File size: 32,831 Bytes
0feea5d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "1e417d15",
   "metadata": {},
   "source": [
    "# **Explore GAIA Questions Data**\n",
    "\n",
    "Explore the `metadata.jsonl` file in order to gain a deeper comprehension of the dataset."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8a696d11",
   "metadata": {},
   "source": [
    "#### **Imports**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 183,
   "id": "d3e11d83",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import re\n",
    "import json\n",
    "import random\n",
    "import psycopg2\n",
    "import pandas as pd\n",
    "from collections import Counter, OrderedDict\n",
    "\n",
    "from dotenv import load_dotenv\n",
    "from huggingface_hub import login\n",
    "\n",
    "from langchain.schema import Document\n",
    "from langchain_community.retrievers import BM25Retriever\n",
    "from langchain.tools import Tool, StructuredTool\n",
    "from langchain_core.tools import tool\n",
    "from langchain_huggingface import HuggingFaceEmbeddings\n",
    "from langchain_community.vectorstores import SupabaseVectorStore\n",
    "\n",
    "from supabase import Client, create_client\n",
    "from supabase.client import ClientOptions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 194,
   "id": "17734566",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Number of QAs: 165\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'task_id': 'c61d22de-5f6c-4958-a7f6-5e9707bd3466',\n",
       " 'Question': 'A paper about AI regulation that was originally submitted to arXiv.org in June 2022 shows a figure with three axes, where each axis has a label word at both ends. Which of these words is used to describe a type of society in a Physics and Society article submitted to arXiv.org on August 11, 2016?',\n",
       " 'Level': 2,\n",
       " 'Final answer': 'egalitarian',\n",
       " 'file_name': '',\n",
       " 'Annotator Metadata': {'Steps': '1. Go to arxiv.org and navigate to the Advanced Search page.\\n2. Enter \"AI regulation\" in the search box and select \"All fields\" from the dropdown.\\n3. Enter 2022-06-01 and 2022-07-01 into the date inputs, select \"Submission date (original)\", and submit the search.\\n4. Go through the search results to find the article that has a figure with three axes and labels on each end of the axes, titled \"Fairness in Agreement With European Values: An Interdisciplinary Perspective on AI Regulation\".\\n5. Note the six words used as labels: deontological, egalitarian, localized, standardized, utilitarian, and consequential.\\n6. Go back to arxiv.org\\n7. Find \"Physics and Society\" and go to the page for the \"Physics and Society\" category.\\n8. Note that the tag for this category is \"physics.soc-ph\".\\n9. Go to the Advanced Search page.\\n10. Enter \"physics.soc-ph\" in the search box and select \"All fields\" from the dropdown.\\n11. Enter 2016-08-11 and 2016-08-12 into the date inputs, select \"Submission date (original)\", and submit the search.\\n12. Search for instances of the six words in the results to find the paper titled \"Phase transition from egalitarian to hierarchical societies driven by competition between cognitive and social constraints\", indicating that \"egalitarian\" is the correct answer.',\n",
       "  'Number of steps': '12',\n",
       "  'How long did this take?': '8 minutes',\n",
       "  'Tools': '1. Web browser\\n2. Image recognition tools (to identify and parse a figure with three axes)',\n",
       "  'Number of tools': '2'}}"
      ]
     },
     "execution_count": 194,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "with open(\"metadata.jsonl\") as dataset_file:\n",
    "    json_list = list(dataset_file)\n",
    "\n",
    "QAs = [json.loads(qa) for qa in json_list]\n",
    "print(f\"Number of QAs: {len(QAs)}\")\n",
    "QAs[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "id": "40328df2",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "TaskId: 7a4a336d-dcfa-45a0-b014-824c7619e8de\n",
      "Level: 2\n",
      "Question: At the two-minute mark in the YouTube video uploaded by the channel “GameGrumps” on May 14, 2017 as part of their playthrough of the game Mario Kart 8 Deluxe, the shows’ hosts are competing on one of the game’s racetracks. What was the world record time for that track in the game’s 150cc mode as of June 7, 2023? Express your answer in minutes and seconds, rounding the seconds to the nearest hundredth, e.g. 1:01.001.\n",
      "Ground Truth: 1:41.614\n",
      "Additional file: \n",
      "Annotator Metadata:\n",
      " - Steps:\n",
      "    1. Search the web for “gamegrumps mario kart 8 deluxe may 14 2017”.\n",
      "    2. Click on the YouTube video result.\n",
      "    3. Navigate to two minutes into the video.\n",
      "    4. Scroll further back until I see the name of the racecourse, Yoshi Circuit.\n",
      "    5. Search the web for “mario kart 8 deluxe yoshi circuit world record 150cc”\n",
      "    6. Scroll down until I find a reliable world record listing site.\n",
      "    7. Navigate through the site until I find the record that meets the specified criteria.\n",
      "    8. Read the date the record was set to confirm that it applies to the question’s specified date.\n",
      " - Number of steps: 8\n",
      " - How long did this take: 5-10 minutes\n",
      " - Tools [4]:\n",
      "    1. Search engine\n",
      "    2. Web browser\n",
      "    3. YouTube\n",
      "    4. OCR\n",
      "- Number of tools: 4\n"
     ]
    }
   ],
   "source": [
    "random_samples = random.sample(QAs, 1)\n",
    "for samp in random_samples:\n",
    "    print(\n",
    "        f\"TaskId: {samp['task_id']}\\nLevel: {samp['Level']}\\n\"\n",
    "        f\"Question: {samp['Question']}\\nGround Truth: {samp['Final answer']}\\n\"\n",
    "        f\"Additional file: {samp['file_name']}\"\n",
    "    )\n",
    "    print(\"Annotator Metadata:\")\n",
    "    print(\" - Steps:\")\n",
    "    metadata = samp['Annotator Metadata']\n",
    "    steps = metadata['Steps'].split(\"\\n\")\n",
    "    for step in steps:\n",
    "        print(f\"    {step}\")\n",
    "    print(f\" - Number of steps: {metadata['Number of steps']}\")\n",
    "    print(f\" - How long did this take: {metadata['How long did this take?']}\")\n",
    "    tools = metadata['Tools'].split(\"\\n\")\n",
    "    print(f\" - Tools [{len(tools)}]:\")\n",
    "    for t in tools:\n",
    "        print(f\"    {t}\")\n",
    "    print(f\"- Number of tools: {metadata['Number of tools']}\")\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "52ca1954",
   "metadata": {},
   "source": [
    "As we can see, the `Dataset` contains:\n",
    "\n",
    "- **task_id** : The unique identifier for the task\n",
    "\n",
    "- **Level** : Difficulty level of the GAIA task\n",
    "\n",
    "- **Question** : The specific GAIA task\n",
    "\n",
    "- **Final answer** : The ground truth for the GAIA task\n",
    "\n",
    "- **file_name** : The additional file related to the task\n",
    "\n",
    "- **Annotator Metadata** : \n",
    "\n",
    "    - **Steps** : The **sequence** of steps followed to accomplish the correct answer\n",
    "\n",
    "    - **Number of steps** : Total number of steps to accomplish the correct answer\n",
    "\n",
    "    - **Tools** : The list of `tools` used to answer the question/task\n",
    "\n",
    "    - **Number of tools** : Total number of tools used"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ccc5f181",
   "metadata": {},
   "source": [
    "**GAIA Agent** must be an `Agentic RAG`. This way the agent will be able to combine retrieval system, accessing the QAs `dataset`."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bfe371b8",
   "metadata": {},
   "source": [
    "#### **Explore Dataset Tools Types**\n",
    "\n",
    "Since the *`dataset`* provides for each question a list of `Tools` used to reaching the final answer, it is useful to explore these tools in order to define an efficient and relevant set of tools for our agent to incorporate:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 169,
   "id": "f470a028",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Total number of Tools used in entire set: 55\n",
      "Tools used in QAs:\n"
     ]
    },
    {
     "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>Tool</th>\n",
       "      <th>Count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>SEARCH ENGINE</td>\n",
       "      <td>35</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>CALCULATOR</td>\n",
       "      <td>33</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>WEB BROWSER</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>NE</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>IMAGE RECOGNITION TOOLS</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>PDF VIEWER</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>A CALCULATOR</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>OCR</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>VIDEO RECOGNITION TOOLS</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>MICROSOFT EXCEL</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>PDF ACCESS</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>MICROSOFT EXCEL / GOOGLE SHEETS</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>IMAGE RECOGNITION</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>A SPEECH-TO-TEXT TOOL</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>A SEARCH ENGINE</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>IMAGE RECOGNITION/OCR</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>GOOGLE MAPS</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>SPREADSHEET EDITOR</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>TOOLS REQUIRED</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>B BROWSER</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                               Tool  Count\n",
       "0                     SEARCH ENGINE     35\n",
       "1                        CALCULATOR     33\n",
       "2                       WEB BROWSER     12\n",
       "3                                NE      9\n",
       "4           IMAGE RECOGNITION TOOLS      8\n",
       "5                        PDF VIEWER      6\n",
       "6                      A CALCULATOR      5\n",
       "7                               OCR      3\n",
       "8           VIDEO RECOGNITION TOOLS      3\n",
       "9                   MICROSOFT EXCEL      2\n",
       "10                       PDF ACCESS      2\n",
       "11  MICROSOFT EXCEL / GOOGLE SHEETS      2\n",
       "12                IMAGE RECOGNITION      2\n",
       "13            A SPEECH-TO-TEXT TOOL      2\n",
       "14                  A SEARCH ENGINE      1\n",
       "15            IMAGE RECOGNITION/OCR      1\n",
       "16                      GOOGLE MAPS      1\n",
       "17               SPREADSHEET EDITOR      1\n",
       "18                   TOOLS REQUIRED      1\n",
       "19                        B BROWSER      1"
      ]
     },
     "execution_count": 169,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tools_qa = []\n",
    "for qa in QAs:\n",
    "    for t in qa[\"Annotator Metadata\"][\"Tools\"].split(\"\\n\"):\n",
    "        tool_qa = t[2:].strip().upper()\n",
    "        tool_qa = re.sub(r\"\\s*\\([^)]*\\)\\s*\", \"\", tool_qa)\n",
    "    tools_qa.append(tool_qa)\n",
    "tools_counter = OrderedDict(Counter(tools_qa))\n",
    "\n",
    "print(f\"Total number of Tools used in entire set: {len(tools_counter)}\")\n",
    "print(\"Tools used in QAs:\")\n",
    "df = pd.DataFrame(\n",
    "    list(tools_counter.items()), columns = [\"Tool\", \"Count\"]\n",
    "    ).sort_values(\"Count\", ascending = False)\\\n",
    "    .reset_index(drop = True)\n",
    "df.head(20)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "15be46b0",
   "metadata": {},
   "source": [
    "#### **Tools to be Implemented**\n",
    "\n",
    "- `Search Engine` (arXiv, Wikipedia, DuckDuckGo)\n",
    "\n",
    "- `Calculator` (add, substract, divide, multiply, modulus, etc.)\n",
    "\n",
    "- `Access` and `Download Files` from Web\n",
    "\n",
    "- `Excel`/`Google Sheets`: Process Downloaded files"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e7cec064",
   "metadata": {},
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5ea41219",
   "metadata": {},
   "source": [
    "## **Project Structure: GAIA Agent**\n",
    "\n",
    "In order to implement our agent within a `Hugging Face Space`, as a structured `Python` project, ensuring clean and modular code organized in different functionalities it is recommended to use separate files. For instance the structure would be:\n",
    "\n",
    "- `tools.py` - To provide the auxiliary tools for the GAIA Agent\n",
    "\n",
    "- `retriever.py` - To implement the retrieval functions to support acces to the knowledge base (*dataset*)\n",
    "\n",
    "- `agent.py` - To implement the agent\n",
    "\n",
    "- `app.py` - To integrate all the components into a fully functional agent"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "62e07469",
   "metadata": {},
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "31ede212",
   "metadata": {},
   "source": [
    "## **Dataset Loading and Dataset**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "81c53670",
   "metadata": {},
   "outputs": [],
   "source": [
    "docs = [\n",
    "    Document(\n",
    "        page_content = \"\\n\".join([\n",
    "            f\"Question: {qa['Question']}\",\n",
    "            f\"Final answer: {qa['Final answer']}\",\n",
    "            # f\"file_name: {qa['file_name']}\",\n",
    "            # f\"Annotator Metadata: {qa['Annotator Metadata']}\"\n",
    "        ]),\n",
    "        metadata = {\"task_id\": qa[\"task_id\"], \"level\": qa['Level']}\n",
    "    )\n",
    "    for qa in QAs\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "44d0020e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Document(metadata={'task_id': 'c61d22de-5f6c-4958-a7f6-5e9707bd3466', 'level': 2}, page_content='Question: A paper about AI regulation that was originally submitted to arXiv.org in June 2022 shows a figure with three axes, where each axis has a label word at both ends. Which of these words is used to describe a type of society in a Physics and Society article submitted to arXiv.org on August 11, 2016?\\nFinal answer: egalitarian')"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "docs[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dd2479f3",
   "metadata": {},
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a9bf2b7f",
   "metadata": {},
   "source": [
    "## **Retrival Tool Creation**\n",
    "\n",
    "There are $2$ options for this:\n",
    "\n",
    "1. ***Semantic Search*** - `BM25Retriever`\n",
    "2. ***Vector Search*** - \n",
    "\n",
    "Let's explore both with the following methods and tools:\n",
    "\n",
    "- **Semantic Search**: `BM25Retriever`\n",
    "- **Vector Search**: `bge-base-en-v1.5` for Embeddings and `Supabase` as *Vector Store*"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "27ae6dcc",
   "metadata": {},
   "source": [
    "### **Retriever for Semantic Search**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "920ba41c",
   "metadata": {},
   "outputs": [],
   "source": [
    "bm25_retriever = BM25Retriever.from_documents(documents = docs)\n",
    "bm25_retriever.k = 3\n",
    "\n",
    "# @tool(parse_docstring = True)\n",
    "def retrieve_semantic(query: str) -> str:\n",
    "    \"\"\"\n",
    "    Retrieves information about QA's based on semantic search.\n",
    "\n",
    "    Args:\n",
    "        query (str): The user query.\n",
    "\n",
    "    Returns:\n",
    "        str: The result of the semantic search\n",
    "    \"\"\"\n",
    "    res = bm25_retriever.invoke(query)\n",
    "    if res:\n",
    "        return \"\\n\\n\".join([doc.page_content for doc in res])\n",
    "    else: \n",
    "        return \"No matching information found.\"\n",
    "\n",
    "tool_retrieve_semantic = StructuredTool.from_function(\n",
    "    retrieve_semantic\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "d69970f1",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Question: A paper about AI regulation that was originally submitted to arXiv.org in June 2022 shows a figure with three axes, where each axis has a label word at both ends. Which of these words is used to describe a type of society in a Physics and Society article submitted to arXiv.org on August 11, 2016?\n",
      "Final answer: egalitarian\n",
      "\n",
      "Question: An office held a Secret Santa gift exchange where each of its twelve employees was assigned one other employee in the group to present with a gift. Each employee filled out a profile including three likes or hobbies. On the day of the gift exchange, only eleven gifts were given, each one specific to one of the recipient's interests. Based on the information in the document, who did not give a gift?\n",
      "Final answer: Fred\n",
      "\n",
      "Question: On June 6, 2023, an article by Carolyn Collins Petersen was published in Universe Today. This article mentions a team that produced a paper about their observations, linked at the bottom of the article. Find this paper. Under what NASA award number was the work performed by R. G. Arendt supported by?\n",
      "Final answer: 80GSFC21M0002\n",
      "Question: A paper about AI regulation that was originally submitted to arXiv.org in June 2022 shows a figure with three axes, where each axis has a label word at both ends. Which of these words is used to describe a type of society in a Physics and Society article submitted to arXiv.org on August 11, 2016?\n",
      "Final answer: egalitarian\n",
      "\n",
      "Question: An office held a Secret Santa gift exchange where each of its twelve employees was assigned one other employee in the group to present with a gift. Each employee filled out a profile including three likes or hobbies. On the day of the gift exchange, only eleven gifts were given, each one specific to one of the recipient's interests. Based on the information in the document, who did not give a gift?\n",
      "Final answer: Fred\n",
      "\n",
      "Question: On June 6, 2023, an article by Carolyn Collins Petersen was published in Universe Today. This article mentions a team that produced a paper about their observations, linked at the bottom of the article. Find this paper. Under what NASA award number was the work performed by R. G. Arendt supported by?\n",
      "Final answer: 80GSFC21M0002\n"
     ]
    }
   ],
   "source": [
    "# Comparing outputs\n",
    "print(tool_retrieve_semantic.invoke(QAs[0]['Question']))\n",
    "print(retrieve_semantic(QAs[0]['Question']))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fbb40ebd",
   "metadata": {},
   "source": [
    "### **Retriever for Vector Search**\n",
    "\n",
    "For this we must create:\n",
    "- **Table** in `supabase` with extension for `pgvector`\n",
    "- RLS for security"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "d152a0b0",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Logging to HF for downloading Embedding Model\n",
    "\n",
    "load_dotenv()\n",
    "hf_token = os.getenv(\"HF_API_TOKEN\")\n",
    "if hf_token:\n",
    "    login(token = hf_token)\n",
    "else:\n",
    "    print(\"Warning: No Hugging Face token found.\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "e379ef2c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "768"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# MODEL_NAME = \"sentence-transformers/all-mpnet-base-v2\"\n",
    "MODEL_NAME = \"BAAI/bge-base-en-v1.5\"\n",
    "embedding_model = HuggingFaceEmbeddings(model_name = MODEL_NAME)\n",
    "model = embedding_model._client\n",
    "dim = model.get_sentence_embedding_dimension()\n",
    "dim"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "612935dd",
   "metadata": {},
   "source": [
    "#### **Supabase (Postgresql) Table Creation**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 170,
   "id": "ef54ff9f",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create postgresql connection\n",
    "conn = psycopg2.connect(\n",
    "    host = os.getenv(\"SUPABASE_DB_HOST\"),\n",
    "    port = os.getenv(\"SUPABASE_DB_PORT\"),\n",
    "    dbname = os.getenv(\"SUPABASE_DB_NAME\"),\n",
    "    user = os.getenv(\"SUPABASE_DB_USER\"),\n",
    "    password = os.getenv(\"SUPABASE_DB_PASSWORD\")\n",
    ")\n",
    "conn.autocommit = True\n",
    "cursor = conn.cursor()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 171,
   "id": "13d1774e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Table documents_tbl' successfully created and ready to insert embeddings.\n"
     ]
    }
   ],
   "source": [
    "TBL_NAME = \"documents_tbl\"\n",
    "create_table = f\"\"\"\n",
    "DROP TABLE IF EXISTS {TBL_NAME};\n",
    "CREATE TABLE IF NOT EXISTS {TBL_NAME} (\n",
    "    id BIGINT GENERATED ALWAYS AS IDENTITY PRIMARY KEY,\n",
    "    content TEXT,\n",
    "    metadata JSONB,\n",
    "    embedding VECTOR({dim})\n",
    ");\n",
    "\"\"\"\n",
    "try:\n",
    "    cursor.execute(\"CREATE SCHEMA IF NOT EXISTS extensions;\")\n",
    "    cursor.execute(\"CREATE EXTENSION IF NOT EXISTS vector WITH SCHEMA extensions;\")\n",
    "    cursor.execute(create_table)\n",
    "    cursor.execute(f\"ALTER TABLE {TBL_NAME} ENABLE ROW LEVEL SECURITY;\")\n",
    "    print(f\"Table {TBL_NAME}' successfully created and ready to insert embeddings.\")\n",
    "except Exception as e:\n",
    "    conn.rollback()\n",
    "    print(\"Couldn't create the Postgresql table. Error: {e}\")\n",
    "    raise e\n",
    "\n",
    "cursor.execute(f\"\"\"\n",
    "    DROP POLICY IF EXISTS \"Allow read to all\" ON {TBL_NAME};\n",
    "\"\"\")\n",
    "\n",
    "cursor.execute(f\"\"\"\n",
    "CREATE POLICY \"Allow read to all\"\n",
    "ON {TBL_NAME}\n",
    "FOR SELECT\n",
    "USING (true);\n",
    "\"\"\")\n",
    "# cursor.close()\n",
    "# conn.close()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "667f0966",
   "metadata": {},
   "source": [
    "#### **Function to Seach Documents in Supabase**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 172,
   "id": "d0fc9a37",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_func_def = f\"\"\"\n",
    "CREATE FUNCTION match_documents (\n",
    "    query_embedding VECTOR({dim}),\n",
    "    filter JSONB DEFAULT '{{}}',\n",
    "    match_count INT DEFAULT 5\n",
    ") RETURNS TABLE (\n",
    "    id BIGINT,\n",
    "    content TEXT,\n",
    "    metadata JSONB,\n",
    "    similarity FLOAT\n",
    ") LANGUAGE plpgsql\n",
    "SET search_path = 'extensions', 'public'\n",
    "AS $$\n",
    "BEGIN\n",
    "    RETURN QUERY\n",
    "    SELECT\n",
    "        {TBL_NAME}.id,\n",
    "        {TBL_NAME}.content,\n",
    "        {TBL_NAME}.metadata,\n",
    "        1 - ({TBL_NAME}.embedding <=> query_embedding) AS similarity\n",
    "    FROM {TBL_NAME}\n",
    "    WHERE {TBL_NAME}.metadata @> filter\n",
    "    ORDER BY {TBL_NAME}.embedding <=> query_embedding\n",
    "    LIMIT match_count;\n",
    "END;\n",
    "$$;\n",
    "\"\"\"\n",
    "\n",
    "cursor.execute(\"DROP FUNCTION IF EXISTS match_documents(VECTOR, JSONB, INT);\")\n",
    "cursor.execute(df_func_def)\n",
    "cursor.execute(f\"GRANT SELECT ON {TBL_NAME} TO anon;\")\n",
    "cursor.execute(\"GRANT EXECUTE ON FUNCTION match_documents(VECTOR, JSONB, INT) TO service_role;\")\n",
    "cursor.execute(\"GRANT EXECUTE ON FUNCTION match_documents(VECTOR, JSONB, INT) TO anon;\")\n",
    "\n",
    "cursor.close()\n",
    "conn.close()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8f8345e4",
   "metadata": {},
   "source": [
    "#### **Data Insertion into Supabase Table**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 173,
   "id": "16cd7045",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Embedding first 5 dims: [0.006851373240351677, 0.019783932715654373, -0.005305973347276449, 0.04809008538722992, 0.03095371648669243]\n"
     ]
    }
   ],
   "source": [
    "docs_qa = []\n",
    "for i, qa in enumerate(QAs):\n",
    "    question = qa.get(\"Question\", \"\").strip()\n",
    "    final_answer = qa.get(\"Final answer\", \"\").strip()\n",
    "    additional_file = qa.get(\"file_name\")\n",
    "    has_file = additional_file != \"\"\n",
    "\n",
    "    content = f\"Question: {question}\\n\\nAdditional file: {additional_file}\\n\\nFinal answer: {final_answer}\"\n",
    "    embedding = embedding_model.embed_query(content)\n",
    "    doc_qa = {\n",
    "        \"content\": content,\n",
    "        \"metadata\": {\n",
    "            \"task_id\": qa.get(\"task_id\"),\n",
    "            \"has_file\": has_file\n",
    "        },\n",
    "        \"embedding\": embedding\n",
    "    }\n",
    "\n",
    "    if i == 0:\n",
    "        print(f\"Embedding first 5 dims: {embedding[:5]}\")\n",
    "    \n",
    "    docs_qa.append(doc_qa)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1278686d",
   "metadata": {},
   "source": [
    "Intantiate **Supabase** `Client`:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 174,
   "id": "edc9e4f5",
   "metadata": {},
   "outputs": [],
   "source": [
    "supabase_url = os.environ.get(\"SUPABASE_URL\")\n",
    "supabase_key = os.environ.get(\"SUPABASE_KEY\")\n",
    "supabase_anon_key = os.environ.get(\"SUPABASE_ANON_KEY\")\n",
    "supabase: Client = create_client(\n",
    "    supabase_url, supabase_key,\n",
    "    options = ClientOptions(\n",
    "        schema = \"public\"\n",
    "    )\n",
    ")\n",
    "\n",
    "supabase_public: Client = create_client(\n",
    "    supabase_url, supabase_anon_key,\n",
    "    options = ClientOptions(\n",
    "        schema = \"public\"\n",
    "    )\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6699531f",
   "metadata": {},
   "source": [
    "Upload *Documents* to the `Vector Database` (*Supabase*):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 175,
   "id": "52df5e9a",
   "metadata": {},
   "outputs": [],
   "source": [
    "try: \n",
    "    res = (\n",
    "        supabase\n",
    "        .table(TBL_NAME)\n",
    "        .insert(docs_qa)\n",
    "        .execute()\n",
    "    )\n",
    "    if len(res.data) != len(docs):\n",
    "        print(f\"Warning: Only {len(res.data)} out of {len(docs)} docs were inserted.\")\n",
    "except Exception as e:\n",
    "    print(f\"Error inserting documents into Supabase:\\n{e}\")\n",
    "    raise"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "592f110d",
   "metadata": {},
   "source": [
    "#### **Supabase Vector Store**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "id": "3684e86d",
   "metadata": {},
   "outputs": [],
   "source": [
    "vector_store = SupabaseVectorStore(\n",
    "    client = supabase_public,\n",
    "    embedding = embedding_model,\n",
    "    table_name = TBL_NAME,\n",
    "    query_name = \"match_documents\"\n",
    ")\n",
    "vector_retriever = vector_store.as_retriever()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 176,
   "id": "459d8049",
   "metadata": {},
   "outputs": [],
   "source": [
    "vector_store = SupabaseVectorStore(\n",
    "    client = supabase,\n",
    "    embedding = embedding_model,\n",
    "    table_name = TBL_NAME,\n",
    "    query_name = \"match_documents\"\n",
    ")\n",
    "vector_retriever = vector_store.as_retriever()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 177,
   "id": "5cfb08cf",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Question:\n",
      "What is the surname of the equine veterinarian mentioned in 1.E Exercises from the chemistry materials licensed by Marisa Alviar-Agnew & Henry Agnew under the CK-12 license in LibreText's Introductory Chemistry materials as compiled 08/21/2023?\n",
      "\n",
      "Answer:\n",
      "Louvrier\n"
     ]
    }
   ],
   "source": [
    "r_samp = random.sample(QAs, 1)[0]\n",
    "query = r_samp['Question']\n",
    "r_ans = r_samp['Final answer']\n",
    "\n",
    "print(f\"Question:\\n{query}\\n\\nAnswer:\\n{r_ans}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 178,
   "id": "539c374b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Document(metadata={'task_id': 'cabe07ed-9eca-40ea-8ead-410ef5e83f91', 'has_file': False}, page_content=\"Question: What is the surname of the equine veterinarian mentioned in 1.E Exercises from the chemistry materials licensed by Marisa Alviar-Agnew & Henry Agnew under the CK-12 license in LibreText's Introductory Chemistry materials as compiled 08/21/2023?\\n\\nAdditional file: \\n\\nFinal answer: Louvrier\")"
      ]
     },
     "execution_count": 178,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cntx = vector_retriever.invoke(query)\n",
    "cntx[0]"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.13.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}