File size: 52,463 Bytes
d7eda6a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import streamlit as st
import os
import json
from PIL import Image

# Set page configuration with a title and favicon
st.set_page_config(page_title="🌌🚀 Transhuman Space Encyclopedia", page_icon="🌠", layout="wide")

# Ensure the directory for storing scores exists
score_dir = "scores"
os.makedirs(score_dir, exist_ok=True)

# Function to generate a unique key for each button, including an emoji
def generate_key(label, header, idx):
    return f"{header}_{label}_{idx}_key"

# Function to increment and save score
def update_score(key, increment=1):
    score_file = os.path.join(score_dir, f"{key}.json")
    if os.path.exists(score_file):
        with open(score_file, "r") as file:
            score_data = json.load(file)
    else:
        score_data = {"clicks": 0, "score": 0}
    
    score_data["clicks"] += 1
    score_data["score"] += increment
    
    with open(score_file, "w") as file:
        json.dump(score_data, file)
    
    return score_data["score"]

# Function to load score
def load_score(key):
    score_file = os.path.join(score_dir, f"{key}.json")
    if os.path.exists(score_file):
        with open(score_file, "r") as file:
            score_data = json.load(file)
        return score_data["score"]
    return 0

# Transhuman Space glossary with full content
transhuman_glossary = {
    "🚀 Core Technologies": ["Nanotechnology🔬", "Artificial Intelligence🤖", "Quantum Computing💻", "Spacecraft Engineering🛸", "Biotechnology🧬", "Cybernetics🦾", "Virtual Reality🕶️", "Energy Systems⚡", "Material Science🧪", "Communication Technologies📡"],
    "🌐 Nations": ["Terran Federation🌍", "Martian Syndicate🔴", "Jovian Republics🪐", "Asteroid Belt Communities🌌", "Venusian Colonies🌋", "Lunar States🌖", "Outer System Alliances✨", "Digital Consciousness Collectives🧠", "Transhumanist Enclaves🦿", "Non-Human Intelligence Tribes👽"],
    "💡 Memes": ["Post-Humanism🚶‍♂️➡️🚀", "Neo-Evolutionism🧬📈", "Digital Ascendancy💾👑", "Solar System Nationalism🌞🏛", "Space Explorationism🚀🛰", "Cyber Democracy🖥️🗳️", "Interstellar Environmentalism🌍💚", "Quantum Mysticism🔮💫", "Techno-Anarchism🔌🏴", "Cosmic Preservationism🌌🛡️"],
    "🏛 Institutions": ["Interstellar Council🪖", "Transhuman Ethical Standards Organization📜", "Galactic Trade Union🤝", "Space Habitat Authority🏠", "Artificial Intelligence Safety Commission🤖🔒", "Extraterrestrial Relations Board👽🤝", "Quantum Research Institute🔬", "Biogenetics Oversight Committee🧫", "Cyberspace Regulatory Agency💻", "Planetary Defense Coalition🌍🛡"],
    "🔗 Organizations": ["Neural Network Pioneers🧠🌐", "Spacecraft Innovators Guild🚀🛠", "Quantum Computing Consortium💻🔗", "Interplanetary Miners Union⛏️🪐", "Cybernetic Augmentation Advocates🦾❤️", "Biotechnological Harmony Group🧬🕊", "Stellar Navigation Circle🧭✨", "Virtual Reality Creators Syndicate🕶️🎨", "Renewable Energy Pioneers⚡🌱", "Transhuman Rights Activists🦿📢"],
    "⚔️ War": ["Space Warfare Tactics🚀⚔️", "Cyber Warfare🖥️🔒", "Biological Warfare🧬💣", "Nanotech Warfare🔬⚔️", "Psychological Operations🧠🗣️", "Quantum Encryption & Decryption🔐💻", "Kinetic Bombardment🚀💥", "Energy Shield Defense🛡️⚡", "Stealth Spacecraft🚀🔇", "Artificial Intelligence Combat🤖⚔️"],
    "🎖 Military": ["Interstellar Navy🚀🎖", "Planetary Guard🌍🛡", "Cybernetic Marines🦾🔫", "Nanotech Soldiers🔬💂", "Space Drone Fleet🛸🤖", "Quantum Signal Corps💻📡", "Special Operations Forces👥⚔️", "Artificial Intelligence Strategists🤖🗺️", "Orbital Defense Systems🌌🛡️", "Exoskeleton Brigades🦾🚶‍♂️"],
    "🦹 Outlaws": ["Pirate Fleets🏴‍☠️🚀", "Hacktivist Collectives💻🚫", "Smuggler Caravans🛸💼", "Rebel AI Entities🤖🚩", "Black Market Biotech Dealers🧬💰", "Quantum Thieves💻🕵️‍♂️", "Space Nomad Raiders🚀🏴‍☠️", "Cyberspace Intruders💻👾", "Anti-Transhumanist Factions🚫🦾", "Rogue Nanotech Swarms🔬🦠"],
    "👽 Terrorists": ["Bioengineered Virus Spreaders🧬💉", "Nanotechnology Saboteurs🔬🧨", "Cyber Terrorist Networks💻🔥", "Rogue AI Sects🤖🛑", "Space Anarchist Cells🚀Ⓐ", "Quantum Data Hijackers💻🔓", "Environmental Extremists🌍💣", "Technological Singularity Cults🤖🙏", "Interspecies Supremacists👽👑", "Orbital Bombardment Threats🛰️💥"],
}


# Function to search glossary and display results
def search_glossary(query):
    for category, terms in transhuman_glossary.items():
        if query.lower() in (term.lower() for term in terms):
            st.markdown(f"### {category}")
            st.write(f"- {query}")

    st.write('## Processing query against GPT and Llama:')
    # ------------------------------------------------------------------------------------------------
    st.write('Reasoning with your inputs using GPT...')
    response = chat_with_model(query)
    st.write('Response:')
    st.write(response)
    filename = generate_filename(response, "txt")
    create_file(filename, query, response, should_save)
    
    st.write('Reasoning with your inputs using Llama...')    
    response = StreamLLMChatResponse(query)
    filename_txt = generate_filename(query, "md")
    create_file(filename_txt, query, response, should_save)
    # ------------------------------------------------------------------------------------------------
        
            
# Display the glossary with Streamlit components, ensuring emojis are used
def display_glossary(area):
    st.subheader(f"📘 Glossary for {area}")
    terms = transhuman_glossary[area]
    for idx, term in enumerate(terms, start=1):
        st.write(f"{idx}. {term}")


# Function to display glossary in a 3x3 grid
def display_glossary_grid(glossary):
    # Group related categories for a 3x3 grid
    groupings = [
        ["🚀 Core Technologies", "🌐 Nations", "💡 Memes"],
        ["🏛 Institutions", "🔗 Organizations", "⚔️ War"],
        ["🎖 Military", "🦹 Outlaws", "👽 Terrorists"],
    ]
    
    for group in groupings:
        cols = st.columns(3)  # Create three columns
        for idx, category in enumerate(group):
            with cols[idx]:
                st.markdown(f"### {category}")
                terms = glossary[category]
                for term in terms:
                    st.write(f"- {term}")

# Streamlined UI for displaying buttons with scores, integrating emojis
def display_buttons_with_scores():
    for header, terms in transhuman_glossary.items():
        st.markdown(f"## {header}")
        for term in terms:
            key = generate_key(term, header, terms.index(term))
            score = load_score(key)
            if st.button(f"{term} {score}🚀", key=key):
                update_score(key)
                search_glossary('Create a three level markdown outline with 3 subpoints each where each line defines and writes out the core technology descriptions with appropriate emojis for the glossary term: ' + term)
                st.experimental_rerun()

def fetch_wikipedia_summary(keyword):
    # Placeholder function for fetching Wikipedia summaries
    # In a real app, you might use requests to fetch from the Wikipedia API
    return f"Summary for {keyword}. For more information, visit Wikipedia."

def create_search_url_youtube(keyword):
    base_url = "https://www.youtube.com/results?search_query="
    return base_url + keyword.replace(' ', '+')

def create_search_url_bing(keyword):
    base_url = "https://www.bing.com/search?q="
    return base_url + keyword.replace(' ', '+')

def create_search_url_wikipedia(keyword):
    base_url = "https://www.wikipedia.org/search-redirect.php?family=wikipedia&language=en&search="
    return base_url + keyword.replace(' ', '+')

def create_search_url_google(keyword):
    base_url = "https://www.google.com/search?q="
    return base_url + keyword.replace(' ', '+')


def display_images_and_wikipedia_summaries():
    st.title('Gallery with Related Stories')
    image_files = [f for f in os.listdir('.') if f.endswith('.png')]
    if not image_files:
        st.write("No PNG images found in the current directory.")
        return
    
    for image_file in image_files:
        image = Image.open(image_file)
        st.image(image, caption=image_file, use_column_width=True)
        
        keyword = image_file.split('.')[0]  # Assumes keyword is the file name without extension
        
        # Display Wikipedia and Google search links
        wikipedia_url = create_search_url_wikipedia(keyword)
        google_url = create_search_url_google(keyword)
        youtube_url = create_search_url_youtube(keyword)
        bing_url = create_search_url_bing(keyword)
        
        links_md = f"""
        [Wikipedia]({wikipedia_url}) | 
        [Google]({google_url}) | 
        [YouTube]({youtube_url}) | 
        [Bing]({bing_url})
        """
        st.markdown(links_md)


def get_all_query_params(key):
    return st.query_params().get(key, [])

def clear_query_params():
    st.query_params()  
                

# Function to display content or image based on a query
def display_content_or_image(query):
    # Check if the query matches any glossary term
    for category, terms in transhuman_glossary.items():
        for term in terms:
            if query.lower() in term.lower():
                st.subheader(f"Found in {category}:")
                st.write(term)
                return True  # Return after finding and displaying the first match
    
    # Check for an image match in a predefined directory (adjust path as needed)
    image_dir = "images"  # Example directory where images are stored
    image_path = f"{image_dir}/{query}.png"  # Construct image path with query
    if os.path.exists(image_path):
        st.image(image_path, caption=f"Image for {query}")
        return True
    
    # If no content or image is found
    st.warning("No matching content or image found.")
    return False






    
# Imports
import base64
import glob
import json
import math
import openai
import os
import pytz
import re
import requests
import streamlit as st
import textract
import time
import zipfile
import huggingface_hub
import dotenv
from audio_recorder_streamlit import audio_recorder
from bs4 import BeautifulSoup
from collections import deque
from datetime import datetime
from dotenv import load_dotenv
from huggingface_hub import InferenceClient
from io import BytesIO
from langchain.chat_models import ChatOpenAI
from langchain.chains import ConversationalRetrievalChain
from langchain.embeddings import OpenAIEmbeddings
from langchain.memory import ConversationBufferMemory
from langchain.text_splitter import CharacterTextSplitter
from langchain.vectorstores import FAISS
from openai import ChatCompletion
from PyPDF2 import PdfReader
from templates import bot_template, css, user_template
from xml.etree import ElementTree as ET
import streamlit.components.v1 as components  # Import Streamlit Components for HTML5


def add_Med_Licensing_Exam_Dataset():
    import streamlit as st
    from datasets import load_dataset
    dataset = load_dataset("augtoma/usmle_step_1")['test']  # Using 'test' split
    st.title("USMLE Step 1 Dataset Viewer")
    if len(dataset) == 0:
        st.write("😢 The dataset is empty.")
    else:
        st.write("""
        🔍 Use the search box to filter questions or use the grid to scroll through the dataset.
        """)
    
        # 👩‍🔬 Search Box
        search_term = st.text_input("Search for a specific question:", "")
        
        # 🎛 Pagination
        records_per_page = 100
        num_records = len(dataset)
        num_pages = max(int(num_records / records_per_page), 1)
        
        # Skip generating the slider if num_pages is 1 (i.e., all records fit in one page)
        if num_pages > 1:
            page_number = st.select_slider("Select page:", options=list(range(1, num_pages + 1)))
        else:
            page_number = 1  # Only one page
        
        # 📊 Display Data
        start_idx = (page_number - 1) * records_per_page
        end_idx = start_idx + records_per_page
    
        # 🧪 Apply the Search Filter
        filtered_data = []
        for record in dataset[start_idx:end_idx]:
            if isinstance(record, dict) and 'text' in record and 'id' in record:
                if search_term:
                    if search_term.lower() in record['text'].lower():
                        st.markdown(record)
                        filtered_data.append(record)
                else:
                    filtered_data.append(record)
    
        # 🌐 Render the Grid
        for record in filtered_data:
            st.write(f"## Question ID: {record['id']}")
            st.write(f"### Question:")
            st.write(f"{record['text']}")
            st.write(f"### Answer:")
            st.write(f"{record['answer']}")
            st.write("---")
    
        st.write(f"😊 Total Records: {num_records} | 📄 Displaying {start_idx+1} to {min(end_idx, num_records)}")

# 1. Constants and Top Level UI Variables

# My Inference API Copy
API_URL = 'https://qe55p8afio98s0u3.us-east-1.aws.endpoints.huggingface.cloud'  # Dr Llama
# Meta's Original - Chat HF Free Version:
#API_URL = "https://api-inference.huggingface.co/models/meta-llama/Llama-2-7b-chat-hf"
API_KEY = os.getenv('API_KEY')
MODEL1="meta-llama/Llama-2-7b-chat-hf"
MODEL1URL="https://huggingface.co/meta-llama/Llama-2-7b-chat-hf"
HF_KEY = os.getenv('HF_KEY')
headers = {
    "Authorization": f"Bearer {HF_KEY}",
    "Content-Type": "application/json"
}
key = os.getenv('OPENAI_API_KEY')
prompt = f"Write instructions to teach discharge planning along with guidelines and patient education. List entities, features and relationships to CCDA and FHIR objects in boldface."
should_save = st.sidebar.checkbox("💾 Save", value=True, help="Save your session data.")

# 2. Prompt label button demo for LLM
def add_witty_humor_buttons():
    with st.expander("Wit and Humor 🤣", expanded=True):
        # Tip about the Dromedary family
        st.markdown("🔬 **Fun Fact**: Dromedaries, part of the camel family, have a single hump and are adapted to arid environments. Their 'superpowers' include the ability to survive without water for up to 7 days, thanks to their specialized blood cells and water storage in their hump.")
        
        # Define button descriptions
        descriptions = {
            "Generate Limericks 😂": "Write ten random adult limericks based on quotes that are tweet length and make you laugh 🎭",
            "Wise Quotes 🧙": "Generate ten wise quotes that are tweet length 🦉",
            "Funny Rhymes 🎤": "Create ten funny rhymes that are tweet length 🎶",
            "Medical Jokes 💉": "Create ten medical jokes that are tweet length 🏥",
            "Minnesota Humor ❄️": "Create ten jokes about Minnesota that are tweet length 🌨️",
            "Top Funny Stories 📖": "Create ten funny stories that are tweet length 📚",
            "More Funny Rhymes 🎙️": "Create ten more funny rhymes that are tweet length 🎵"
        }
        
        # Create columns
        col1, col2, col3 = st.columns([1, 1, 1], gap="small")
        
        # Add buttons to columns
        if col1.button("Wise Limericks 😂"):
            StreamLLMChatResponse(descriptions["Generate Limericks 😂"])
        
        if col2.button("Wise Quotes 🧙"):
            StreamLLMChatResponse(descriptions["Wise Quotes 🧙"])
        
        #if col3.button("Funny Rhymes 🎤"):
        #    StreamLLMChatResponse(descriptions["Funny Rhymes 🎤"])
        
        col4, col5, col6 = st.columns([1, 1, 1], gap="small")
        
        if col4.button("Top Ten Funniest Clean Jokes 💉"):
            StreamLLMChatResponse(descriptions["Top Ten Funniest Clean Jokes  💉"])
        
        if col5.button("Minnesota Humor ❄️"):
            StreamLLMChatResponse(descriptions["Minnesota Humor ❄️"])
        
        if col6.button("Origins of Medical Science True Stories"):
            StreamLLMChatResponse(descriptions["Origins of Medical Science True Stories"])
        
        col7 = st.columns(1, gap="small")
        
        if col7[0].button("Top Ten Best Write a streamlit python program prompts to build AI programs. 🎙️"):
            StreamLLMChatResponse(descriptions["Top Ten Best Write a streamlit python program prompts to build AI programs. 🎙️"])

def SpeechSynthesis(result):
    documentHTML5='''
    <!DOCTYPE html>
    <html>
    <head>
        <title>Read It Aloud</title>
        <script type="text/javascript">
            function readAloud() {
                const text = document.getElementById("textArea").value;
                const speech = new SpeechSynthesisUtterance(text);
                window.speechSynthesis.speak(speech);
            }
        </script>
    </head>
    <body>
        <h1>🔊 Read It Aloud</h1>
        <textarea id="textArea" rows="10" cols="80">
    '''
    documentHTML5 = documentHTML5 + result
    documentHTML5 = documentHTML5 + '''
        </textarea>
        <br>
        <button onclick="readAloud()">🔊 Read Aloud</button>
    </body>
    </html>
    '''

    components.html(documentHTML5, width=1280, height=300)
    #return result


# 3. Stream Llama Response
# @st.cache_resource
def StreamLLMChatResponse(prompt):
    try:
        endpoint_url = API_URL
        hf_token = API_KEY
        st.write('Running client ' + endpoint_url)
        client = InferenceClient(endpoint_url, token=hf_token)
        gen_kwargs = dict(
            max_new_tokens=512,
            top_k=30,
            top_p=0.9,
            temperature=0.2,
            repetition_penalty=1.02,
            stop_sequences=["\nUser:", "<|endoftext|>", "</s>"],
        )
        stream = client.text_generation(prompt, stream=True, details=True, **gen_kwargs)
        report=[]
        res_box = st.empty()
        collected_chunks=[]
        collected_messages=[]
        allresults=''
        for r in stream:
            if r.token.special:
                continue
            if r.token.text in gen_kwargs["stop_sequences"]:
                break
            collected_chunks.append(r.token.text)
            chunk_message = r.token.text
            collected_messages.append(chunk_message)
            try:
                report.append(r.token.text)
                if len(r.token.text) > 0:
                    result="".join(report).strip()
                    res_box.markdown(f'*{result}*')
                    
            except:
                st.write('Stream llm issue')
        SpeechSynthesis(result)
        return result
    except:
        st.write('Llama model is asleep. Starting up now on A10 - please give 5 minutes then retry as KEDA scales up from zero to activate running container(s).')

# 4. Run query with payload
def query(payload):
    response = requests.post(API_URL, headers=headers, json=payload)
    st.markdown(response.json())
    return response.json()
def get_output(prompt):
    return query({"inputs": prompt})

# 5. Auto name generated output files from time and content
def generate_filename(prompt, file_type):
    central = pytz.timezone('US/Central')
    safe_date_time = datetime.now(central).strftime("%m%d_%H%M")
    replaced_prompt = prompt.replace(" ", "_").replace("\n", "_")
    safe_prompt = "".join(x for x in replaced_prompt if x.isalnum() or x == "_")[:255]  # 255 is linux max, 260 is windows max
    #safe_prompt = "".join(x for x in replaced_prompt if x.isalnum() or x == "_")[:45]
    return f"{safe_date_time}_{safe_prompt}.{file_type}"

# 6. Speech transcription via OpenAI service
def transcribe_audio(openai_key, file_path, model):
    openai.api_key = openai_key
    OPENAI_API_URL = "https://api.openai.com/v1/audio/transcriptions"
    headers = {
        "Authorization": f"Bearer {openai_key}",
    }
    with open(file_path, 'rb') as f:
        data = {'file': f}
        st.write('STT transcript ' + OPENAI_API_URL)
        response = requests.post(OPENAI_API_URL, headers=headers, files=data, data={'model': model})
    if response.status_code == 200:
        st.write(response.json())
        chatResponse = chat_with_model(response.json().get('text'), '') # *************************************
        transcript = response.json().get('text')
        filename = generate_filename(transcript, 'txt')
        response = chatResponse
        user_prompt = transcript
        create_file(filename, user_prompt, response, should_save)
        return transcript
    else:
        st.write(response.json())
        st.error("Error in API call.")
        return None

# 7. Auto stop on silence audio control for recording WAV files
def save_and_play_audio(audio_recorder):
    audio_bytes = audio_recorder(key='audio_recorder')
    if audio_bytes:
        filename = generate_filename("Recording", "wav")
        with open(filename, 'wb') as f:
            f.write(audio_bytes)
        st.audio(audio_bytes, format="audio/wav")
        return filename
    return None

# 8. File creator that interprets type and creates output file for text, markdown and code
def create_file(filename, prompt, response, should_save=True):
    if not should_save:
        return
    base_filename, ext = os.path.splitext(filename)
    if ext in ['.txt', '.htm', '.md']:
        with open(f"{base_filename}.md", 'w') as file:
            try:
                content = prompt.strip() + '\r\n' + response
                file.write(content)
            except:
                st.write('.')

    #has_python_code = re.search(r"```python([\s\S]*?)```", prompt.strip() + '\r\n' + response)
    #has_python_code = bool(re.search(r"```python([\s\S]*?)```", prompt.strip() + '\r\n' + response))
        #if has_python_code:
        #    python_code = re.findall(r"```python([\s\S]*?)```", response)[0].strip()
        #    with open(f"{base_filename}-Code.py", 'w') as file:
        #        file.write(python_code)
        #    with open(f"{base_filename}.md", 'w') as file:
        #        content = prompt.strip() + '\r\n' + response
        #        file.write(content)
            
def truncate_document(document, length):
    return document[:length]
def divide_document(document, max_length):
    return [document[i:i+max_length] for i in range(0, len(document), max_length)]

# 9. Sidebar with UI controls to review and re-run prompts and continue responses
@st.cache_resource
def get_table_download_link(file_path):
    with open(file_path, 'r') as file:
        data = file.read()
   
    b64 = base64.b64encode(data.encode()).decode()  
    file_name = os.path.basename(file_path)
    ext = os.path.splitext(file_name)[1]  # get the file extension
    if ext == '.txt':
        mime_type = 'text/plain'
    elif ext == '.py':
        mime_type = 'text/plain'
    elif ext == '.xlsx':
        mime_type = 'text/plain'
    elif ext == '.csv':
        mime_type = 'text/plain'
    elif ext == '.htm':
        mime_type = 'text/html'
    elif ext == '.md':
        mime_type = 'text/markdown'
    elif ext == '.wav':
        mime_type = 'audio/wav'
    else:
        mime_type = 'application/octet-stream'  # general binary data type
    href = f'<a href="data:{mime_type};base64,{b64}" target="_blank" download="{file_name}">{file_name}</a>'
    return href


def CompressXML(xml_text):
    root = ET.fromstring(xml_text)
    for elem in list(root.iter()):
        if isinstance(elem.tag, str) and 'Comment' in elem.tag:
            elem.parent.remove(elem)
    return ET.tostring(root, encoding='unicode', method="xml")

# 10. Read in and provide UI for past files
@st.cache_resource
def read_file_content(file,max_length):
    if file.type == "application/json":
        content = json.load(file)
        return str(content)
    elif file.type == "text/html" or file.type == "text/htm":
        content = BeautifulSoup(file, "html.parser")
        return content.text
    elif file.type == "application/xml" or file.type == "text/xml":
        tree = ET.parse(file)
        root = tree.getroot()
        xml = CompressXML(ET.tostring(root, encoding='unicode'))
        return xml
    elif file.type == "text/markdown" or file.type == "text/md":
        md = mistune.create_markdown()
        content = md(file.read().decode())
        return content
    elif file.type == "text/plain":
        return file.getvalue().decode()
    else:
        return ""

# 11. Chat with GPT - Caution on quota - now favoring fastest AI pipeline STT Whisper->LLM Llama->TTS
@st.cache_resource
def chat_with_model(prompt, document_section='', model_choice='gpt-3.5-turbo'):
    model = model_choice
    conversation = [{'role': 'system', 'content': 'You are a helpful assistant.'}]
    conversation.append({'role': 'user', 'content': prompt})
    if len(document_section)>0:
        conversation.append({'role': 'assistant', 'content': document_section})
    start_time = time.time()
    report = []
    res_box = st.empty()
    collected_chunks = []
    collected_messages = []

    st.write('LLM stream ' + 'gpt-3.5-turbo')
    for chunk in openai.ChatCompletion.create(model='gpt-3.5-turbo', messages=conversation, temperature=0.5, stream=True):
        collected_chunks.append(chunk)  
        chunk_message = chunk['choices'][0]['delta']  
        collected_messages.append(chunk_message) 
        content=chunk["choices"][0].get("delta",{}).get("content")
        try:
            report.append(content)
            if len(content) > 0:
                result = "".join(report).strip()
                res_box.markdown(f'*{result}*') 
        except:
            st.write(' ')
    full_reply_content = ''.join([m.get('content', '') for m in collected_messages])
    st.write("Elapsed time:")
    st.write(time.time() - start_time)
    return full_reply_content

# 12. Embedding VectorDB for LLM query of documents to text to compress inputs and prompt together as Chat memory using Langchain
@st.cache_resource
def chat_with_file_contents(prompt, file_content, model_choice='gpt-3.5-turbo'):
    conversation = [{'role': 'system', 'content': 'You are a helpful assistant.'}]
    conversation.append({'role': 'user', 'content': prompt})
    if len(file_content)>0:
        conversation.append({'role': 'assistant', 'content': file_content})
    response = openai.ChatCompletion.create(model=model_choice, messages=conversation)
    return response['choices'][0]['message']['content']

def extract_mime_type(file):
    if isinstance(file, str):
        pattern = r"type='(.*?)'"
        match = re.search(pattern, file)
        if match:
            return match.group(1)
        else:
            raise ValueError(f"Unable to extract MIME type from {file}")
    elif isinstance(file, streamlit.UploadedFile):
        return file.type
    else:
        raise TypeError("Input should be a string or a streamlit.UploadedFile object")

def extract_file_extension(file):
    # get the file name directly from the UploadedFile object
    file_name = file.name
    pattern = r".*?\.(.*?)$"
    match = re.search(pattern, file_name)
    if match:
        return match.group(1)
    else:
        raise ValueError(f"Unable to extract file extension from {file_name}")

# Normalize input as text from PDF and other formats
@st.cache_resource
def pdf2txt(docs):
    text = ""
    for file in docs:
        file_extension = extract_file_extension(file)
        st.write(f"File type extension: {file_extension}")
        if file_extension.lower() in ['py', 'txt', 'html', 'htm', 'xml', 'json']:
            text += file.getvalue().decode('utf-8')
        elif file_extension.lower() == 'pdf':
            from PyPDF2 import PdfReader
            pdf = PdfReader(BytesIO(file.getvalue()))
            for page in range(len(pdf.pages)):
                text += pdf.pages[page].extract_text() # new PyPDF2 syntax
    return text

def txt2chunks(text):
    text_splitter = CharacterTextSplitter(separator="\n", chunk_size=1000, chunk_overlap=200, length_function=len)
    return text_splitter.split_text(text)

# Vector Store using FAISS
@st.cache_resource
def vector_store(text_chunks):
    embeddings = OpenAIEmbeddings(openai_api_key=key)
    return FAISS.from_texts(texts=text_chunks, embedding=embeddings)

# Memory and Retrieval chains
@st.cache_resource
def get_chain(vectorstore):
    llm = ChatOpenAI()
    memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)
    return ConversationalRetrievalChain.from_llm(llm=llm, retriever=vectorstore.as_retriever(), memory=memory)

def process_user_input(user_question):
    response = st.session_state.conversation({'question': user_question})
    st.session_state.chat_history = response['chat_history']
    for i, message in enumerate(st.session_state.chat_history):
        template = user_template if i % 2 == 0 else bot_template
        st.write(template.replace("{{MSG}}", message.content), unsafe_allow_html=True)
        filename = generate_filename(user_question, 'txt')
        response = message.content
        user_prompt = user_question
        create_file(filename, user_prompt, response, should_save)       

def divide_prompt(prompt, max_length):
    words = prompt.split()
    chunks = []
    current_chunk = []
    current_length = 0
    for word in words:
        if len(word) + current_length <= max_length:
            current_length += len(word) + 1 
            current_chunk.append(word)
        else:
            chunks.append(' '.join(current_chunk))
            current_chunk = [word]
            current_length = len(word)
    chunks.append(' '.join(current_chunk))
    return chunks

    
# 13. Provide way of saving all and deleting all to give way of reviewing output and saving locally before clearing it
    
@st.cache_resource
def create_zip_of_files(files):
    zip_name = "all_files.zip"
    with zipfile.ZipFile(zip_name, 'w') as zipf:
        for file in files:
            zipf.write(file)
    return zip_name
    
@st.cache_resource
def get_zip_download_link(zip_file):
    with open(zip_file, 'rb') as f:
        data = f.read()
    b64 = base64.b64encode(data).decode()
    href = f'<a href="data:application/zip;base64,{b64}" download="{zip_file}">Download All</a>'
    return href

# 14. Inference Endpoints for Whisper (best fastest STT) on NVIDIA T4 and Llama (best fastest AGI LLM) on NVIDIA A10
# My Inference Endpoint
API_URL_IE = f'https://tonpixzfvq3791u9.us-east-1.aws.endpoints.huggingface.cloud'
# Original
API_URL_IE = "https://api-inference.huggingface.co/models/openai/whisper-small.en"
MODEL2 = "openai/whisper-small.en"
MODEL2_URL = "https://huggingface.co/openai/whisper-small.en"
#headers = {
#	"Authorization": "Bearer XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX",
#	"Content-Type": "audio/wav"
#}
# HF_KEY = os.getenv('HF_KEY')
HF_KEY = st.secrets['HF_KEY']
headers = {
    "Authorization": f"Bearer {HF_KEY}",
    "Content-Type": "audio/wav"
}

#@st.cache_resource
def query(filename):
    with open(filename, "rb") as f:
        data = f.read()
    response = requests.post(API_URL_IE, headers=headers, data=data)
    return response.json()

def generate_filename(prompt, file_type):
    central = pytz.timezone('US/Central')
    safe_date_time = datetime.now(central).strftime("%m%d_%H%M")
    replaced_prompt = prompt.replace(" ", "_").replace("\n", "_")
    safe_prompt = "".join(x for x in replaced_prompt if x.isalnum() or x == "_")[:90]
    return f"{safe_date_time}_{safe_prompt}.{file_type}"

# 15. Audio recorder to Wav file 
def save_and_play_audio(audio_recorder):
    audio_bytes = audio_recorder()
    if audio_bytes:
        filename = generate_filename("Recording", "wav")
        with open(filename, 'wb') as f:
            f.write(audio_bytes)
        st.audio(audio_bytes, format="audio/wav")
        return filename

# 16. Speech transcription to file output
def transcribe_audio(filename):
    output = query(filename)
    return output

def whisper_main():
    #st.title("Speech to Text")
    #st.write("Record your speech and get the text.")

    # Audio, transcribe, GPT:
    filename = save_and_play_audio(audio_recorder)
    if filename is not None:
        transcription = transcribe_audio(filename)
        try:
            transcript = transcription['text']
            st.write(transcript)

        except:
            transcript=''
            st.write(transcript)

        
        # Whisper to GPT: New!! ---------------------------------------------------------------------
        st.write('Reasoning with your inputs with GPT..')
        response = chat_with_model(transcript)
        st.write('Response:')
        st.write(response)

        filename = generate_filename(response, "txt")
        create_file(filename, transcript, response, should_save)
        # Whisper to GPT: New!! ---------------------------------------------------------------------
        
        
        # Whisper to Llama:
        response = StreamLLMChatResponse(transcript)
        filename_txt = generate_filename(transcript, "md")
        create_file(filename_txt, transcript, response, should_save)

        filename_wav = filename_txt.replace('.txt', '.wav')
        import shutil
        try: 
            if os.path.exists(filename):
                shutil.copyfile(filename, filename_wav)
        except:
            st.write('.')

        if os.path.exists(filename):
            os.remove(filename)

        #st.experimental_rerun()
        #except:
        #    st.write('Starting Whisper Model on GPU.  Please retry in 30 seconds.')



# Sample function to demonstrate a response, replace with your own logic
def StreamMedChatResponse(topic):
    st.write(f"Showing resources or questions related to: {topic}")



def add_medical_exam_buttons():
    # Medical exam terminology descriptions
    descriptions = {
        "White Blood Cells 🌊": "3 Q&A with emojis about types, facts, function, inputs and outputs of white blood cells 🎥",
        "CT Imaging🦠": "3 Q&A with emojis on CT Imaging post surgery, how to, what to look for 💊",
        "Hematoma 💉": "3 Q&A with emojis about hematoma and infection care and study including bacteria cultures and tests or labs💪",
        "Post Surgery Wound Care 🍌": "3 Q&A with emojis on wound care, and good bedside manner 🩸",
        "Healing and humor 💊": "3 Q&A with emojis on stories and humor about healing and caregiving 🚑",
        "Psychology of bedside manner 🧬": "3 Q&A with emojis on bedside manner and how to make patients feel at ease🛠",
        "CT scan 💊": "3 Q&A with analysis on infection using CT scan and packing for skin, cellulitus and fascia 🩺"
    }

    # Expander for medical topics
    with st.expander("Medical Licensing Exam Topics 📚", expanded=False):
        st.markdown("🩺 **Important**: Variety of topics for medical licensing exams.")

        # Create buttons for each description with unique keys
        for idx, (label, content) in enumerate(descriptions.items()):
            button_key = f"button_{idx}"
            if st.button(label, key=button_key):
                st.write(f"Running {label}")
                input='Create markdown outline for definition of topic ' + label + ' also short quiz with appropriate emojis and definitions for:  ' + content
                response=StreamLLMChatResponse(input)
                filename = generate_filename(response, 'txt')   
                create_file(filename, input, response, should_save)

def add_medical_exam_buttons2():
    with st.expander("Medical Licensing Exam Topics 📚", expanded=False):
        st.markdown("🩺 **Important**: This section provides a variety of medical topics that are often encountered in medical licensing exams.")

        # Define medical exam terminology descriptions
        descriptions = {
            "White Blood Cells 🌊": "3 Questions and Answers with emojis about white blood cells 🎥",
            "CT Imaging🦠": "3 Questions and Answers with emojis about CT Imaging of post surgery abscess, hematoma, and cerosanguiness fluid 💊",
            "Hematoma 💉": "3 Questions and Answers with emojis about hematoma and infection and how heat helps white blood cells 💪",
            "Post Surgery Wound Care 🍌": "3 Questions and Answers with emojis about wound care and how to help as a caregiver🩸",
            "Healing and humor 💊": "3 Questions and Answers with emojis on the use of stories and humor to help patients and family 🚑",
            "Psychology of bedside manner 🧬": "3 Questions and Answers with emojis  about good bedside manner 🛠",
            "CT scan 💊": "3 Questions and Answers with analysis of bacteria and understanding infection using cultures and CT scan 🩺"
        }

        # Create columns
        col1, col2, col3, col4 = st.columns([1, 1, 1, 1], gap="small")
        
        # Add buttons to columns
        if col1.button("Ultrasound with Doppler 🌊"):
            StreamLLMChatResponse(descriptions["Ultrasound with Doppler 🌊"])

        if col2.button("Oseltamivir 🦠"):
            StreamLLMChatResponse(descriptions["Oseltamivir 🦠"])

        if col3.button("IM Epinephrine 💉"):
            StreamLLMChatResponse(descriptions["IM Epinephrine 💉"])

        if col4.button("Hypokalemia 🍌"):
            StreamLLMChatResponse(descriptions["Hypokalemia 🍌"])

        col5, col6, col7, col8 = st.columns([1, 1, 1, 1], gap="small")

        if col5.button("Succinylcholine 💊"):
            StreamLLMChatResponse(descriptions["Succinylcholine 💊"])

        if col6.button("Phosphoinositol System 🧬"):
            StreamLLMChatResponse(descriptions["Phosphoinositol System 🧬"])

        if col7.button("Ramipril 💊"):
            StreamLLMChatResponse(descriptions["Ramipril 💊"])
        


# 17. Main
def main():
    prompt = f"Write ten funny jokes that are tweet length stories that make you laugh.  Show as markdown outline with emojis for each."
    # Add Wit and Humor buttons
    # add_witty_humor_buttons()
    # add_medical_exam_buttons()

    with st.expander("Prompts 📚", expanded=False):
        example_input = st.text_input("Enter your prompt text for Llama:", value=prompt, help="Enter text to get a response from DromeLlama.")
        if st.button("Run Prompt With Llama model", help="Click to run the prompt."):
            try:
                response=StreamLLMChatResponse(example_input)
                create_file(filename, example_input, response, should_save)
            except:
                st.write('Llama model is asleep. Starting now on A10 GPU.  Please wait one minute then retry.  KEDA triggered.')

        openai.api_key = os.getenv('OPENAI_API_KEY')
        if openai.api_key == None: openai.api_key = st.secrets['OPENAI_API_KEY']
        
        menu = ["txt", "htm", "xlsx", "csv", "md", "py"]
        choice = st.sidebar.selectbox("Output File Type:", menu)
        
        model_choice = st.sidebar.radio("Select Model:", ('gpt-3.5-turbo', 'gpt-3.5-turbo-0301'))        
        
        user_prompt = st.text_area("Enter prompts, instructions & questions:", '', height=100)
        collength, colupload = st.columns([2,3])  # adjust the ratio as needed
        with collength:
            max_length = st.slider("File section length for large files", min_value=1000, max_value=128000, value=12000, step=1000)
        with colupload:
            uploaded_file = st.file_uploader("Add a file for context:", type=["pdf", "xml", "json", "xlsx", "csv", "html", "htm", "md", "txt"])
        document_sections = deque()
        document_responses = {}
        if uploaded_file is not None:
            file_content = read_file_content(uploaded_file, max_length)
            document_sections.extend(divide_document(file_content, max_length))
        if len(document_sections) > 0:
            if st.button("👁️ View Upload"):
                st.markdown("**Sections of the uploaded file:**")
                for i, section in enumerate(list(document_sections)):
                    st.markdown(f"**Section {i+1}**\n{section}")
            st.markdown("**Chat with the model:**")
            for i, section in enumerate(list(document_sections)):
                if i in document_responses:
                    st.markdown(f"**Section {i+1}**\n{document_responses[i]}")
                else:
                    if st.button(f"Chat about Section {i+1}"):
                        st.write('Reasoning with your inputs...')
                        #response = chat_with_model(user_prompt, section, model_choice)
                        st.write('Response:')
                        st.write(response)
                        document_responses[i] = response
                        filename = generate_filename(f"{user_prompt}_section_{i+1}", choice)
                        create_file(filename, user_prompt, response, should_save)
                        st.sidebar.markdown(get_table_download_link(filename), unsafe_allow_html=True)

                        
        if st.button('💬 Chat'):
            st.write('Reasoning with your inputs...')
            user_prompt_sections = divide_prompt(user_prompt, max_length)
            full_response = ''
            for prompt_section in user_prompt_sections:
                response = chat_with_model(prompt_section, ''.join(list(document_sections)), model_choice)
                full_response += response + '\n'  # Combine the responses
            response = full_response
            st.write('Response:')
            st.write(response)
            filename = generate_filename(user_prompt, choice)
            create_file(filename, user_prompt, response, should_save)

    # Compose a file sidebar of markdown md files:
    all_files = glob.glob("*.md")
    all_files = [file for file in all_files if len(os.path.splitext(file)[0]) >= 10]  # exclude files with short names
    all_files.sort(key=lambda x: (os.path.splitext(x)[1], x), reverse=True)  # sort by file type and file name in descending order
    if st.sidebar.button("🗑 Delete All Text"):
        for file in all_files:
            os.remove(file)
        st.experimental_rerun()
    if st.sidebar.button("⬇️ Download All"):
        zip_file = create_zip_of_files(all_files)
        st.sidebar.markdown(get_zip_download_link(zip_file), unsafe_allow_html=True)
    file_contents=''
    next_action=''
    for file in all_files:
        col1, col2, col3, col4, col5 = st.sidebar.columns([1,6,1,1,1])  # adjust the ratio as needed
        with col1:
            if st.button("🌐", key="md_"+file):  # md emoji button
                with open(file, 'r') as f:
                    file_contents = f.read()
                    next_action='md'
        with col2:
            st.markdown(get_table_download_link(file), unsafe_allow_html=True)
        with col3:
            if st.button("📂", key="open_"+file):  # open emoji button
                with open(file, 'r') as f:
                    file_contents = f.read()
                    next_action='open'
        with col4:
            if st.button("🔍", key="read_"+file):  # search emoji button
                with open(file, 'r') as f:
                    file_contents = f.read()
                    next_action='search'
        with col5:
            if st.button("🗑", key="delete_"+file):
                os.remove(file)
                st.experimental_rerun()

                
    if len(file_contents) > 0:
        if next_action=='open':
            file_content_area = st.text_area("File Contents:", file_contents, height=500)
        if next_action=='md':
            st.markdown(file_contents)

            buttonlabel = '🔍Run with Llama and GPT.'
            if st.button(key='RunWithLlamaandGPT', label = buttonlabel):
                user_prompt = file_contents
                
                # Llama versus GPT Battle!
                all=""
                try:
                    st.write('🔍Running with Llama.')
                    response = StreamLLMChatResponse(file_contents)
                    filename = generate_filename(user_prompt, "md")
                    create_file(filename, file_contents, response, should_save)
                    all=response
                    #SpeechSynthesis(response)
                except:
                    st.markdown('Llama is sleeping.  Restart ETA 30 seconds.')
                
                # gpt
                try:
                    st.write('🔍Running with GPT.')
                    response2 = chat_with_model(user_prompt, file_contents, model_choice)
                    filename2 = generate_filename(file_contents, choice)
                    create_file(filename2, user_prompt, response, should_save)
                    all=all+response2
                    #SpeechSynthesis(response2)
                except:
                    st.markdown('GPT is sleeping.  Restart ETA 30 seconds.')
    
                SpeechSynthesis(all)

            
        if next_action=='search':
            file_content_area = st.text_area("File Contents:", file_contents, height=500)
            st.write('🔍Running with Llama and GPT.')

            user_prompt = file_contents
            
            # Llama versus GPT Battle!
            all=""
            try:
                st.write('🔍Running with Llama.')
                response = StreamLLMChatResponse(file_contents)
                filename = generate_filename(user_prompt, ".md")
                create_file(filename, file_contents, response, should_save)
                all=response
                #SpeechSynthesis(response)
            except:
                st.markdown('Llama is sleeping.  Restart ETA 30 seconds.')
            
            # gpt
            try:
                st.write('🔍Running with GPT.')
                response2 = chat_with_model(user_prompt, file_contents, model_choice)
                filename2 = generate_filename(file_contents, choice)
                create_file(filename2, user_prompt, response, should_save)
                all=all+response2
                #SpeechSynthesis(response2)
            except:
                st.markdown('GPT is sleeping.  Restart ETA 30 seconds.')

            SpeechSynthesis(all)
            

    # Function to encode file to base64
    def get_base64_encoded_file(file_path):
        with open(file_path, "rb") as file:
            return base64.b64encode(file.read()).decode()

    # Function to create a download link
    def get_audio_download_link(file_path):
        base64_file = get_base64_encoded_file(file_path)
        return f'<a href="data:file/wav;base64,{base64_file}" download="{os.path.basename(file_path)}">⬇️ Download Audio</a>'

    # Compose a file sidebar of past encounters
    all_files = glob.glob("*.wav")
    all_files = [file for file in all_files if len(os.path.splitext(file)[0]) >= 10]  # exclude files with short names
    all_files.sort(key=lambda x: (os.path.splitext(x)[1], x), reverse=True)  # sort by file type and file name in descending order

    filekey = 'delall'
    if st.sidebar.button("🗑 Delete All Audio", key=filekey):
        for file in all_files:
            os.remove(file)
        st.experimental_rerun()

    for file in all_files:
        col1, col2 = st.sidebar.columns([6, 1])  # adjust the ratio as needed
        with col1:
            st.markdown(file)
            if st.button("🎵", key="play_" + file):  # play emoji button
                audio_file = open(file, 'rb')
                audio_bytes = audio_file.read()
                st.audio(audio_bytes, format='audio/wav')
                #st.markdown(get_audio_download_link(file), unsafe_allow_html=True)
                #st.text_input(label="", value=file)
        with col2:
            if st.button("🗑", key="delete_" + file):
                os.remove(file)
                st.experimental_rerun()



    # Feedback
    # Step: Give User a Way to Upvote or Downvote
    GiveFeedback=False
    if GiveFeedback:
        with st.expander("Give your feedback 👍", expanded=False):
    
            feedback = st.radio("Step 8: Give your feedback", ("👍 Upvote", "👎 Downvote"))
            if feedback == "👍 Upvote":
                st.write("You upvoted 👍. Thank you for your feedback!")
            else:
                st.write("You downvoted 👎. Thank you for your feedback!")
                
            load_dotenv()
            st.write(css, unsafe_allow_html=True)
            st.header("Chat with documents :books:")
            user_question = st.text_input("Ask a question about your documents:")
            if user_question:
                process_user_input(user_question)
            with st.sidebar:
                st.subheader("Your documents")
                docs = st.file_uploader("import documents", accept_multiple_files=True)
                with st.spinner("Processing"):
                    raw = pdf2txt(docs)
                    if len(raw) > 0:
                        length = str(len(raw))
                        text_chunks = txt2chunks(raw)
                        vectorstore = vector_store(text_chunks)
                        st.session_state.conversation = get_chain(vectorstore)
                        st.markdown('# AI Search Index of Length:' + length + ' Created.')  # add timing
                        filename = generate_filename(raw, 'txt')
                        create_file(filename, raw, '', should_save)
    
    # Relocated!  Hope you like your new space - enjoy!
    # Display instructions and handle query parameters
    st.markdown("## Glossary Lookup\nEnter a term in the URL query, like `?q=Nanotechnology` or `?query=Martian Syndicate`.")
    try:
        query_params = st.query_params
        #query = (query_params.get('q') or query_params.get('query') or [''])[0]
        query = (query_params.get('q') or query_params.get('query') or [''])
        st.markdown('# Running query: ' + query)
        if query: search_glossary(query)
    except:
        st.markdown('No glossary lookup')

    # Display the glossary grid
    st.title("Transhuman Space Glossary 🌌")
    display_glossary_grid(transhuman_glossary)
    
    st.title("🌌🚀 Transhuman Space Encyclopedia")
    st.markdown("## Explore the universe of Transhuman Space through interactive storytelling and encyclopedic knowledge.🌠")
    
    display_buttons_with_scores()
    
    display_images_and_wikipedia_summaries()
    
    # Assuming the transhuman_glossary and other setup code remains the same
    #st.write("Current Query Parameters:", st.query_params)
    #st.markdown("### Query Parameters - These Deep Link Map to Remixable Methods, Navigate or Trigger Functionalities")
    
    # Example: Using query parameters to navigate or trigger functionalities
    if 'action' in st.query_params:
        action = st.query_params()['action'][0]  # Get the first (or only) 'action' parameter
        if action == 'show_message':
            st.success("Showing a message because 'action=show_message' was found in the URL.")
        elif action == 'clear':
            clear_query_params()
            st.experimental_rerun()
    
    # Handling repeated keys
    if 'multi' in st.query_params:
        multi_values = get_all_query_params('multi')
        st.write("Values for 'multi':", multi_values)
    
    # Manual entry for demonstration
    st.write("Enter query parameters in the URL like this: ?action=show_message&multi=1&multi=2")
    
    if 'query' in st.query_params:
        query = st.query_params['query'][0]  # Get the query parameter
        # Display content or image based on the query
        display_content_or_image(query)
    
    # Add a clear query parameters button for convenience
    if st.button("Clear Query Parameters", key='ClearQueryParams'):
        # This will clear the browser URL's query parameters
        st.experimental_set_query_params
        st.experimental_rerun()
                    
# 18. Run AI Pipeline
if __name__ == "__main__":
    whisper_main()
    main()