File size: 66,720 Bytes
6ecf14b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "\n",
    "# Use Watsonx to respond to natural language questions using RAG approach for Doctor AI"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "\n",
    "\n",
    "#### About Retrieval Augmented Generation\n",
    "Retrieval Augmented Generation (RAG) is a versatile pattern that can unlock a number of use cases requiring factual recall of information, such as querying a knowledge base in natural language.\n",
    "\n",
    "In its simplest form, RAG requires 3 steps:\n",
    "\n",
    "- Index knowledge base passages (once)\n",
    "- Retrieve relevant passage(s) from the knowledge base (for every user query)\n",
    "- Generate a response by feeding retrieved passage into a large language model (for every user query)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "<a id=\"setup\"></a>\n",
    "##  Set up the environment"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "### Install and import dependecies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "#!pip install chromadb==0.3.27\n",
    "#!pip install sentence_transformers \n",
    "#!pip install pandas \n",
    "#!pip install rouge_score \n",
    "#!pip install nltk\n",
    "#!pip install \"ibm-watson-machine-learning>=1.0.312\" "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Note:** Please restart the notebook kernel to pick up proper version of packages installed above."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "import os, getpass\n",
    "import pandas as pd\n",
    "from typing import Optional, Dict, Any, Iterable, List\n",
    "\n",
    "try:\n",
    "    from sentence_transformers import SentenceTransformer\n",
    "except ImportError:\n",
    "    raise ImportError(\"Could not import sentence_transformers: Please install sentence-transformers package.\")\n",
    "    \n",
    "try:\n",
    "    import chromadb\n",
    "    from chromadb.api.types import EmbeddingFunction\n",
    "except ImportError:\n",
    "    raise ImportError(\"Could not import chromdb: Please install chromadb package.\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "### Watsonx API connection\n",
    "This cell defines the credentials required to work with watsonx API for Foundation\n",
    "Model inferencing.\n",
    "\n",
    "**Action:** Provide the IBM Cloud user API key. For details, see\n",
    "[documentation](https://cloud.ibm.com/docs/account?topic=account-userapikey&interface=ui)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Python program to read\n",
    "# json file\n",
    "import json\n",
    "# Opening JSON file\n",
    "f = open('./credentials/api.json')\n",
    "# returns JSON object as\n",
    "# a dictionary\n",
    "data = json.load(f)\n",
    "# Ensure you have your API key set in your environment\n",
    "#in ./credentials/api.json\n",
    "IBM_CLOUD_API = data['IBM_CLOUD_API']\n",
    "PROJECT_ID = data['PROJECT_ID']\n",
    "# Closing file\n",
    "f.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "credentials = {\n",
    "    \"url\": \"https://us-south.ml.cloud.ibm.com\",\n",
    "    \"apikey\": IBM_CLOUD_API\n",
    "}"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "### Defining the project id\n",
    "The API requires project id that provides the context for the call. We will obtain the id from the project in which this notebook runs. Otherwise, please provide the project id.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "try:\n",
    "    project_id = os.environ[\"PROJECT_ID\"]\n",
    "except KeyError:\n",
    "    project_id = PROJECT_ID"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "<a id=\"data\"></a>\n",
    "## Train data loading"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "Load train and test datasets. At first, training dataset (`train_data`) should be used to work with the models to prepare and tune prompt. Then, test dataset (`test_data`) should be used to calculate the metrics score for selected model, defined prompts and parameters."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "# imports\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "# load data\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "filename_data = \"../2-Data/dialogues_embededd.pkl\"\n",
    "data =  pd.read_pickle(filename_data)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "#data = data.reset_index()\n",
    "#data.rename(columns = {'index':'ids'}, inplace = True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_data, test_data= train_test_split(data, test_size=0.05)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(950, 6)"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_data.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(50, 6)"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_data.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "## Build up knowledge base\n",
    "\n",
    "The current state-of-the-art in RAG is to create dense vector representations of the knowledge base in order to calculate the semantic similarity to a given user query.\n",
    "\n",
    "We can generate dense vector representations using embedding models. In this notebook, we use [SentenceTransformers](https://www.google.com/search?client=safari&rls=en&q=sentencetransformers&ie=UTF-8&oe=UTF-8) [all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) to embed both the knowledge base passages and user queries. `all-MiniLM-L6-v2` is a performant open-source model that is small enough to run locally.\n",
    "\n",
    "A vector database is optimized for dense vector indexing and retrieval. This notebook uses [Chroma](https://docs.trychroma.com), a user-friendly open-source vector database, licensed under Apache 2.0, which offers good speed and performance with all-MiniLM-L6-v2 embedding model."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "The dataset we are using is already split into self-contained passages that can be ingested by Chroma. \n",
    "\n",
    "The size of each passage is limited by the embedding model's context window (which is 256 tokens for `all-MiniLM-L6-v2`)."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Load knowledge base documents\n",
    "\n",
    "Load set of documents used further to build knowledge base. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "data_root = \"../2-Data/\"\n",
    "knowledge_base_dir = f\"{data_root}/knowledge_base\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'../2-Data//knowledge_base'"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "knowledge_base_dir"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "#if not os.path.exists(knowledge_base_dir):\n",
    "#    from zipfile import ZipFile\n",
    "#    with ZipFile(knowledge_base_dir + \".zip\", 'r') as zObject:\n",
    "#        zObject.extractall(data_root)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "#documents = pd.read_csv(f\"{knowledge_base_dir}/psgs.tsv\", sep='\\t', header=0)\n",
    "#documents['indextext'] = documents['title'].astype(str) + \"\\n\" + documents['text']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Question</th>\n",
       "      <th>Patient</th>\n",
       "      <th>Answer</th>\n",
       "      <th>combined</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Q. What does abutment of the nerve root mean?</td>\n",
       "      <td>Hi doctor,I am just wondering what is abutting...</td>\n",
       "      <td>Hi. I have gone through your query with dilige...</td>\n",
       "      <td>Question: Q. What does abutment of the nerve r...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Q. What should I do to reduce my weight gained...</td>\n",
       "      <td>Hi doctor, I am a 22-year-old female who was d...</td>\n",
       "      <td>Hi. You have really done well with the hypothy...</td>\n",
       "      <td>Question: Q. What should I do to reduce my wei...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                            Question  \\\n",
       "0      Q. What does abutment of the nerve root mean?   \n",
       "1  Q. What should I do to reduce my weight gained...   \n",
       "\n",
       "                                             Patient  \\\n",
       "0  Hi doctor,I am just wondering what is abutting...   \n",
       "1  Hi doctor, I am a 22-year-old female who was d...   \n",
       "\n",
       "                                              Answer  \\\n",
       "0  Hi. I have gone through your query with dilige...   \n",
       "1  Hi. You have really done well with the hypothy...   \n",
       "\n",
       "                                            combined  \n",
       "0  Question: Q. What does abutment of the nerve r...  \n",
       "1  Question: Q. What should I do to reduce my wei...  "
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# load & inspect dataset\n",
    "df = pd.read_csv(\"../2-Data/dialogues.csv\", sep = '\\t')\n",
    "df = df.dropna()#.head(1000)\n",
    "df.rename(columns = {'Description':'Question',\"Doctor\":\"Answer\"}, inplace = True)\n",
    "#df[\"case\"] = (\" Patient: \" + df.Patient.str.strip()+ \"\\n\" + \"Question: \" + df.Question.str.strip() +)\n",
    "#df[\"combined\"] = (\"Question: \" + df.Question.str.strip() + \"\\n\" +\" Patient: \" + df.Patient.str.strip()+  \"\\n\" +\" Answer: \" + df.Answer.str.strip())\n",
    "\n",
    "df[\"combined\"] = (\"Question: \" + df.Question.str.strip() + \"\\n\" +\" Answer: \" + df.Answer.str.strip())\n",
    "\n",
    "df.head(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(256916, 4)"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "df =df.drop_duplicates()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(246538, 4)"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.reset_index()\n",
    "df.rename(columns = {'index':'ids'}, inplace = True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "documents=df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(246538, 5)"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "documents.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>ids</th>\n",
       "      <th>Question</th>\n",
       "      <th>Patient</th>\n",
       "      <th>Answer</th>\n",
       "      <th>combined</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>Q. What does abutment of the nerve root mean?</td>\n",
       "      <td>Hi doctor,I am just wondering what is abutting...</td>\n",
       "      <td>Hi. I have gone through your query with dilige...</td>\n",
       "      <td>Question: Q. What does abutment of the nerve r...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>Q. What should I do to reduce my weight gained...</td>\n",
       "      <td>Hi doctor, I am a 22-year-old female who was d...</td>\n",
       "      <td>Hi. You have really done well with the hypothy...</td>\n",
       "      <td>Question: Q. What should I do to reduce my wei...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>Q. I have started to get lots of acne on my fa...</td>\n",
       "      <td>Hi doctor! I used to have clear skin but since...</td>\n",
       "      <td>Hi there Acne has multifactorial etiology. Onl...</td>\n",
       "      <td>Question: Q. I have started to get lots of acn...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>Q. Why do I have uncomfortable feeling between...</td>\n",
       "      <td>Hello doctor,I am having an uncomfortable feel...</td>\n",
       "      <td>Hello. The popping and discomfort what you fel...</td>\n",
       "      <td>Question: Q. Why do I have uncomfortable feeli...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>Q. My symptoms after intercourse threatns me e...</td>\n",
       "      <td>Hello doctor,Before two years had sex with a c...</td>\n",
       "      <td>Hello. The HIV test uses a finger prick blood ...</td>\n",
       "      <td>Question: Q. My symptoms after intercourse thr...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>246533</th>\n",
       "      <td>256911</td>\n",
       "      <td>Why is hair fall increasing while using Bontre...</td>\n",
       "      <td>I am suffering from excessive hairfall. My doc...</td>\n",
       "      <td>Hello Dear Thanks for writing to us, we are he...</td>\n",
       "      <td>Question: Why is hair fall increasing while us...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>246534</th>\n",
       "      <td>256912</td>\n",
       "      <td>Why was I asked to discontinue Androanagen whi...</td>\n",
       "      <td>Hi Doctor, I have been having severe hair fall...</td>\n",
       "      <td>hello,        hair4u is combination of minoxid...</td>\n",
       "      <td>Question: Why was I asked to discontinue Andro...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>246535</th>\n",
       "      <td>256913</td>\n",
       "      <td>Can Mintop 5% Lotion be used by women for seve...</td>\n",
       "      <td>Hi..i hav sever hair loss problem so consulted...</td>\n",
       "      <td>HI  I have evaluated your query thoroughly you...</td>\n",
       "      <td>Question: Can Mintop 5% Lotion be used by wome...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>246536</th>\n",
       "      <td>256914</td>\n",
       "      <td>Is Minoxin 5% lotion advisable instead of Foli...</td>\n",
       "      <td>Hi, i am 25 year old girl, i am having massive...</td>\n",
       "      <td>Hello and Welcome to ‘Ask A Doctor’ service.I ...</td>\n",
       "      <td>Question: Is Minoxin 5% lotion advisable inste...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>246537</th>\n",
       "      <td>256915</td>\n",
       "      <td>Are Biotin supplements need to reduce severe h...</td>\n",
       "      <td>iam having hairfall for a decade.. but fews we...</td>\n",
       "      <td>you did'nt mention about thyroid problem ...us...</td>\n",
       "      <td>Question: Are Biotin supplements need to reduc...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>246538 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "           ids                                           Question  \\\n",
       "0            0      Q. What does abutment of the nerve root mean?   \n",
       "1            1  Q. What should I do to reduce my weight gained...   \n",
       "2            2  Q. I have started to get lots of acne on my fa...   \n",
       "3            3  Q. Why do I have uncomfortable feeling between...   \n",
       "4            4  Q. My symptoms after intercourse threatns me e...   \n",
       "...        ...                                                ...   \n",
       "246533  256911  Why is hair fall increasing while using Bontre...   \n",
       "246534  256912  Why was I asked to discontinue Androanagen whi...   \n",
       "246535  256913  Can Mintop 5% Lotion be used by women for seve...   \n",
       "246536  256914  Is Minoxin 5% lotion advisable instead of Foli...   \n",
       "246537  256915  Are Biotin supplements need to reduce severe h...   \n",
       "\n",
       "                                                  Patient  \\\n",
       "0       Hi doctor,I am just wondering what is abutting...   \n",
       "1       Hi doctor, I am a 22-year-old female who was d...   \n",
       "2       Hi doctor! I used to have clear skin but since...   \n",
       "3       Hello doctor,I am having an uncomfortable feel...   \n",
       "4       Hello doctor,Before two years had sex with a c...   \n",
       "...                                                   ...   \n",
       "246533  I am suffering from excessive hairfall. My doc...   \n",
       "246534  Hi Doctor, I have been having severe hair fall...   \n",
       "246535  Hi..i hav sever hair loss problem so consulted...   \n",
       "246536  Hi, i am 25 year old girl, i am having massive...   \n",
       "246537  iam having hairfall for a decade.. but fews we...   \n",
       "\n",
       "                                                   Answer  \\\n",
       "0       Hi. I have gone through your query with dilige...   \n",
       "1       Hi. You have really done well with the hypothy...   \n",
       "2       Hi there Acne has multifactorial etiology. Onl...   \n",
       "3       Hello. The popping and discomfort what you fel...   \n",
       "4       Hello. The HIV test uses a finger prick blood ...   \n",
       "...                                                   ...   \n",
       "246533  Hello Dear Thanks for writing to us, we are he...   \n",
       "246534  hello,        hair4u is combination of minoxid...   \n",
       "246535  HI  I have evaluated your query thoroughly you...   \n",
       "246536  Hello and Welcome to ‘Ask A Doctor’ service.I ...   \n",
       "246537  you did'nt mention about thyroid problem ...us...   \n",
       "\n",
       "                                                 combined  \n",
       "0       Question: Q. What does abutment of the nerve r...  \n",
       "1       Question: Q. What should I do to reduce my wei...  \n",
       "2       Question: Q. I have started to get lots of acn...  \n",
       "3       Question: Q. Why do I have uncomfortable feeli...  \n",
       "4       Question: Q. My symptoms after intercourse thr...  \n",
       "...                                                   ...  \n",
       "246533  Question: Why is hair fall increasing while us...  \n",
       "246534  Question: Why was I asked to discontinue Andro...  \n",
       "246535  Question: Can Mintop 5% Lotion be used by wome...  \n",
       "246536  Question: Is Minoxin 5% lotion advisable inste...  \n",
       "246537  Question: Are Biotin supplements need to reduc...  \n",
       "\n",
       "[246538 rows x 5 columns]"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "documents"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "documents=documents.head(2000)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(2000, 5)"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "documents.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "### Create an embedding function\n",
    "\n",
    "Note that you can feed a custom embedding function to be used by chromadb. The performance of chromadb may differ depending on the embedding model used."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "class MiniLML6V2EmbeddingFunction(EmbeddingFunction):\n",
    "    MODEL = SentenceTransformer('all-MiniLM-L6-v2')\n",
    "    def __call__(self, texts):\n",
    "        return MiniLML6V2EmbeddingFunction.MODEL.encode(texts).tolist()\n",
    "emb_func = MiniLML6V2EmbeddingFunction()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "### Set up Chroma upsert\n",
    "\n",
    "Upserting a document means update the document even if it exists in the database. Otherwise re-inserting a document throws an error. This is useful for experimentation purpose."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "class ChromaWithUpsert:\n",
    "    def __init__(\n",
    "            self,\n",
    "            name: Optional[str] = \"watsonx_rag_collection\",\n",
    "            persist_directory:Optional[str]=None,\n",
    "            embedding_function: Optional[EmbeddingFunction]=None,\n",
    "            collection_metadata: Optional[Dict] = None,\n",
    "    ):\n",
    "        self._client_settings = chromadb.config.Settings()\n",
    "        if persist_directory is not None:\n",
    "            self._client_settings = chromadb.config.Settings(\n",
    "                chroma_db_impl=\"duckdb+parquet\",\n",
    "                persist_directory=persist_directory,\n",
    "            )\n",
    "        self._client = chromadb.Client(self._client_settings)\n",
    "        self._embedding_function = embedding_function\n",
    "        self._persist_directory = persist_directory\n",
    "        self._name = name\n",
    "        self._collection = self._client.get_or_create_collection(\n",
    "            name=self._name,\n",
    "            embedding_function=self._embedding_function\n",
    "            if self._embedding_function is not None\n",
    "            else None,\n",
    "            metadata=collection_metadata,\n",
    "        )\n",
    "\n",
    "    def upsert_texts(\n",
    "        self,\n",
    "        texts: Iterable[str],\n",
    "        metadata: Optional[List[dict]] = None,\n",
    "        ids: Optional[List[str]] = None,\n",
    "        **kwargs: Any,\n",
    "    ) -> List[str]:\n",
    "        \"\"\"Run more texts through the embeddings and add to the vectorstore.\n",
    "        Args:\n",
    "            :param texts (Iterable[str]): Texts to add to the vectorstore.\n",
    "            :param metadatas (Optional[List[dict]], optional): Optional list of metadatas.\n",
    "            :param ids (Optional[List[str]], optional): Optional list of IDs.\n",
    "            :param metadata: Optional[List[dict]] - optional metadata (such as title, etc.)\n",
    "        Returns:\n",
    "            List[str]: List of IDs of the added texts.\n",
    "        \"\"\"\n",
    "        # TODO: Handle the case where the user doesn't provide ids on the Collection\n",
    "        if ids is None:\n",
    "            import uuid\n",
    "            ids = [str(uuid.uuid1()) for _ in texts]\n",
    "        embeddings = None\n",
    "        self._collection.upsert(\n",
    "            metadatas=metadata, documents=texts, ids=ids\n",
    "        )\n",
    "        return ids\n",
    "\n",
    "    def is_empty(self):\n",
    "        return self._collection.count()==0\n",
    "\n",
    "    def persist(self):\n",
    "        self._client.persist()\n",
    "\n",
    "    def query(self, query_texts:str, n_results:int=5):\n",
    "        \"\"\"\n",
    "        Returns the closests vector to the question vector\n",
    "        :param query_texts: the question\n",
    "        :param n_results: number of results to generate\n",
    "        :return: the closest result to the given question\n",
    "        \"\"\"\n",
    "        return self._collection.query(query_texts=query_texts, n_results=n_results)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: total: 93.8 ms\n",
      "Wall time: 93 ms\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "chroma = ChromaWithUpsert(\n",
    "    name=f\"nq910_minilm6v2\",\n",
    "    embedding_function=emb_func,  # you can have something here using /embed endpoint\n",
    "    persist_directory=knowledge_base_dir,\n",
    ")\n",
    "if chroma.is_empty():\n",
    "    _ = chroma.upsert_texts(\n",
    "        texts=documents.combined.tolist(),\n",
    "        # we handle tokenization, embedding, and indexing automatically. \n",
    "        #You can skip that and add your own embeddings as well\n",
    "        metadata=[{'Question': Question,\n",
    "                   'Patient':Patient,\n",
    "                   'ids': ids}\n",
    "                  for (Question,Patient,ids) in\n",
    "                  zip(documents.Question,documents.Patient, documents.ids)],  # filter on these!\n",
    "        ids=[str(i) for i in documents.ids],  # unique for each doc\n",
    "    )\n",
    "    chroma.persist()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "### Embed and index documents with Chroma\n",
    "\n",
    "**Note: Could take several minutes if you don't have pre-built indices**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: total: 20.1 s\n",
      "Wall time: 16.3 s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "chroma = ChromaWithUpsert(\n",
    "    name=f\"nq910_minilm6v2\",\n",
    "    embedding_function=emb_func,  # you can have something here using /embed endpoint\n",
    "    persist_directory=knowledge_base_dir,\n",
    ")\n",
    "if chroma.is_empty():\n",
    "    _ = chroma.upsert_texts(\n",
    "        texts=documents.combined.tolist(),\n",
    "        # we handle tokenization, embedding, and indexing automatically. \n",
    "        #You can skip that and add your own embeddings as well\n",
    "        metadata=[{'Question': Question, \n",
    "                   'ids': ids}\n",
    "                  for (Question,ids) in\n",
    "                  zip(documents.Question, documents.ids)],  # filter on these!\n",
    "        ids=[str(i) for i in documents.ids],  # unique for each doc\n",
    "    )\n",
    "    chroma.persist()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "<a id=\"models\"></a>\n",
    "## Foundation Models on Watsonx"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "You need to specify `model_id` that will be used for inferencing."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "**Action**: Use `FLAN_UL2` model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "from ibm_watson_machine_learning.foundation_models.utils.enums import ModelTypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "model_id = ModelTypes.FLAN_UL2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "<a id=\"predict\"></a>\n",
    "## Generate a retrieval-augmented response to a question"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "### Select questions\n",
    "\n",
    "Get questions from the previously loaded test dataset."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Q. Every time I eat spicy food, I poop blood. Why?\n",
      "Q. Will Kalarchikai cure multiple ovarian cysts in PCOD?\n",
      "Q. Please enlighten me on non-invasive procedures to detect prostate cancer.?\n",
      "Q. My sciatica is heavy after a minor herniated disc L4 or L5. Why?\n",
      "Q. I feel as if the skin over my belly button is firm. Is it hernia?\n",
      "Q. A white patch has been formed at the tip of the penis associated with skin tightness. Why?\n",
      "Q. I masturbate only by rubbing the tip of the penis. Is it a wrong way?\n",
      "Q. Every time I eat spicy food, I poop blood. Why?\n",
      "Q. Please provide opinion on my complete blood count report.?\n",
      "Q. My child got hurt while playing. Can we use T-Bact or Neosporin ointment?\n",
      "Q. Please comment on the severity of my wife's wrist x-ray.?\n",
      "Q. Why am I having extreme bloating, abdominal pain, and fatigue with scaly marks?\n",
      "Q. I masturbate only by rubbing the tip of the penis. Is it a wrong way?\n",
      "Q. What can be done for tender and itchy red spots on hands?\n",
      "Q. Will Kalarchikai cure multiple ovarian cysts in PCOD?\n",
      "Q. Does swollen lymphnode everywhere in the body mean cancer?\n",
      "Q. What are the tests I have to undergo after having unprotected oral sex?\n",
      "Q. Every time I eat spicy food, I poop blood. Why?\n",
      "Q. Is Bimatoprost safe enough for optical nerve damage?\n",
      "Q. Every time I eat spicy food, I poop blood. Why?\n",
      "Q. 18 weeks pregnant woman used spray pesticide. Is it harmful for the baby?\n",
      "Q. I masturbate only by rubbing the tip of the penis. Is it a wrong way?\n",
      "Q. Delayed periods even after taking Gestin. What is the reason?\n",
      "Q. My mother had TB meningitis and is now suspected to have tubercular spine. Help.?\n",
      "Q. I masturbate only by rubbing the tip of the penis. Is it a wrong way?\n",
      "Q. I masturbate only by rubbing the tip of the penis. Is it a wrong way?\n",
      "Q. I had a surgery which ended up with some failures. What can I do to fix it?\n",
      "Q. I am having small black spots on my toenail. Does it indicate melanoma?\n",
      "Q. What is the cause for itching of face and chest after sex?\n",
      "Q. My left hip is completely fused. Can we have a healthy baby?\n",
      "Q. Should I continue the Olanzapine as I had a blackout episode when I was drunken?\n",
      "Q. I am suffering from stomach cramps and diarrhea. What should I do?\n",
      "Q. I am consuming Codeine. Will this affect conceiving?\n",
      "Q. Is it normal to have cobblestone appearance at the back of throat after tonsillectomy?\n",
      "Q. After lying on stomach for 20 minutes, I get most intense headache. Is this brain aneurysm?\n",
      "Q. What are the chances of me to get pregnant after taking i-pill?\n",
      "Q. Are my symptoms due to HIV infection? I had a high-risk exposure 15 months ago.?\n",
      "Q. Will Nano-Leo give permanent solution for erection problem?\n",
      "Q. I have erectile dysfunction inspite of having L-Arginine. Kindly advice.?\n",
      "Q. What does abutment of the nerve root mean?\n",
      "Q. Every time I eat spicy food, I poop blood. Why?\n",
      "Q. Are my symptoms suggestive of schizophrenia or OCD?\n",
      "Q. Every time I eat spicy food, I poop blood. Why?\n",
      "Q. Why do I get wrinkles on the glans penis after using Lobate cream for pimples?\n",
      "Q. Will Nano-Leo give permanent solution for erection problem?\n",
      "Q. Sometimes, I get palpitations, low BP and low sugar blackouts. Please advise.?\n",
      "Q. Will Nano-Leo give permanent solution for erection problem?\n",
      "Q. I masturbate only by rubbing the tip of the penis. Is it a wrong way?\n",
      "Q. Why is there a discomfort in my gums where the wisdom tooth is piercing them?\n",
      "Q. Does side effect of the anxiety drug diminishes the memory?\n"
     ]
    }
   ],
   "source": [
    "question_texts = [q.strip(\"?\") + \"?\" for q in test_data['Question'].tolist()]\n",
    "print(\"\\n\".join(question_texts))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "### Retrieve relevant context\n",
    "\n",
    "Fetch paragraphs similar to the question."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "relevant_contexts = []\n",
    "\n",
    "for question_text in question_texts:\n",
    "    relevant_chunks = chroma.query(\n",
    "        query_texts=[question_text],\n",
    "        n_results=5,\n",
    "    )\n",
    "    relevant_contexts.append(relevant_chunks)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "Get the set of chunks for one of the questions."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "=========\n",
      "Paragraph index :  10\n",
      "Paragraph :  Question: Q. Every time I eat spicy food, I poop blood. Why?\n",
      " Answer: Hello. I have gone through your information and test reports (attachment removed to protect patient identity). So, in view of that, there are a couple of things that I can opine upon: Hope that helps. For more information consult a general surgeon online -->\n",
      "Distance :  0.23510286211967468\n",
      "=========\n",
      "Paragraph index :  2968\n",
      "Paragraph :  Question: Q. Why is there burning sensation after passing stools?\n",
      " Answer: Hello. Intake of spicy food may cause burning sensation and irritation of anal mucosa which may lead to a burning pain during defecation. It is due to the spiciness of the food. You may try yogurt, cucumber, tender coconut water, probiotic capsules, buttermilk. Use tablet Nexium before breakfast for one week. Avoid spicy food intake. If symptoms do not improve, please consult a physician or post me a query.\n",
      "Distance :  0.7934628129005432\n",
      "=========\n",
      "Paragraph index :  397\n",
      "Paragraph :  Question: Q. Can you explain the reason behind burning sensation of gums?\n",
      " Answer: Hi. Hurting of gums while taking spicy food might be due to the following causes: 1. Gingivitis (swelling and inflammation of the gums) - Swollen gums may be painful and may cause burning sensation and pain while taking hot and spicy food. Gingivitis occurs due to either plaque or other debris accumulating around the teeth and gums. Also hormonal changes occurring during menstrual cycle can cause swollen and painful gums. Any medicines taken for medical issues like hypertension, epilepsy, etc., also cause gum changes and swelling. 2. Any ulcers in the mouth will get hurt while taking hot and spicy food. Ulcers might occur due to faulty tooth brushing techniques, usage of toothbrushes with hard bristles, stress, sharp tooth hurting the tissues, any dental appliances or ill-fitting dentures. 3. Any abscess related to infected tooth might also hurt while taking spicy food. But, you have mentioned that you do not have any cavities or teeth issues. Have you been examined by a dentist regarding this? 4. Any impacted tooth (teeth that remain unerupted due to inadequate space inside the mouth or remain inside the bone itself) may develop swelling of gums around it. When the opposing teeth impinges on this swollen tissue while taking spicy food it gets hurt. 5. Hypersensitivity reactions may occur to certain foods. This might cause swelling, reddening and burning sensation of the mouth. This may occur due to some food additives. 6. Habits like smoking and usage of tobacco products may also cause burning sensation while consuming spicy and hot food. 7. Dental procedures like scaling (cleaning of teeth) might cause minor tissue injuries. These hurt and cause burning sensation while taking hot and spicy food. But, this heals in 4-5 days after cleaning. In your case, this might not be the reason, as you have undergone scaling before 2-3 years. 1. Get dental scaling done, if you have any plaque or calculus deposits causing swollen gums. 2. Get your oral cavity examined by your dentist, for any ulcers, abscesses, infected teeth and impacted teeth. 3. Also get checked for any sharp teeth and any dental appliances or ill-fitting dentures. If found, sharp teeth have to be trimmed and reduced, and ill-fitting dentures and dental appliances have to be corrected immediately. 1. Kindly make a note if you develop any gum swelling, redness or bleeding gums during your periods. 2. Use toothbrushes with soft bristles for brushing your teeth. Also follow the proper brushing technique for brushing your teeth. 3. Make a note whenever your gum hurts and what foods hurt your gums. Check if any food causes the same issue repeatedly. In case, if that food contains some additive that causes hypersensitive reaction, then you may have to avoid that particular food in future. 4.Quit habits like smoking or usage of other tobacco products (in case you do). For further information consult a dentist online.--->\n",
      "Distance :  0.9654074907302856\n",
      "=========\n",
      "Paragraph index :  2873\n",
      "Paragraph :  Question: Q. How can blood in stool be managed?\n",
      " Answer: Hello. You may be suffering from constipation with internal hemorrhoids or fissure in ano. You have to avoid spicy food, low fiber diet. Use high fiber diet with plenty of liquids. Use Metamucil or Benefiber for stool bulk formation. Do regular exercise and yoga. If symptoms not improved you may use syrup Lactulose 30 ml after dinner for five days if necessary. If symptoms do not improve or develop an allergy to the above drug, please consult your physician. He will examine and treat you accordingly. Take care.\n",
      "Distance :  0.998435914516449\n",
      "=========\n",
      "Paragraph index :  1547\n",
      "Paragraph :  Question: Q. I have a muscular thing right out of my anus. What it could be?\n",
      " Answer: Hello. It is anal hemorrhoids (attachment removed to protect patient identity), and it is very painful. You may be suffering from constipation, or you must have been eating very spicy food. The treatment is sitz bath, and it means you have to sit in a tub full of warm water. It gets relieved, and you have to do this for two to three times a day. Kindly consult your doctor to discuss the suggestion and take the treatment with consent. You may apply ointment Pilex over the area. Stop eating spicy food and take syrup Duphalac (Lactulose) two spoons daily at bedtime to avoid constipation. If it is not relieved, then you have to consult a general surgeon.\n",
      "Distance :  1.0564740896224976\n"
     ]
    }
   ],
   "source": [
    "sample_chunks = relevant_contexts[0]\n",
    "for i, chunk in enumerate(sample_chunks['documents'][0]):\n",
    "    print(\"=========\")\n",
    "    print(\"Paragraph index : \", sample_chunks['ids'][0][i])\n",
    "    print(\"Paragraph : \", chunk)\n",
    "    print(\"Distance : \", sample_chunks['distances'][0][i])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "### Feed the context and the questions to `watsonx.ai` model."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Define instructions for the model.\n",
    "\n",
    "**Note:** Please start with finding better prompts using small subset of training records (under `train_data` variable). Make sure to not run an inference of all of `train_data`, as it'll take a long time to get the results. To get a sample from `train_data`, you can use e.g.`train_data.head(n=10)` to get first 10 records, or `train_data.sample(n=10)` to get random 10 records. Only once you have identified the best performing prompt, update this notebook to use the prompt and compute the metrics on the test data.\n",
    "\n",
    "**Action:** Please edit the below cell and add your own prompt here. In the below prompt, we have the instruction (first sentence) and one example included in the prompt. If you want to change the prompt or add your own examples or more examples, please change the below prompt accordingly."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "def make_prompt(context, question_text):\n",
    "    return (f\"Please answer the following.\\n\"\n",
    "          + f\"{context}:\\n\\n\"\n",
    "          + f\"{question_text}\")\n",
    "\n",
    "prompt_texts = []\n",
    "\n",
    "for relevant_context, question_text in zip(relevant_contexts, question_texts):\n",
    "    context = \"\\n\\n\\n\".join(relevant_context[\"documents\"][0])\n",
    "    prompt_text = make_prompt(context, question_text)\n",
    "    prompt_texts.append(prompt_text)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "Inspect prompt for sample question."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Please answer the following.\n",
      "Question: Q. Every time I eat spicy food, I poop blood. Why?\n",
      " Answer: Hello. I have gone through your information and test reports (attachment removed to protect patient identity). So, in view of that, there are a couple of things that I can opine upon: Hope that helps. For more information consult a general surgeon online -->\n",
      "\n",
      "\n",
      "Question: Q. Why is there burning sensation after passing stools?\n",
      " Answer: Hello. Intake of spicy food may cause burning sensation and irritation of anal mucosa which may lead to a burning pain during defecation. It is due to the spiciness of the food. You may try yogurt, cucumber, tender coconut water, probiotic capsules, buttermilk. Use tablet Nexium before breakfast for one week. Avoid spicy food intake. If symptoms do not improve, please consult a physician or post me a query.\n",
      "\n",
      "\n",
      "Question: Q. Can you explain the reason behind burning sensation of gums?\n",
      " Answer: Hi. Hurting of gums while taking spicy food might be due to the following causes: 1. Gingivitis (swelling and inflammation of the gums) - Swollen gums may be painful and may cause burning sensation and pain while taking hot and spicy food. Gingivitis occurs due to either plaque or other debris accumulating around the teeth and gums. Also hormonal changes occurring during menstrual cycle can cause swollen and painful gums. Any medicines taken for medical issues like hypertension, epilepsy, etc., also cause gum changes and swelling. 2. Any ulcers in the mouth will get hurt while taking hot and spicy food. Ulcers might occur due to faulty tooth brushing techniques, usage of toothbrushes with hard bristles, stress, sharp tooth hurting the tissues, any dental appliances or ill-fitting dentures. 3. Any abscess related to infected tooth might also hurt while taking spicy food. But, you have mentioned that you do not have any cavities or teeth issues. Have you been examined by a dentist regarding this? 4. Any impacted tooth (teeth that remain unerupted due to inadequate space inside the mouth or remain inside the bone itself) may develop swelling of gums around it. When the opposing teeth impinges on this swollen tissue while taking spicy food it gets hurt. 5. Hypersensitivity reactions may occur to certain foods. This might cause swelling, reddening and burning sensation of the mouth. This may occur due to some food additives. 6. Habits like smoking and usage of tobacco products may also cause burning sensation while consuming spicy and hot food. 7. Dental procedures like scaling (cleaning of teeth) might cause minor tissue injuries. These hurt and cause burning sensation while taking hot and spicy food. But, this heals in 4-5 days after cleaning. In your case, this might not be the reason, as you have undergone scaling before 2-3 years. 1. Get dental scaling done, if you have any plaque or calculus deposits causing swollen gums. 2. Get your oral cavity examined by your dentist, for any ulcers, abscesses, infected teeth and impacted teeth. 3. Also get checked for any sharp teeth and any dental appliances or ill-fitting dentures. If found, sharp teeth have to be trimmed and reduced, and ill-fitting dentures and dental appliances have to be corrected immediately. 1. Kindly make a note if you develop any gum swelling, redness or bleeding gums during your periods. 2. Use toothbrushes with soft bristles for brushing your teeth. Also follow the proper brushing technique for brushing your teeth. 3. Make a note whenever your gum hurts and what foods hurt your gums. Check if any food causes the same issue repeatedly. In case, if that food contains some additive that causes hypersensitive reaction, then you may have to avoid that particular food in future. 4.Quit habits like smoking or usage of other tobacco products (in case you do). For further information consult a dentist online.--->\n",
      "\n",
      "\n",
      "Question: Q. How can blood in stool be managed?\n",
      " Answer: Hello. You may be suffering from constipation with internal hemorrhoids or fissure in ano. You have to avoid spicy food, low fiber diet. Use high fiber diet with plenty of liquids. Use Metamucil or Benefiber for stool bulk formation. Do regular exercise and yoga. If symptoms not improved you may use syrup Lactulose 30 ml after dinner for five days if necessary. If symptoms do not improve or develop an allergy to the above drug, please consult your physician. He will examine and treat you accordingly. Take care.\n",
      "\n",
      "\n",
      "Question: Q. I have a muscular thing right out of my anus. What it could be?\n",
      " Answer: Hello. It is anal hemorrhoids (attachment removed to protect patient identity), and it is very painful. You may be suffering from constipation, or you must have been eating very spicy food. The treatment is sitz bath, and it means you have to sit in a tub full of warm water. It gets relieved, and you have to do this for two to three times a day. Kindly consult your doctor to discuss the suggestion and take the treatment with consent. You may apply ointment Pilex over the area. Stop eating spicy food and take syrup Duphalac (Lactulose) two spoons daily at bedtime to avoid constipation. If it is not relieved, then you have to consult a general surgeon.:\n",
      "\n",
      "Q. Every time I eat spicy food, I poop blood. Why?\n"
     ]
    }
   ],
   "source": [
    "print(prompt_texts[0])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "### Defining the model parameters\n",
    "We need to provide a set of model parameters that will influence the result:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "from ibm_watson_machine_learning.metanames import GenTextParamsMetaNames as GenParams\n",
    "from ibm_watson_machine_learning.foundation_models.utils.enums import DecodingMethods\n",
    "\n",
    "parameters = {\n",
    "    GenParams.DECODING_METHOD: DecodingMethods.GREEDY,\n",
    "    GenParams.MIN_NEW_TOKENS: 1,\n",
    "    GenParams.MAX_NEW_TOKENS: 200\n",
    "}"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "Initialize the `Model` class."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [],
   "source": [
    "#this cell should never fail, and will produce no output\n",
    "import requests\n",
    "\n",
    "def getBearer(apikey):\n",
    "    form = {'apikey': apikey, 'grant_type': \"urn:ibm:params:oauth:grant-type:apikey\"}\n",
    "    print(\"About to create bearer\")\n",
    "#    print(form)\n",
    "    response = requests.post(\"https://iam.cloud.ibm.com/oidc/token\", data = form)\n",
    "    if response.status_code != 200:\n",
    "        print(\"Bad response code retrieving token\")\n",
    "        raise Exception(\"Failed to get token, invalid status\")\n",
    "    json = response.json()\n",
    "    if not json:\n",
    "        print(\"Invalid/no JSON retrieving token\")\n",
    "        raise Exception(\"Failed to get token, invalid response\")\n",
    "    print(\"Bearer retrieved\")\n",
    "    return json.get(\"access_token\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "About to create bearer\n",
      "Bearer retrieved\n"
     ]
    }
   ],
   "source": [
    "credentials[\"token\"] = getBearer(credentials[\"apikey\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "from ibm_watson_machine_learning.foundation_models import Model\n",
    "model = Model(\n",
    "    model_id=model_id,\n",
    "    params=parameters,\n",
    "    credentials=credentials,\n",
    "    project_id=project_id)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "### Generate a retrieval-augmented response"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Note:** Execution of this cell could take several minutes."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Please answer the following.\\nQuestion: Q. Every time I eat spicy food, I poop blood. Why?\\n Answer: Hello. I have gone through your information and test reports (attachment removed to protect patient identity). So, in view of that, there are a couple of things that I can opine upon: Hope that helps. For more information consult a general surgeon online -->\\n\\n\\nQuestion: Q. Why is there burning sensation after passing stools?\\n Answer: Hello. Intake of spicy food may cause burning sensation and irritation of anal mucosa which may lead to a burning pain during defecation. It is due to the spiciness of the food. You may try yogurt, cucumber, tender coconut water, probiotic capsules, buttermilk. Use tablet Nexium before breakfast for one week. Avoid spicy food intake. If symptoms do not improve, please consult a physician or post me a query.\\n\\n\\nQuestion: Q. Can you explain the reason behind burning sensation of gums?\\n Answer: Hi. Hurting of gums while taking spicy food might be due to the following causes: 1. Gingivitis (swelling and inflammation of the gums) - Swollen gums may be painful and may cause burning sensation and pain while taking hot and spicy food. Gingivitis occurs due to either plaque or other debris accumulating around the teeth and gums. Also hormonal changes occurring during menstrual cycle can cause swollen and painful gums. Any medicines taken for medical issues like hypertension, epilepsy, etc., also cause gum changes and swelling. 2. Any ulcers in the mouth will get hurt while taking hot and spicy food. Ulcers might occur due to faulty tooth brushing techniques, usage of toothbrushes with hard bristles, stress, sharp tooth hurting the tissues, any dental appliances or ill-fitting dentures. 3. Any abscess related to infected tooth might also hurt while taking spicy food. But, you have mentioned that you do not have any cavities or teeth issues. Have you been examined by a dentist regarding this? 4. Any impacted tooth (teeth that remain unerupted due to inadequate space inside the mouth or remain inside the bone itself) may develop swelling of gums around it. When the opposing teeth impinges on this swollen tissue while taking spicy food it gets hurt. 5. Hypersensitivity reactions may occur to certain foods. This might cause swelling, reddening and burning sensation of the mouth. This may occur due to some food additives. 6. Habits like smoking and usage of tobacco products may also cause burning sensation while consuming spicy and hot food. 7. Dental procedures like scaling (cleaning of teeth) might cause minor tissue injuries. These hurt and cause burning sensation while taking hot and spicy food. But, this heals in 4-5 days after cleaning. In your case, this might not be the reason, as you have undergone scaling before 2-3 years. 1. Get dental scaling done, if you have any plaque or calculus deposits causing swollen gums. 2. Get your oral cavity examined by your dentist, for any ulcers, abscesses, infected teeth and impacted teeth. 3. Also get checked for any sharp teeth and any dental appliances or ill-fitting dentures. If found, sharp teeth have to be trimmed and reduced, and ill-fitting dentures and dental appliances have to be corrected immediately. 1. Kindly make a note if you develop any gum swelling, redness or bleeding gums during your periods. 2. Use toothbrushes with soft bristles for brushing your teeth. Also follow the proper brushing technique for brushing your teeth. 3. Make a note whenever your gum hurts and what foods hurt your gums. Check if any food causes the same issue repeatedly. In case, if that food contains some additive that causes hypersensitive reaction, then you may have to avoid that particular food in future. 4.Quit habits like smoking or usage of other tobacco products (in case you do). For further information consult a dentist online.--->\\n\\n\\nQuestion: Q. How can blood in stool be managed?\\n Answer: Hello. You may be suffering from constipation with internal hemorrhoids or fissure in ano. You have to avoid spicy food, low fiber diet. Use high fiber diet with plenty of liquids. Use Metamucil or Benefiber for stool bulk formation. Do regular exercise and yoga. If symptoms not improved you may use syrup Lactulose 30 ml after dinner for five days if necessary. If symptoms do not improve or develop an allergy to the above drug, please consult your physician. He will examine and treat you accordingly. Take care.\\n\\n\\nQuestion: Q. I have a muscular thing right out of my anus. What it could be?\\n Answer: Hello. It is anal hemorrhoids (attachment removed to protect patient identity), and it is very painful. You may be suffering from constipation, or you must have been eating very spicy food. The treatment is sitz bath, and it means you have to sit in a tub full of warm water. It gets relieved, and you have to do this for two to three times a day. Kindly consult your doctor to discuss the suggestion and take the treatment with consent. You may apply ointment Pilex over the area. Stop eating spicy food and take syrup Duphalac (Lactulose) two spoons daily at bedtime to avoid constipation. If it is not relieved, then you have to consult a general surgeon.:\\n\\nQ. Every time I eat spicy food, I poop blood. Why?']"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "prompt_texts[:1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(prompt_texts[:1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "results = []\n",
    "for prompt_text in prompt_texts[:1]:\n",
    "    results.append(model.generate_text(prompt=prompt_text))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [],
   "source": [
    "#test_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Question =  Q. Every time I eat spicy food, I poop blood. Why?\n",
      "Answer =  Hello. I have gone through your information and test reports (attachment removed to protect patient identity). So, in view of that, there are a couple of things that I can opine upon: Hope that helps. For more information consult a general surgeon online -->\n",
      "Expected Answer(s) (may not be appear with exact wording in the dataset) =  Hello. I have gone through your information and test reports (attachment removed to protect patient identity). So, in view of that, there are a couple of things that I can opine upon: Hope that helps. For more information consult a general surgeon online -->\n",
      "\n",
      "\n"
     ]
    }
   ],
   "source": [
    "for idx, result in enumerate(results):\n",
    "    print(\"Question = \", test_data.iloc[idx]['Question'])\n",
    "    print(\"Answer = \", result)\n",
    "    print(\"Expected Answer(s) (may not be appear with exact wording in the dataset) = \", test_data.iloc[idx]['Answer'])\n",
    "    print(\"\\n\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "<a id=\"score\"></a>\n",
    "## Calculate rougeL metric"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In this sample notebook `rouge_score` module was used for rougeL calculation."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "#### Rouge Metric"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "**Note:** The Rouge (Recall-Oriented Understudy for Gisting Evaluation) metric is a set of evaluation measures used in natural language processing (NLP) and specifically in text summarization and machine translation tasks. The Rouge metrics are designed to assess the quality of generated summaries or translations by comparing them to one or more reference texts.\n",
    "\n",
    "The main idea behind Rouge is to measure the overlap between the generated summary (or translation) and the reference text(s) in terms of n-grams or longest common subsequences. By calculating recall, precision, and F1 scores based on these overlapping units, Rouge provides a quantitative assessment of the summary's content overlap with the reference(s).\n",
    "\n",
    "Rouge-1 focuses on individual word overlap, Rouge-2 considers pairs of consecutive words, and Rouge-L takes into account the ordering of words and phrases. These metrics provide different perspectives on the similarity between two texts and can be used to evaluate different aspects of summarization or text generation models."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "from rouge_score import rouge_scorer\n",
    "from collections import defaultdict\n",
    "import numpy as np\n",
    "\n",
    "def get_rouge_score(predictions, references):\n",
    "    scorer = rouge_scorer.RougeScorer(['rouge1', 'rouge2', 'rougeL', 'rougeLsum'])\n",
    "    aggregate_score = defaultdict(list)\n",
    "\n",
    "    for result, ref in zip(predictions, references):\n",
    "        for key, val in scorer.score(result, ref).items():\n",
    "            aggregate_score[key].append(val.fmeasure)\n",
    "\n",
    "    scores = {}\n",
    "    for key in aggregate_score:\n",
    "        scores[key] = np.mean(aggregate_score[key])\n",
    "    \n",
    "    return scores"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'rouge1': 1.0, 'rouge2': 1.0, 'rougeL': 1.0, 'rougeLsum': 1.0}\n"
     ]
    }
   ],
   "source": [
    "print(get_rouge_score(results, test_data.Answer))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python3 (GPT)",
   "language": "python",
   "name": "gpt"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}