail(f"Error occurred: {e}")
# test_completion_azure3()

# new azure test for using litellm. vars, 
# use the following vars in this test and make an azure_api_call
#  litellm.api_type = self.azure_api_type 
#  litellm.api_base = self.azure_api_base 
#  litellm.api_version = self.azure_api_version 
#  litellm.api_key = self.api_key 
def test_completion_azure_with_litellm_key():
    try:
        print("azure gpt-3.5 test\n\n")
        import openai


        #### set litellm vars
        litellm.api_type = "azure"
        litellm.api_base = os.environ['AZURE_API_BASE']
        litellm.api_version = os.environ['AZURE_API_VERSION']
        litellm.api_key = os.environ['AZURE_API_KEY']

        ######### UNSET ENV VARs for this ################
        os.environ['AZURE_API_BASE'] = ""
        os.environ['AZURE_API_VERSION'] = ""
        os.environ['AZURE_API_KEY'] = ""

        ######### UNSET OpenAI vars for this ##############
        openai.api_type = ""
        openai.api_base = "gm"
        openai.api_version = "333"
        openai.api_key = "ymca"

        response = completion(
            model="azure/chatgpt-v-2",
            messages=messages,
        )
        # Add any assertions here to check the response
        print(response)


        ######### RESET ENV VARs for this ################
        os.environ['AZURE_API_BASE'] = litellm.api_base
        os.environ['AZURE_API_VERSION'] = litellm.api_version
        os.environ['AZURE_API_KEY'] = litellm.api_key

        ######### UNSET litellm vars
        litellm.api_type = None
        litellm.api_base = None
        litellm.api_version = None
        litellm.api_key = None

    except Exception as e:
        pytest.fail(f"Error occurred: {e}")
# test_completion_azure()


def test_completion_azure_deployment_id():
    try:
        litellm.set_verbose = True
        response = completion(
            deployment_id="chatgpt-v-2",
            model="gpt-3.5-turbo",
            messages=messages,
        )
        # Add any assertions here to check the response
        print(response)
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")
# test_completion_azure_deployment_id()

# Only works for local endpoint
# def test_completion_anthropic_openai_proxy():
#     try:
#         response = completion(
#             model="custom_openai/claude-2",
#             messages=messages,
#             api_base="http://0.0.0.0:8000"
#         )
#         # Add any assertions here to check the response
#         print(response)
#     except Exception as e:
#         pytest.fail(f"Error occurred: {e}")

# test_completion_anthropic_openai_proxy()

def test_completion_replicate_vicuna():
    print("TESTING REPLICATE")
    litellm.set_verbose=True
    model_name = "replicate/vicuna-13b:6282abe6a492de4145d7bb601023762212f9ddbbe78278bd6771c8b3b2f2a13b"
    try:
        response = completion(
            model=model_name, 
            messages=messages, 
            temperature=0.5,
            top_k=20,
            repetition_penalty=1,
            min_tokens=1,
            seed=-1,
            max_tokens=20,
        )
        print(response)
        # Add any assertions here to check the response
        response_str = response["choices"][0]["message"]["content"]
        print("RESPONSE STRING\n", response_str)
        if type(response_str) != str:
            pytest.fail(f"Error occurred: {e}")
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")
# test_completion_replicate_vicuna()
# commenting out - flaky test
# def test_completion_replicate_llama2_stream():
#     litellm.set_verbose=False
#     model_name = "replicate/meta/llama-2-7b-chat:13c3cdee13ee059ab779f0291d29054dab00a47dad8261375654de5540165fb0"
#     try:
#         response = completion(
#             model=model_name, 
#             messages=[
#                 {
#                     "role": "user",
#                     "content": "what is yc write 1 paragraph",
#                 }
#             ], 
#             stream=True,
#             max_tokens=20,
#             num_retries=3
#         )
#         print(f"response: {response}")
#         # Add any assertions here to check the response
#         complete_response = "" 
#         for i, chunk in enumerate(response):
#             complete_response += chunk.choices[0].delta["content"]
#             # if i == 0:
#             #     assert len(chunk.choices[0].delta["content"]) > 2
#             # print(chunk)
#         assert len(complete_response) > 5
#         print(f"complete_response: {complete_response}")
#     except Exception as e:
#         pytest.fail(f"Error occurred: {e}")
# test_completion_replicate_llama2_stream()

def test_replicate_custom_prompt_dict(): 
    litellm.set_verbose = True
    model_name = "replicate/meta/llama-2-7b-chat:13c3cdee13ee059ab779f0291d29054dab00a47dad8261375654de5540165fb0"
    litellm.register_prompt_template(
        model="replicate/meta/llama-2-7b-chat:13c3cdee13ee059ab779f0291d29054dab00a47dad8261375654de5540165fb0",
        initial_prompt_value="You are a good assistant", # [OPTIONAL]
        roles={
            "system": {
                "pre_message": "[INST] <<SYS>>\n", # [OPTIONAL]
                "post_message": "\n<</SYS>>\n [/INST]\n" # [OPTIONAL]
            },
            "user": { 
                "pre_message": "[INST] ", # [OPTIONAL]
                "post_message": " [/INST]" # [OPTIONAL]
            }, 
            "assistant": {
                "pre_message": "\n", # [OPTIONAL]
                "post_message": "\n" # [OPTIONAL]
            }
        },
        final_prompt_value="Now answer as best you can:" # [OPTIONAL]
    )
    response = completion(
            model=model_name, 
            messages=[
                {
                    "role": "user",
                    "content": "what is yc write 1 paragraph",
                }
            ],
            num_retries=3
    )
    print(f"response: {response}")
    litellm.custom_prompt_dict = {} # reset 

# test_replicate_custom_prompt_dict() 

# commenthing this out since we won't be always testing a custom replicate deployment
# def test_completion_replicate_deployments():
#     print("TESTING REPLICATE")
#     litellm.set_verbose=False
#     model_name = "replicate/deployments/ishaan-jaff/ishaan-mistral"
#     try:
#         response = completion(
#             model=model_name, 
#             messages=messages, 
#             temperature=0.5,
#             seed=-1,
#         )
#         print(response)
#         # Add any assertions here to check the response
#         response_str = response["choices"][0]["message"]["content"]
#         print("RESPONSE STRING\n", response_str)
#         if type(response_str) != str:
#             pytest.fail(f"Error occurred: {e}")
#     except Exception as e:
#         pytest.fail(f"Error occurred: {e}")
# test_completion_replicate_deployments()


######## Test TogetherAI ######## 
def test_completion_together_ai():
    model_name = "together_ai/togethercomputer/llama-2-70b-chat"
    try:
        response = completion(model=model_name, messages=messages, max_tokens=256, n=1, logger_fn=logger_fn)
        # Add any assertions here to check the response
        print(response)
        cost = completion_cost(completion_response=response)
        print("Cost for completion call together-computer/llama-2-70b: ", f"${float(cost):.10f}")
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")

# test_completion_together_ai()
def test_customprompt_together_ai():
    try:
        litellm.set_verbose = False
        litellm.num_retries = 0
        response = completion(
            model="together_ai/togethercomputer/llama-2-70b-chat",
            messages=messages, 
            roles={"system":{"pre_message":"<|im_start|>system\n", "post_message":"<|im_end|>"}, "assistant":{"pre_message":"<|im_start|>assistant\n","post_message":"<|im_end|>"}, "user":{"pre_message":"<|im_start|>user\n","post_message":"<|im_end|>"}}
        )
        print(response)
    except litellm.exceptions.Timeout as e:
        print(f"Timeout Error")
        litellm.num_retries = 3 # reset retries
        pass
    except Exception as e:
        print(f"ERROR TYPE {type(e)}")
        pytest.fail(f"Error occurred: {e}")

# test_customprompt_together_ai()

def test_completion_sagemaker():
    try:
        print("testing sagemaker")
        litellm.set_verbose=True
        response = completion(
            model="sagemaker/jumpstart-dft-meta-textgeneration-llama-2-7b", 
            messages=messages,
            temperature=0.2,
            max_tokens=80,
        )
        # Add any assertions here to check the response
        print(response)
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")
# test_completion_sagemaker() 

def test_completion_chat_sagemaker():
    try:
        print("testing sagemaker")
        litellm.set_verbose=True
        response = completion(
            model="sagemaker/jumpstart-dft-meta-textgeneration-llama-2-7b-f", 
            messages=messages,
            stream=True,
        )
        # Add any assertions here to check the response
        print(response)
        for chunk in response:
            print(chunk)
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")
# test_completion_chat_sagemaker()

def test_completion_bedrock_titan():
    try:
        response = completion(
            model="bedrock/amazon.titan-tg1-large", 
            messages=messages,
            temperature=0.2,
            max_tokens=200,
            top_p=0.8,
            logger_fn=logger_fn
        )
        # Add any assertions here to check the response
        print(response)
    except RateLimitError:
        pass
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")
# test_completion_bedrock_titan()

def test_completion_bedrock_claude():
    print("calling claude")
    try:
        response = completion(
            model="anthropic.claude-instant-v1", 
            messages=messages,
            max_tokens=10,
            temperature=0.1,
            logger_fn=logger_fn
        )
        # Add any assertions here to check the response
        print(response)
    except RateLimitError:
        pass
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")
# test_completion_bedrock_claude()

def test_completion_bedrock_cohere():
    print("calling bedrock cohere")
    litellm.set_verbose = True
    try:
        response = completion(
            model="bedrock/cohere.command-text-v14", 
            messages=[{"role": "user", "content": "hi"}],
            temperature=0.1,
            max_tokens=10,
            stream=True
        )
        # Add any assertions here to check the response
        print(response)
        for chunk in response:
            print(chunk)
    except RateLimitError:
        pass
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")
# test_completion_bedrock_cohere()


def test_completion_bedrock_claude_completion_auth():
    print("calling bedrock claude completion params auth")
    import os

    aws_access_key_id = os.environ["AWS_ACCESS_KEY_ID"]
    aws_secret_access_key = os.environ["AWS_SECRET_ACCESS_KEY"]
    aws_region_name = os.environ["AWS_REGION_NAME"]

    os.environ["AWS_ACCESS_KEY_ID"] = ""
    os.environ["AWS_SECRET_ACCESS_KEY"] = ""
    os.environ["AWS_REGION_NAME"] = ""


    try:
        response = completion(
            model="bedrock/anthropic.claude-instant-v1", 
            messages=messages,
            max_tokens=10,
            temperature=0.1,
            logger_fn=logger_fn,
            aws_access_key_id=aws_access_key_id,
            aws_secret_access_key=aws_secret_access_key,
            aws_region_name=aws_region_name,
        )
        # Add any assertions here to check the response
        print(response)

        os.environ["AWS_ACCESS_KEY_ID"] = aws_access_key_id
        os.environ["AWS_SECRET_ACCESS_KEY"] = aws_secret_access_key
        os.environ["AWS_REGION_NAME"] = aws_region_name
    except RateLimitError:
        pass
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")
# test_completion_bedrock_claude_completion_auth()

# def test_completion_bedrock_claude_external_client_auth():
#     print("calling bedrock claude external client auth")
#     import os

#     aws_access_key_id = os.environ["AWS_ACCESS_KEY_ID"]
#     aws_secret_access_key = os.environ["AWS_SECRET_ACCESS_KEY"]
#     aws_region_name = os.environ["AWS_REGION_NAME"]

#     os.environ["AWS_ACCESS_KEY_ID"] = ""
#     os.environ["AWS_SECRET_ACCESS_KEY"] = ""
#     os.environ["AWS_REGION_NAME"] = ""

#     try:
#         import boto3
#         bedrock = boto3.client(
#             service_name="bedrock-runtime",
#             region_name=aws_region_name,
#             aws_access_key_id=aws_access_key_id,
#             aws_secret_access_key=aws_secret_access_key,
#             endpoint_url=f"https://bedrock-runtime.{aws_region_name}.amazonaws.com"
#         )

#         response = completion(
#             model="bedrock/anthropic.claude-instant-v1",
#             messages=messages,
#             max_tokens=10,
#             temperature=0.1,
#             logger_fn=logger_fn,
#             aws_bedrock_client=bedrock,
#         )
#         # Add any assertions here to check the response
#         print(response)

#         os.environ["AWS_ACCESS_KEY_ID"] = aws_access_key_id
#         os.environ["AWS_SECRET_ACCESS_KEY"] = aws_secret_access_key
#         os.environ["AWS_REGION_NAME"] = aws_region_name
#     except RateLimitError:
#         pass
#     except Exception as e:
#         pytest.fail(f"Error occurred: {e}")
# test_completion_bedrock_claude_external_client_auth()

# def test_completion_bedrock_claude_stream():
#     print("calling claude")
#     litellm.set_verbose = False
#     try:
#         response = completion(
#             model="bedrock/anthropic.claude-instant-v1", 
#             messages=messages,
#             stream=True
#         )
#         # Add any assertions here to check the response
#         print(response)
#         for chunk in response:
#             print(chunk)
#     except RateLimitError:
#         pass
#     except Exception as e:
#         pytest.fail(f"Error occurred: {e}")
# test_completion_bedrock_claude_stream()

# def test_completion_bedrock_ai21():
#     try:
#         litellm.set_verbose = False
#         response = completion(
#             model="bedrock/ai21.j2-mid", 
#             messages=messages,
#             temperature=0.2,
#             top_p=0.2,
#             max_tokens=20
#         )
#         # Add any assertions here to check the response 
#         print(response)
#     except RateLimitError:
#         pass
#     except Exception as e:
#         pytest.fail(f"Error occurred: {e}")


######## Test VLLM ########
# def test_completion_vllm():
#     try:
#         response = completion(
#             model="vllm/facebook/opt-125m", 
#             messages=messages,
#             temperature=0.2,
#             max_tokens=80,
#         )
#         print(response)
#     except Exception as e:
#         pytest.fail(f"Error occurred: {e}")

# test_completion_vllm()

# def test_completion_hosted_chatCompletion():
#     # this tests calling a server where vllm is hosted
#     # this should make an openai.Completion() call to the specified api_base
#     # send a request to this proxy server: https://replit.com/@BerriAI/openai-proxy#main.py
#     # it checks if model == facebook/opt-125m and returns test passed
#     try:
#         litellm.set_verbose = True
#         response = completion(
#             model="facebook/opt-125m", 
#             messages=messages,
#             temperature=0.2,
#             max_tokens=80,
#             api_base="https://openai-proxy.berriai.repl.co",
#             custom_llm_provider="openai"
#         )
#         print(response)

#         if response['choices'][0]['message']['content'] != "passed":
#             # see https://replit.com/@BerriAI/openai-proxy#main.py
#             pytest.fail(f"Error occurred: proxy server did not respond")
#     except Exception as e:
#         pytest.fail(f"Error occurred: {e}")

# test_completion_hosted_chatCompletion()

# def test_completion_custom_api_base():
#     try:
#         response = completion(
#             model="custom/meta-llama/Llama-2-13b-hf", 
#             messages=messages,
#             temperature=0.2,
#             max_tokens=10,
#             api_base="https://api.autoai.dev/inference",
#             request_timeout=300,
#         )
#         # Add any assertions here to check the response
#         print("got response\n", response)
#     except Exception as e:
#         pytest.fail(f"Error occurred: {e}")

# test_completion_custom_api_base()

# def test_vertex_ai():
#     test_models = ["codechat-bison"] + litellm.vertex_chat_models + litellm.vertex_code_chat_models + litellm.vertex_text_models + litellm.vertex_code_text_models
#     # test_models = ["chat-bison"]
#     for model in test_models:
#         try:
#             if model in ["code-gecko@001", "code-gecko@latest"]:
#                 # our account does not have access to this model
#                 continue
#             print("making request", model)
#             response = completion(model=model, messages=[{'role': 'user', 'content': 'hi'}])
#             print(response)

#             print(response.usage.completion_tokens)
#             print(response['usage']['completion_tokens'])
#             assert type(response.choices[0].message.content) == str
#         except Exception as e:
#             pytest.fail(f"Error occurred: {e}")
# test_vertex_ai()

# def test_vertex_ai_stream():
#     litellm.set_verbose=False
#     test_models = litellm.vertex_chat_models + litellm.vertex_code_chat_models + litellm.vertex_text_models + litellm.vertex_code_text_models
#     for model in test_models:
#         try:
#             if model in ["code-gecko@001", "code-gecko@latest"]:
#                 # our account does not have access to this model
#                 continue
#             print("making request", model)
#             response = completion(model=model, messages=[{"role": "user", "content": "write 100 line code code for saying hi"}], stream=True)
#             for chunk in response:
#                 print(chunk)
#                 # pass
#         except Exception as e:
#             pytest.fail(f"Error occurred: {e}")
# test_vertex_ai_stream() 


def test_completion_with_fallbacks():
    print(f"RUNNING TEST COMPLETION WITH FALLBACKS -  test_completion_with_fallbacks")
    fallbacks = ["gpt-3.5-turbo", "gpt-3.5-turbo", "command-nightly"]
    try:
        response = completion(
            model="bad-model", messages=messages, force_timeout=120, fallbacks=fallbacks
        )
        # Add any assertions here to check the response
        print(response)
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")

# test_completion_with_fallbacks()
def test_completion_anyscale_api():
    try:
        # litellm.set_verbose=True
        messages=[{
            "role": "system", 
            "content": "You're a good bot"
        },{
            "role": "user", 
            "content": "Hey", 
        },{
            "role": "user", 
            "content": "Hey", 
        }]
        response = completion(
            model="anyscale/meta-llama/Llama-2-7b-chat-hf", 
            messages=messages,)
        print(response)
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")

# test_completion_anyscale_api()

def test_azure_cloudflare_api(): 
    try: 
        messages = [
                {
                    "role": "user",
                    "content": "How do I output all files in a directory using Python?",
                },
            ]
        response = completion(model="azure/gpt-turbo", messages=messages, base_url=os.getenv("CLOUDFLARE_AZURE_BASE_URL"), api_key=os.getenv("AZURE_FRANCE_API_KEY"))
        print(f"response: {response}")
    except Exception as e: 
        traceback.print_exc()
        pass

# test_azure_cloudflare_api() 

def test_completion_anyscale_2():
    try:
        # litellm.set_verbose=True
        messages=[{
            "role": "system", 
            "content": "You're a good bot"
        },{
            "role": "user", 
            "content": "Hey", 
        },{
            "role": "user", 
            "content": "Hey", 
        }]
        response = completion(
            model="anyscale/meta-llama/Llama-2-7b-chat-hf", 
            messages=messages
        )
        print(response)
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")

def test_mistral_anyscale_stream():
    litellm.set_verbose=False
    response = completion(
        model = 'anyscale/mistralai/Mistral-7B-Instruct-v0.1', 
        messages = [{ "content": "hello, good morning","role": "user"}],
        stream=True,
    )
    for chunk in response:
        # print(chunk)
        print(chunk["choices"][0]["delta"].get("content", ""), end="")
# test_mistral_anyscale_stream()
# test_completion_anyscale_2()
# def test_completion_with_fallbacks_multiple_keys():
#     print(f"backup key 1: {os.getenv('BACKUP_OPENAI_API_KEY_1')}")
#     print(f"backup key 2: {os.getenv('BACKUP_OPENAI_API_KEY_2')}")
#     backup_keys = [{"api_key": os.getenv("BACKUP_OPENAI_API_KEY_1")}, {"api_key": os.getenv("BACKUP_OPENAI_API_KEY_2")}]
#     try:
#         api_key = "bad-key"
#         response = completion(
#             model="gpt-3.5-turbo", messages=messages, force_timeout=120, fallbacks=backup_keys, api_key=api_key
#         )
#         # Add any assertions here to check the response
#         print(response)
#     except Exception as e:
#         error_str = traceback.format_exc()
#         pytest.fail(f"Error occurred: {error_str}")

# test_completion_with_fallbacks_multiple_keys() 
# def test_petals():
#     try:
#         response = completion(model="petals-team/StableBeluga2", messages=messages)
#         # Add any assertions here to check the response
#         print(response)

#         response = completion(model="petals-team/StableBeluga2", messages=messages)
#         # Add any assertions here to check the response
#         print(response)
#     except Exception as e:
#         pytest.fail(f"Error occurred: {e}")

# def test_baseten():
#     try:

#         response = completion(model="baseten/7qQNLDB", messages=messages, logger_fn=logger_fn)
#         # Add any assertions here to check the response
#         print(response)
#     except Exception as e:
#         pytest.fail(f"Error occurred: {e}")

# test_baseten()
# def test_baseten_falcon_7bcompletion():
#     model_name = "qvv0xeq"
#     try:
#         response = completion(model=model_name, messages=messages, custom_llm_provider="baseten")
#         # Add any assertions here to check the response
#         print(response)
#     except Exception as e:
#         pytest.fail(f"Error occurred: {e}")
# test_baseten_falcon_7bcompletion()

# def test_baseten_falcon_7bcompletion_withbase():
#     model_name = "qvv0xeq"
#     litellm.api_base = "https://app.baseten.co"
#     try:
#         response = completion(model=model_name, messages=messages)
#         # Add any assertions here to check the response
#         print(response)
#     except Exception as e:
#         pytest.fail(f"Error occurred: {e}")
#     litellm.api_base = None

# test_baseten_falcon_7bcompletion_withbase()


# def test_baseten_wizardLMcompletion_withbase():
#     model_name = "q841o8w"
#     litellm.api_base = "https://app.baseten.co"
#     try:
#         response = completion(model=model_name, messages=messages)
#         # Add any assertions here to check the response
#         print(response)
#     except Exception as e:
#         pytest.fail(f"Error occurred: {e}")

# test_baseten_wizardLMcompletion_withbase()

# def test_baseten_mosaic_ML_completion_withbase():
#     model_name = "31dxrj3"
#     litellm.api_base = "https://app.baseten.co"
#     try:
#         response = completion(model=model_name, messages=messages)
#         # Add any assertions here to check the response
#         print(response)
#     except Exception as e:
#         pytest.fail(f"Error occurred: {e}")


#### Test A121 ###################
def test_completion_ai21():
    print("running ai21 j2light test")
    litellm.set_verbose=True
    model_name = "j2-light"
    try:
        response = completion(model=model_name, messages=messages, max_tokens=100, temperature=0.8)
        # Add any assertions here to check the response
        print(response)
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")

# test_completion_ai21()
# test_completion_ai21()
## test deep infra 
def test_completion_deep_infra():
    litellm.set_verbose = False
    model_name = "deepinfra/meta-llama/Llama-2-70b-chat-hf"
    try:
        response = completion(
            model=model_name, 
            messages=messages,
            temperature=0,
            max_tokens=10
        )
        # Add any assertions here to check the response
        print(response)
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")
# test_completion_deep_infra()

def test_completion_deep_infra_mistral():
    print("deep infra test with temp=0")
    model_name = "deepinfra/mistralai/Mistral-7B-Instruct-v0.1"
    try:
        response = completion(
            model=model_name, 
            messages=messages,
            temperature=0.01, # mistrail fails with temperature=0
            max_tokens=10
        )
        # Add any assertions here to check the response
        print(response)
    except litellm.exceptions.Timeout as e: 
        pass
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")
# test_completion_deep_infra_mistral()

# Palm tests
def test_completion_palm():
    litellm.set_verbose = True
    model_name = "palm/chat-bison"
    messages = [{"role": "user", "content": "Hey, how's it going?"}]
    try:
        response = completion(model=model_name, messages=messages)
        # Add any assertions here to check the response
        print(response)
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")
# test_completion_palm()

# test palm with streaming
def test_completion_palm_stream():
    # litellm.set_verbose = True
    model_name = "palm/chat-bison"
    try:
        response = completion(
            model=model_name, 
            messages=messages,
            stop=["stop"],
            stream=True,
            max_tokens=20
        )
        # Add any assertions here to check the response
        for chunk in response:
            print(chunk)
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")
# test_completion_palm_stream()

# test_completion_deep_infra()
# test_completion_ai21()
# test config file with completion #
# def test_completion_openai_config():
#     try:
#         litellm.config_path = "../config.json"
#         litellm.set_verbose = True
#         response = litellm.config_completion(messages=messages)
#         # Add any assertions here to check the response
#         print(response)
#         litellm.config_path = None
#     except Exception as e:
#         pytest.fail(f"Error occurred: {e}")


# def test_maritalk():
#     messages = [{"role": "user", "content": "Hey"}]
#     try:
#         response = completion("maritalk", messages=messages)
#         print(f"response: {response}")
#     except Exception as e:
#         pytest.fail(f"Error occurred: {e}")
# test_maritalk()

def test_completion_together_ai_stream():
    user_message = "Write 1pg about YC & litellm"
    messages = [{ "content": user_message,"role": "user"}]
    try:
        response = completion(
            model="together_ai/togethercomputer/llama-2-70b-chat", 
            messages=messages, stream=True, 
            max_tokens=5
        )
        print(response)
        for chunk in response:
            print(chunk)
        # print(string_response)
    except Exception as e:
        pytest.fail(f"Error occurred: {e}")
# test_completion_together_ai_stream()


# async def get_response(generator):
#     async for elem in generator:
#         print(elem)
#     return

# test_completion_together_ai_stream()

def test_moderation():
    import openai
    openai.api_type = "azure" 
    openai.api_version = "GM"
    response = litellm.moderation(input="i'm ishaan cto of litellm")   
    print(response)
    output = response.results[0]
    print(output)
    return output

# test_moderation()