jeevan commited on
Commit
8da9c1e
1 Parent(s): 416fc9c
Tasks/Task 1/Task1.md CHANGED
@@ -190,9 +190,7 @@ Experimented with above chunking strategy and found that `RecursiveCharacterText
190
 
191
  The quality of generation is directly proportional to the quality of the retrieval and at the same time we wanted to choose smaller model that is performant. I choose to use the `snowflake-arctic-embed-l` embedding model as it is small with 334 Million parameter with 1024 dimension support. Currently it is at 27 rank the MTEB leader board which suggest to me that it is efficient competing with other large models.
192
 
193
- ====
194
-
195
- Your response effectively breaks down the documents and uses a clear, methodical approach to answering the task. However, to enhance the response further, consider the following improvements:
196
 
197
  ### 1. **Aligning Chunking Strategy with Context**
198
  - **Current Strategy**: You mention using `RecursiveCharacterTextSplitter` and `SemanticChunker`, which is a good start.
 
190
 
191
  The quality of generation is directly proportional to the quality of the retrieval and at the same time we wanted to choose smaller model that is performant. I choose to use the `snowflake-arctic-embed-l` embedding model as it is small with 334 Million parameter with 1024 dimension support. Currently it is at 27 rank the MTEB leader board which suggest to me that it is efficient competing with other large models.
192
 
193
+ # Consolidation
 
 
194
 
195
  ### 1. **Aligning Chunking Strategy with Context**
196
  - **Current Strategy**: You mention using `RecursiveCharacterTextSplitter` and `SemanticChunker`, which is a good start.
Tasks/Task 1/pre-processing.ipynb CHANGED
@@ -699,481 +699,481 @@
699
  },
700
  {
701
  "cell_type": "code",
702
- "execution_count": 25,
703
  "metadata": {},
704
  "outputs": [
705
  {
706
  "data": {
707
  "text/plain": [
708
- "['dd370438231c41dbb7b1b4f1e7673cf7',\n",
709
- " '02ebba25e01941849b9e2c9d5097b55d',\n",
710
- " '099f0083356a4914b53fcb30df633b50',\n",
711
- " 'f8aefa25a4544c869ca4caaf686b3d47',\n",
712
- " '9ec0798fb4554f95ab65bd05315af118',\n",
713
- " '33bdad4db0ab4145b85726f77f1789ad',\n",
714
- " '98a75a601b114b07953b5aef4e032b4a',\n",
715
- " '1e49952c0d6743ba8ad52a049c18daa3',\n",
716
- " 'c3babb9205e54ca99ba6e5a03679bdba',\n",
717
- " '74cecdae132c4a5e953bd7e72ac6850e',\n",
718
- " '29529ea9530541a0bb446a8e82fab913',\n",
719
- " '4193dcf34f6249b1a29c49a52239deef',\n",
720
- " '84cb5d0f2cee47beabd72baa54161155',\n",
721
- " '622f279ac5bd40b082725d90972e9ae3',\n",
722
- " '48e366f92aa449e89cf7158584d2cf6a',\n",
723
- " 'e2ffb7cb2ac3482fb9290940fabe9582',\n",
724
- " 'f52a4c3353544fff93f241cba063028a',\n",
725
- " '0c81aa08ddd4496a9aaea4b001f3596c',\n",
726
- " '3e9d8d7785b04d5fad063219c94ef0dd',\n",
727
- " '76796785c7b64d428e48b7cf699e155a',\n",
728
- " '593ab20fc2494634959b0bfd8821ea91',\n",
729
- " '654421ae91df4739bfb1ebdfb7c9dda2',\n",
730
- " '27ffe059aafd4d5fa795b2f893b1d57e',\n",
731
- " 'f1468d8276444858acb33bd6e2d36e73',\n",
732
- " '5a6a15255cdd438abd9b2c3358dca939',\n",
733
- " 'fbb13ef430ca47d28013dda9feaf4625',\n",
734
- " 'fc16826ddd504038bb5f32fd97cdd98e',\n",
735
- " '72c878c56d8746dea51fdcf506e48894',\n",
736
- " '257ac1e04a4b478ab3b84c81e5dfc3f4',\n",
737
- " '68b157c05ced46828ac39894e69b8d08',\n",
738
- " '535e59df03184e86b30a09cd2d169dcd',\n",
739
- " '1a6d76252d364a758564a41b922d44a4',\n",
740
- " '61e497e66868447988198ba831096707',\n",
741
- " 'dd9f18bedfed443c8bed0fc4c34c5e23',\n",
742
- " '0ca0575097c24b50a613d5a19de61cfc',\n",
743
- " '7dfba6cbbfe34756ba3f40b1be282324',\n",
744
- " 'e9b68e9579194b04ad65bbf85332d351',\n",
745
- " '7545cee6d2e345ba90e95082a15271b8',\n",
746
- " 'df1e9db6843a4ddbb788b1e9117db9a1',\n",
747
- " 'bb0687d2f3d047138d0414d0b2a22917',\n",
748
- " 'b79ed7024a064c1f9360692c93615657',\n",
749
- " '70fb8aa096a74d0a975705ac44f08577',\n",
750
- " '41bf93d83ebe414e91253e7a96f50ec7',\n",
751
- " 'bdab13de5b514bf68921751b3051ce60',\n",
752
- " 'ccd47e89a09c4519981dc5d9be7b1ad9',\n",
753
- " '334ac2db387848f1829e174c6584288b',\n",
754
- " '5484df8c41cb41babd01c3f8d62121a2',\n",
755
- " 'dd1f97aef70e439ea02c8f0d0ea397e0',\n",
756
- " '99ccff600f8b4470af445f1f060e5518',\n",
757
- " 'd4de01e6623741d3b06c8ee973ad6670',\n",
758
- " '6217b664cbba4a64bf6e4f2ffde27831',\n",
759
- " '3974c50b7e3a4503925f1c397254d259',\n",
760
- " '4959c05e7d8049a4b75cff3bdc6fc30d',\n",
761
- " '9d3aeacd6513463fbe9d13c1fb2441fc',\n",
762
- " '8777904b546e4ef5b2759f0a60fd1fca',\n",
763
- " '7a73c81712804111b6145b57888455ae',\n",
764
- " '87036e89882546b69613378b17610332',\n",
765
- " '5c508cd4449449c486b811d65b9b6db1',\n",
766
- " 'fd5a25bb9038481aabaed2b34a7f2cc9',\n",
767
- " '80b47526b0224fc0ba54cf4a61da11cc',\n",
768
- " 'a2c5d0697278407fb0d89c9c138bfba0',\n",
769
- " '49cb7eb52ea043f2baf21b611709d83a',\n",
770
- " '96d002f0aa0a4cd7a86b188ef7811e9e',\n",
771
- " 'd5a4fd354f904b99a8700363f7bcec7d',\n",
772
- " 'ec384dfa0a5d4caeab593a4d013e40de',\n",
773
- " 'b613bc8f681141249d11f2eea7691f32',\n",
774
- " '7b9e491ad88b48f19ce2698c4d8ef5ec',\n",
775
- " '011946a9fed74b14b7d4be2ff4eaadf5',\n",
776
- " '2c07a4769e85425a9a32a053f1293ff2',\n",
777
- " 'c859a58fd5a54447a22217564e610e77',\n",
778
- " '2d6fcf19e009459e82b344a699c6556f',\n",
779
- " '22ec0544ffc44be1bd557cd91e96caf4',\n",
780
- " '1a9fed777bc8454faed8c60a12dce190',\n",
781
- " '898d974afb3f472a96c9cca3c698fee1',\n",
782
- " '21cb161a28f34fc89b90b369d1895fd6',\n",
783
- " '9409c811bf6542feae01351580bcb32b',\n",
784
- " '1219e011429b4e29a84268bdbb66d7a3',\n",
785
- " '3293d7aeecf54778a4b1e63f09f3f362',\n",
786
- " '543f56abfcda469a826e797aa2a4ae36',\n",
787
- " 'b714fd2157d145658860f0db0bd95163',\n",
788
- " '8be2abe5fee54507a03f0a5d0ba2f0c7',\n",
789
- " '76bf633b2d6d49b98845023de4024f09',\n",
790
- " 'eb00c39f80904f79847f0156e1e88ff0',\n",
791
- " 'c9695522dbb243cbaaf48b9a5b9f4105',\n",
792
- " 'aa3a41bf64fb4136b1fc097ad40378eb',\n",
793
- " '4ba6b441be194008aac5fec9aa0eac53',\n",
794
- " '7b5e6c78bcc64d4c879cc0817436ab35',\n",
795
- " '90229474433449648237b410db3cdfb7',\n",
796
- " '1ace5952f4c043e0a0864b9926475add',\n",
797
- " '2208ad4c34bc4fdb940e1cec9df0f6bc',\n",
798
- " '15e5cc7345b64cc08ad9825085af5486',\n",
799
- " 'ccac823288be4ed2a3d5617dda575120',\n",
800
- " 'e01e349952e54ef4849519acdaa6725b',\n",
801
- " '794cb0ec54724738a48d16e18f6cb3b9',\n",
802
- " 'd9ebc60044124f0a890f7836cb58f4a2',\n",
803
- " '9fda4771fa994fcaa609088cfc961dd4',\n",
804
- " '67fd7a926392436a9b344903bbbc08f7',\n",
805
- " '7892533c0b57466e8249f11d5cba07d3',\n",
806
- " 'ba1b7ad3addd4557aa6983cc309fdd49',\n",
807
- " '3663e44b29e14192abe4f49c98e3db45',\n",
808
- " '476728c883404adea36c903128c98139',\n",
809
- " 'dbec4491b8b94aa0b9327ead46b4251f',\n",
810
- " 'b635ebf0a3644e71ab64bfd43faec517',\n",
811
- " '149ee2b23af9448c896c5bf87f1c9257',\n",
812
- " 'f6082f115738427db840c3ff58a7c48d',\n",
813
- " 'd56f7d290c184a5aabdd80251ee807b5',\n",
814
- " '37738bf3df9048c381a26116632aff03',\n",
815
- " 'a139a0ccd8834a3293c65b8a9fb0a2ad',\n",
816
- " '6cce500b28a944fbb6ad637ae5d3c227',\n",
817
- " 'e16444a94afb409b827c3ee3f57237b9',\n",
818
- " 'd2d0cd1eac154f17b31a6a97d87bca88',\n",
819
- " '75bc3a67451e44a487939e6ca74e39ad',\n",
820
- " '9074393c760844908a39e806f7d4714e',\n",
821
- " 'fe16063331f848d897ac4466e9237fd7',\n",
822
- " 'a9504de4c7cd427cae397ddd551e3bba',\n",
823
- " '791979c2b3d747bf857370c4ab7e7757',\n",
824
- " 'cc31a5edfbfd486482b202b8b87c8e9f',\n",
825
- " '6cf68d7de2334461809f1867dfef1280',\n",
826
- " 'e8acd67d2b614ebd8e0786dcd961c05c',\n",
827
- " 'e30854b096ab48b3b7f3729bd07914e1',\n",
828
- " 'ae46462add43450d899655e2e0819e59',\n",
829
- " '1718ec5c859c4b37a8c8ac0bbcffa616',\n",
830
- " 'ae4a9b112f364a34a47f0cf255b882a4',\n",
831
- " '5ab58a4ae877437898e06968149195b2',\n",
832
- " '76401834e26049b096cdbb054cb37c7a',\n",
833
- " '52b9f9683ba14fb2a6f84f5b6d619b40',\n",
834
- " '96d56773bf2e4d858f62654f20ccd53d',\n",
835
- " 'd8a258c7815040808dbab44252e15e77',\n",
836
- " '9f4ca5df27674f4cba5628dd98f1ef2b',\n",
837
- " '8e0679ac4cbc44839a7f77a12ce52220',\n",
838
- " '964aa8b0653c4bdaa236d5bb6f1eff1d',\n",
839
- " '219697ddd2d545c484443ca116943b63',\n",
840
- " '607bf4aa92c64da9a4873477e2e9b363',\n",
841
- " 'efd6114026d2454d983e7b4063656266',\n",
842
- " '81fdf32f6fb949508196043e4142261b',\n",
843
- " '14f82f6a28a9488a93ce3724bdc2a476',\n",
844
- " '3d44caaa301046af9acdd238d1e3cbda',\n",
845
- " 'd8d11ff667ed4c0f94958e794e9b2c60',\n",
846
- " '90ba7f9ad22d46d99316b36cf213ec01',\n",
847
- " '76e251b11fb04240ae381af227c136bd',\n",
848
- " '3dec921799b24369a5b9189dd28c0f55',\n",
849
- " 'e7d706e31326405aa1a8acaa627ee2f6',\n",
850
- " '9b8c00a9f69649a1a66decee2aa77c9c',\n",
851
- " 'e2902a1405cf41db9a0428259089cbef',\n",
852
- " '5d43e9e802fb49098531b257c5633723',\n",
853
- " '413aeaa9a2bc4970b21371940026dba8',\n",
854
- " 'bfb4471ff2af4bada2ac8bcd14429d24',\n",
855
- " '533ff7a97fca4578999e6e0434df17d5',\n",
856
- " '04ba353da230424bbf25ab29a18e20f4',\n",
857
- " '1ed6dc9440f14ac9b1deadc10fbb660b',\n",
858
- " '734aa1cc14a34825be7dbc947ecdb525',\n",
859
- " '482153d0c05f4453a3bc9f57a1804406',\n",
860
- " '76d988efad614d3dafc0ecb8fbdb2189',\n",
861
- " '6d9ada3651704a0ca2b40664a59c8579',\n",
862
- " 'ac9272192bfc416d8386487c9b381ccf',\n",
863
- " '0d8c4c52de304f7f9778455f8ad178ec',\n",
864
- " '9daf6aed58624240b7fb1fcf79d9dda2',\n",
865
- " '7ee8e6bfacca440f9ef345e59eba7401',\n",
866
- " 'e80b50ed3a3a42d2a24bfe85cd5d45db',\n",
867
- " 'c0a0384aad9345f3b6162bf63c5bc0d3',\n",
868
- " 'df7c71db74af415b96cb2cea32d0ba30',\n",
869
- " '329b6e0ed9cb43cca48970fcc286e299',\n",
870
- " 'fd4c170eb78d401fa3eec3253be26b98',\n",
871
- " 'a98ea19a24cb4b04bd943d226dc41bba',\n",
872
- " '8e917ca54af2400cbd83e08e28ef0bb0',\n",
873
- " '78a3cf3647cc44f9abb083eaa8b79947',\n",
874
- " '140a48e4acbd44da9fede75e12fa80f3',\n",
875
- " '92d6e0856f5848869f7feb8cd17d7088',\n",
876
- " 'bf482ac0daea44a789182b52fbd2f413',\n",
877
- " 'f562e2d3c5b9422b845b6f87806e4d6c',\n",
878
- " 'e8b0bdec066a4bb0b7a47ec7e10c10e1',\n",
879
- " '45a054f0a9824867a52db472b2b65ad4',\n",
880
- " '40ff751a666347ed9c2326341587ea51',\n",
881
- " '1e35fbf001de48599063d4fe6dae165b',\n",
882
- " 'fa3b6f2ebe274d54851e9a31975470a6',\n",
883
- " '42242351bcb844c589f44a80cc139fdf',\n",
884
- " 'e5eb97e74797481d998677225cbaf365',\n",
885
- " '85f4bc0ed08c49feb6fd69f5659eaa36',\n",
886
- " '87df9b4b3b8a44eaa8756bbf8c967d8e',\n",
887
- " '7c04f74911aa4d629f0a545155e60b8d',\n",
888
- " '133597b368564215a8b71b2535a07032',\n",
889
- " '97473d57f4bd40af96f63bc06a1c6117',\n",
890
- " '3b3f2e2c08774f42bf0c904230b06c4c',\n",
891
- " '9661e9d3901e429d9030b04d28d98a19',\n",
892
- " '488e7a22bcdd400fb1ea9e52a102cd8f',\n",
893
- " '95086a933034484b9eeca08343c0dc21',\n",
894
- " 'e5aa0c58bc1448169bdebc7e99fcbd42',\n",
895
- " 'e6ba2f1ca8284d11a309757bc42ead7f',\n",
896
- " '6510e8c73d10408fa038b242f95cae2d',\n",
897
- " '36c2ba7197ce4c238472599a256f60db',\n",
898
- " '12ce3404c5024cc5a3ca4d1c0773d759',\n",
899
- " 'd0b909588d804b1aa89b496efcb6d16f',\n",
900
- " 'e830a0b4f0fa483b9bb9816162bde54f',\n",
901
- " 'eea7403faa024fc8a477b4b2e12bfc99',\n",
902
- " '1fbbcd091c3948229841d1a1e53cedef',\n",
903
- " '0bc14c99eb8141fc9f5ad1a13e8c5f90',\n",
904
- " '544d8570f3e847aea814771f3af2397e',\n",
905
- " 'd4e66a38f60c47deb7307e0f65829409',\n",
906
- " 'b520c61605aa473d89c88e3d277f40c5',\n",
907
- " '3f01a965995e495a8b3067fd0fdcc978',\n",
908
- " '9a5da84235c14817a3f0bda30a2bbcbb',\n",
909
- " '94792a1b19654f45a2fd8cc362dacddf',\n",
910
- " 'b46df9b21e764b39a0180bf42f9a835b',\n",
911
- " '47a4942336cd45cea7afcc68d99f1cd5',\n",
912
- " '2081541601de49199f881ffcb1625d4d',\n",
913
- " '972dcffe6c2e4cf2815cd571e9f4021d',\n",
914
- " 'e4613bb436fe46aaa3c236a209038124',\n",
915
- " '355cc289660d494db52e039127ecde34',\n",
916
- " 'b2b84fffde454e2d967ec6330e637b37',\n",
917
- " 'ab32b49526ee485d998dca366dace258',\n",
918
- " '48e0545b903f49bca771a22861166708',\n",
919
- " '47f62df12d494ba48b1bfee4bc1820f0',\n",
920
- " 'c131bfc970324e068ff4e04df6191c8d',\n",
921
- " '02a961ad52a34d1ead8d5c1a9ee12031',\n",
922
- " 'dcc8094b71444056a9c85f1b69b7e6df',\n",
923
- " 'd95234dd8571413ab9dc2cf2bd4031ef',\n",
924
- " '2b80007625d04c3a8b3c10fd35181861',\n",
925
- " 'b2b150d718c64b38925de1ee0abf14ed',\n",
926
- " '49f5645c803b4da78f09c7f0d337867a',\n",
927
- " 'af890841867746499efe8600704630b4',\n",
928
- " '7218a0d2f3e34a729da8a10e41a591fa',\n",
929
- " 'bafcc1d1244f40da99adcfb72f87b170',\n",
930
- " '14f2b87359524bfbac74a4948fdd135d',\n",
931
- " 'b209da5ac4ad4110834f018a3301f5cb',\n",
932
- " 'bf06ddade01d466592ea9cadbada320d',\n",
933
- " '865d5986afde44f4ab593708125e90ad',\n",
934
- " '3be18dd8e0bb4940bc58b257bad9c5b9',\n",
935
- " 'c02da0af95774b39af650dc268c8eed0',\n",
936
- " '7fae32ee9e934e2b8f164212ad9190b0',\n",
937
- " '8d0c1b678ea742cca445577d36a58e26',\n",
938
- " '4c1667fd01804d08bca4485a427b7cf3',\n",
939
- " '5d3bf9345565447095a9ffd9319997d9',\n",
940
- " 'ca5889dd43c5498ca449a733c36631d9',\n",
941
- " '5ba45f56b2f0412c835d4328b88037d3',\n",
942
- " 'e1d3f4649f234a8395a63ae1de670449',\n",
943
- " '17e91fcb2ae14f56a0f60c6acaf4258d',\n",
944
- " 'ed1d8496e014462db3aae0a046d4aeed',\n",
945
- " '8dd4483ba29448b7a285cefcaeb135fa',\n",
946
- " '77db975e07284a7a814ef386664c97aa',\n",
947
- " '93c28d0a7eb646969d0511b786fa7a71',\n",
948
- " 'c596f3b0927c49c1a4193eb5f0479395',\n",
949
- " 'e1648b2975284446bbbaefba431cdd78',\n",
950
- " '76bcc756b84a4b169a128973ef7228fe',\n",
951
- " 'ba57f715ffaf477fa15a733ddf5339aa',\n",
952
- " '644902133d4645bfbd02d9629fb737da',\n",
953
- " '124a4a8ec036421486e8501be3af4692',\n",
954
- " '0b95233f27f54043aee48dd77096c62c',\n",
955
- " '1ef09ede43d546b4a6a73b48c4cb48f1',\n",
956
- " '9dbee7e4bb32427f8fd0b0229ca0d2a6',\n",
957
- " 'f915f126e0f24f2299e6bfd16a5d3c1d',\n",
958
- " '3686b153c85248f6a2fc1fff12eaafe3',\n",
959
- " '850e99ca1e58439c8ccf36e2b6a7ecde',\n",
960
- " '25c84a37812b47c8adfd41b30af8c0bb',\n",
961
- " 'f96eb4a5818e4ebf8ae654d35cdc08a4',\n",
962
- " '31aaf38fa0bf49f4964d317f000840fd',\n",
963
- " '8c914f8f496741dab0d661f8bf84e061',\n",
964
- " '215a8d37eb5249ae97b9471c8ec0f888',\n",
965
- " '9f5e41e99d314cba824998d58ca1a611',\n",
966
- " '6b01b294c1774e34919059a7388aabd9',\n",
967
- " 'c1c6025360a9458085d5342cf8e703e0',\n",
968
- " 'b3fdbd3082794bd4b0ab4d4f2c8149f8',\n",
969
- " '700188e4d52b44fa9fde7512f54d7b1b',\n",
970
- " '00dad32bd08f4b39b153cc96b8497f4b',\n",
971
- " '9bb6f94103404153b68855d9993e9493',\n",
972
- " '56e07e044da34280830555b42799444d',\n",
973
- " '1d57812e47de41bf99efbbfa34865acd',\n",
974
- " '39c2def37c7d4b15a4e766632ea9eb98',\n",
975
- " '93e308150c2b44688cd13847402815b0',\n",
976
- " '1f595875c8ee4ac9a261bfb0a429067c',\n",
977
- " 'e7043593429e48a6bdcd8095f3ee2993',\n",
978
- " '8827c0bc83eb4dbeb48befa28e6ded29',\n",
979
- " 'acb099517d0449239adf6c9dde626772',\n",
980
- " 'f94e571e12af4903bfe866f6e028124e',\n",
981
- " 'd027a4d37b3640ad894587dab59a7494',\n",
982
- " 'f35c824977cc4d46962b01ad10f5ceb4',\n",
983
- " '836279f1552c4417a642da79743aeb33',\n",
984
- " '002978f8f7ab4cada169ea0d054499a5',\n",
985
- " 'e7a1c0978a2a4cd0b6b317ceda9874fc',\n",
986
- " '0f977a8cf0514392882756b1f7c6fa26',\n",
987
- " '7682cce87cfd470d95274b61e4eef8b8',\n",
988
- " '3947f0e87d00475387486b47326ed258',\n",
989
- " '6ddc01005056438cb611cd958b7a2d1d',\n",
990
- " 'bc81516df0f440d8a1faa7363f011b75',\n",
991
- " 'd676819f49004a56b7dc89cc5d5343ec',\n",
992
- " 'b8fd60c1b629499dac6ea2cdeb837502',\n",
993
- " '4e33d391a5634f0d82dd84dda6957811',\n",
994
- " 'b007e62d2fe749a6ab713c005211a73f',\n",
995
- " '18de6dda198e4f36befe7c81f88a7f42',\n",
996
- " '029857b9fae04c498b62b46c40267afa',\n",
997
- " '3be29a9773f24c079f24d9db9c662801',\n",
998
- " 'a095542002ce46ca95e59094332f0228',\n",
999
- " '40d61bdffba64369af605108a12a2999',\n",
1000
- " '7edeaefb56544debb539a1bafb766796',\n",
1001
- " '2f5335dc55594a04b67b07d86d937139',\n",
1002
- " 'f89a5a9d2d5047d7a74dd991ae0e8102',\n",
1003
- " 'fd4b6403ba4249b19c692a9dbdcdba01',\n",
1004
- " '3e02d74c82764b6997c4f965cfd6c233',\n",
1005
- " 'dfbe54ff42b4457db6cf921dc4ca0753',\n",
1006
- " '7abb841a671b40649ad478bc45c75b47',\n",
1007
- " 'a687e1b6e9dc40099a7d7d4ecd021a46',\n",
1008
- " 'ffdea99f5cec44e4abc9f4b8c6949fc1',\n",
1009
- " 'cb103ab7aa1a46f09d858dcf6880c862',\n",
1010
- " '4709ecfdce6c4392a245fad38093d1c4',\n",
1011
- " 'dbceabef7601444ba3a76c6bed960802',\n",
1012
- " 'a7f1acab40b145cbb2d8d84fc72733af',\n",
1013
- " '4df54db71ffa4dc4b1f10b022e3e6ef8',\n",
1014
- " 'a7fc14d6dbb14af6ae3ef0a3f68f1d07',\n",
1015
- " 'd5048b397eb04c6fb97a083b66aa6ac2',\n",
1016
- " 'b6420e8387b94f85aa36b5bfe589463f',\n",
1017
- " '767857ebb1fe41269ed4d82d967956d9',\n",
1018
- " '400246f61fa94320a267b7ab3f2e8cc7',\n",
1019
- " '8b763f3947974bd192d2d884c05c6428',\n",
1020
- " 'ea8f1f4852d64e09be5ac90b04404dad',\n",
1021
- " 'f6866c404c2c40b3a4314563846a911f',\n",
1022
- " '837631a58af84142b5042772b24da3bf',\n",
1023
- " '9d1586da31e44e6f9fb64ce9ff157673',\n",
1024
- " '098b85fd43c24f1aa3fd7c93a48fb98b',\n",
1025
- " 'f324b2ea7aef49979b23bb34f78846e8',\n",
1026
- " '6c35050aaecf43e7b7fcf40e9edfaa2f',\n",
1027
- " '910792f650bb463493a1b85488133ab5',\n",
1028
- " '2d428a2e50194db792e5a02146be9364',\n",
1029
- " '90ba4b5f05124c26aaec626e14ff2138',\n",
1030
- " '5c4b11be82e54ebab89237c6a4928284',\n",
1031
- " '11c9ce7a16094f788485a13218479435',\n",
1032
- " '27ef6c0ee62d4f4d9767d255f5b0bda6',\n",
1033
- " '603495b3760e453bbc7264b287754bd6',\n",
1034
- " '2afe6de14bc34f6381f30124a069d391',\n",
1035
- " '8666745692804c2bbd16b997d75f9426',\n",
1036
- " 'f9789e9010d44d2fa2eeadd121f9186b',\n",
1037
- " '3fdd94668daa4bd6a96e125c2725d9b4',\n",
1038
- " '02cf5c44de76414bb431468c721ea6ad',\n",
1039
- " 'ea3dc743311b46c6b7c6117c57de0333',\n",
1040
- " 'cac324fb19374fc892f4db768850823d',\n",
1041
- " 'ab4126594df44beb906274bbb1c0f40b',\n",
1042
- " '4cb686862a9a46ecaaa414860edba1cd',\n",
1043
- " '0e6481c6b52e43e5856a779b814b509c',\n",
1044
- " '73c0feaefcd44cffaa712880076005c7',\n",
1045
- " '147e1975a5b545c39eedde3c9e112d3f',\n",
1046
- " 'b52a309d67e44730a3e13f395aec79d4',\n",
1047
- " '6068165a21b64de191a203024d30275b',\n",
1048
- " '939af554456e4f9cb33268bd36d792c5',\n",
1049
- " '3dffe1eb87754b6ab3c932d8d77cfa00',\n",
1050
- " 'bf7419dc8ad84fc9b15e09b9125fe6b8',\n",
1051
- " 'f76718fe634243029f02130498d5afcd',\n",
1052
- " 'ef23c33828ff408abab8607b82eeb016',\n",
1053
- " 'da5f19bce12048a2aa11b06b85072f9c',\n",
1054
- " '32f57a9a758a4e41849fd85cedef76f0',\n",
1055
- " 'fba4c4a802904152bbeb6edb051e2607',\n",
1056
- " '728acf0b65ad4108a1e7a72b146e338e',\n",
1057
- " '0ff6d22870074917a6c014c33f4b7cf9',\n",
1058
- " '29d7bb91ce6b4a74893c614f725c5178',\n",
1059
- " 'b690e48b7dff464cb73dbdf1e6149309',\n",
1060
- " 'd92a821e7fdc4276b4fc8201dadfef62',\n",
1061
- " '7dcaeef50440471f83e8febf47b1049c',\n",
1062
- " 'd06797d35176423f97a118fb2921bf35',\n",
1063
- " '8601101c7fa9428c9624bce8ea4cee15',\n",
1064
- " 'f45441e8e3264add88478323c93e2d38',\n",
1065
- " '985d73938f0744fd9ca3e05d8ed4d99e',\n",
1066
- " 'aec96ecb915d47eea4ae0dae9dc95446',\n",
1067
- " '8120edfc5cf247babcaaf6e7bf59ebe1',\n",
1068
- " '821cb61115ef45f3b24ecf7e7ffe5b27',\n",
1069
- " 'e4dc1ed27a224c9294f648336d261c53',\n",
1070
- " 'b90241dc87844d628f45401349ab9887',\n",
1071
- " 'a255e1c4b31241058595c134f5de807a',\n",
1072
- " '648c5ad4530442e5b50f28f40c386bb6',\n",
1073
- " 'ffa4b3e9e4ae4289b0c404da4abadcbc',\n",
1074
- " 'fa5af409bfe441d1bcee2d0b5e377678',\n",
1075
- " '033a5c2bd8374ca6b8cb9b4d965954ab',\n",
1076
- " '357babd6dd4947749142359d0fc0cdd3',\n",
1077
- " 'e4853735544842de9790530cb56a3eba',\n",
1078
- " '3698a84c5a8644d99072de0b3a6aa9f5',\n",
1079
- " 'd9c6bac4f1dd41dcb3318843c7f79489',\n",
1080
- " '3dd799500efb450f8004d4240e037b20',\n",
1081
- " '686426621d894b2781e6fb48d4b16c8e',\n",
1082
- " '85b807e001ff46fe985770fa6af9a534',\n",
1083
- " '097971e5d47043a2b4d569d56634bb2e',\n",
1084
- " '46bb945a79c94a7da13c0c1506e1c457',\n",
1085
- " '5ef5cbe182d94b5d899d2dbc9595b3a8',\n",
1086
- " '466985e3a3ce424ab38284db938f8d40',\n",
1087
- " '3a87f5d24ee448649a1fb37e1572f0e4',\n",
1088
- " 'e17801c99d6944b899da6568724826a9',\n",
1089
- " '24d0a98cbe0d4450a1e3994c6dab3a15',\n",
1090
- " '3fa0add1d0b642f296690f408b0372c8',\n",
1091
- " '1d657774ca004dc79b7fcb36ac85e26e',\n",
1092
- " '7e69a8dc03104c72bdfc8cb6c2fcf9ee',\n",
1093
- " '40c85cbead07447a8ba67f4c279ffd8b',\n",
1094
- " '7b595edf61784a549e64edfc1e18a497',\n",
1095
- " 'a4d50cd2c1534c02b0a34458d25920d0',\n",
1096
- " '318e51c677b949d09d9a61fb7a069082',\n",
1097
- " 'a45a8c5d6a6a47ccbafb57a1bb45c4b0',\n",
1098
- " 'a0c089e55b15476e8a89292b31b310fc',\n",
1099
- " '41fcfb134a8a44c9931edccd36627ca2',\n",
1100
- " '7e7687c8087a4174850cd19935c845bd',\n",
1101
- " 'a812d2adb03546538480ad44b33fd2bb',\n",
1102
- " '5c5779f29b93468ca603bf37687d068d',\n",
1103
- " '50783f0c8c944ff19aa86f2e5ac781ac',\n",
1104
- " '4a21f30d19f24fd5a331537371b46dce',\n",
1105
- " 'adda51e0076048ca98142173498f3af7',\n",
1106
- " '07fa53932ec041d5bcd71d77b273d8d2',\n",
1107
- " '18768f62094043548f4d280627a9d3a9',\n",
1108
- " 'd5fcc7eeeb154b179028b03beaf8f3f8',\n",
1109
- " 'a6859c0e9eb74acfbfde7fefbc76d9b6',\n",
1110
- " 'c2e90d49e7f14233acebd2ac10622efc',\n",
1111
- " 'e0997f7ee41742ed8a0179f9805bf12e',\n",
1112
- " '9b8dc4963513406d90a71935b05a7601',\n",
1113
- " '1cfc3fe1c73f43f69d776c880641baa9',\n",
1114
- " '34fc9ec282fe475d8314ea0a3a44b881',\n",
1115
- " '0943841a14ef474b8844520d91bfee9c',\n",
1116
- " 'ef27e818cad1462aa3bf7d9aaa19700f',\n",
1117
- " '6e2fdf8601904078986ebb1c71bc8168',\n",
1118
- " 'c18bf0d5ee5e45c8806cc1ea7d486bba',\n",
1119
- " 'a87b5e1ac2dd42d488929580625996de',\n",
1120
- " '8d384236c7e448439e9230a000d6aaf7',\n",
1121
- " '6dabbe7ff4814ab4bdcb84715ab20af4',\n",
1122
- " '943a13d4ef0d4bc2a81b16078b580e78',\n",
1123
- " 'baa6fd13ff6f445a8adc6482e59eb411',\n",
1124
- " '57b39b4eee4d4a0aac587d53ef68ff8d',\n",
1125
- " 'fd07301c3d554f02a0793d5f7bb63f35',\n",
1126
- " 'e99969118642471f887206e1c6a507e7',\n",
1127
- " '584dc05d60844536bdaac7bb3c1b7cd4',\n",
1128
- " 'f1ba0bf7f2b54612a3ffa4a66dd0989c',\n",
1129
- " 'e254c679f27c4143bcdda32f15e846e1',\n",
1130
- " '2d51c45ed9ca4a3ab95590cff7047d37',\n",
1131
- " '3bc9228d85364bd1b1f5bb7d13af5a8c',\n",
1132
- " 'b2de27d51d964d8c9e190f42d7ad9768',\n",
1133
- " 'e08419ed7e154a7da62745b3bd5ebd78',\n",
1134
- " '70a099122b2d43dbbe23d375432beaa1',\n",
1135
- " '01c551bc80134225ad0391bb295b365c',\n",
1136
- " 'c2388131208c4d8c868af7d7e6405cca',\n",
1137
- " 'bb0e3a6a10cc4ac29a168fcee5042c17',\n",
1138
- " '4b20b4b550da419d88ee62758c495138',\n",
1139
- " '5ea09fb9fb074218b814dde11c1aed3f',\n",
1140
- " 'ee62a59cd0784f4cbabb349725d7fe78',\n",
1141
- " 'a58457312c084595ab30bd5c59d0b3cb',\n",
1142
- " 'af5f60ae6a3a48129b15c89bebe493cf',\n",
1143
- " 'e5fddd76079f492f83ab1582f8d46893',\n",
1144
- " 'fd4e785b8d9c4d7bb8af493c54ee6870',\n",
1145
- " 'd91c68bc847c4c5993e6fa53b657b504',\n",
1146
- " '1bfd2c9fa301401a91ff49843b1c842c',\n",
1147
- " '9684447b6a9044339ff355877d86f7d3',\n",
1148
- " '6fcdfdbf98c64c8b89a3730f72f8268f',\n",
1149
- " '6ccdf85fa1ce4bd19775b7fcf5a12ee7',\n",
1150
- " 'e67bb1231dce4f35b3914e3a40bb9c12',\n",
1151
- " '7a55571c1f654084844ec308bba0ba42',\n",
1152
- " '38d650edd70742898f976233a7dfb85a',\n",
1153
- " '496b340000dc4eb09780ce18b3ba5392',\n",
1154
- " 'a79b3b9c6ea74599885fdb8d28d12cfd',\n",
1155
- " 'f4de9dfe9b9c47f7aee86802c145d2d4',\n",
1156
- " 'c5b4d1fed5874094acaadc869998174f',\n",
1157
- " 'd4ca3a34bfeb41bc8065e682213eaaab',\n",
1158
- " '40786361d73e4a58a173a099821b3020',\n",
1159
- " 'c267c513aa0049168f2ab2e2444029c9',\n",
1160
- " 'de47fda5d45340b58a4febf243c18c90',\n",
1161
- " 'b8f6f44e9ca64d28956c159f9aa284bb',\n",
1162
- " 'cb6cd0c5ffb743ce8d07d0c02ed2cbe3',\n",
1163
- " 'f42720e5bcd94c4ab0f3880cf75dbb50',\n",
1164
- " '3bd78527eff54c5db6ead2f0471d1b55',\n",
1165
- " 'c5257e382fbc4f69a16aa0bc047dfee2',\n",
1166
- " '22df791dc8fa45c9867e2cd4de171bd9',\n",
1167
- " 'b3a0c0feba764bd0abfb446204a8239f',\n",
1168
- " 'ba39d1b49cf840289c2d2d04e88948cd',\n",
1169
- " '1a956280d4db49aea6007c9c1d0f698a',\n",
1170
- " 'e7062f6c5dba476facf895b6faee99cd',\n",
1171
- " '95f2febaef5a433f89c11d3e9741347f',\n",
1172
- " 'fded3452cdbf42fa90f7fadfacd5dd63',\n",
1173
- " '0a89bd45fc9d4148828cddb02a0921e7']"
1174
  ]
1175
  },
1176
- "execution_count": 25,
1177
  "metadata": {},
1178
  "output_type": "execute_result"
1179
  }
@@ -1206,7 +1206,7 @@
1206
  },
1207
  {
1208
  "cell_type": "code",
1209
- "execution_count": 26,
1210
  "metadata": {},
1211
  "outputs": [],
1212
  "source": [
@@ -1216,25 +1216,25 @@
1216
  },
1217
  {
1218
  "cell_type": "code",
1219
- "execution_count": 28,
1220
  "metadata": {},
1221
  "outputs": [
1222
  {
1223
  "data": {
1224
  "text/plain": [
1225
- "[Document(metadata={'source': 'https://www.whitehouse.gov/wp-content/uploads/2022/10/Blueprint-for-an-AI-Bill-of-Rights.pdf', 'file_path': 'https://www.whitehouse.gov/wp-content/uploads/2022/10/Blueprint-for-an-AI-Bill-of-Rights.pdf', 'page': 11, 'total_pages': 73, 'format': 'PDF 1.6', 'title': 'Blueprint for an AI Bill of Rights', 'author': '', 'subject': '', 'keywords': '', 'creator': 'Adobe Illustrator 26.3 (Macintosh)', 'producer': 'iLovePDF', 'creationDate': \"D:20220920133035-04'00'\", 'modDate': \"D:20221003104118-04'00'\", 'trapped': '', '_id': '70fb8aa0-96a7-4d0a-9757-05ac44f08577', '_collection_name': 'ai-safety-sr-arctic-embed-l-recursive'}, page_content='FROM \\nPRINCIPLES \\nTO PRACTICE \\nA TECHINCAL COMPANION TO\\nTHE Blueprint for an \\nAI BILL OF RIGHTS\\n12'),\n",
1226
- " Document(metadata={'source': 'https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf', 'file_path': 'https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf', 'page': 50, 'total_pages': 64, 'format': 'PDF 1.6', 'title': 'Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile', 'author': 'National Institute of Standards and Technology', 'subject': '', 'keywords': '', 'creator': 'Acrobat PDFMaker 24 for Word', 'producer': 'Adobe PDF Library 24.2.159', 'creationDate': \"D:20240805141702-04'00'\", 'modDate': \"D:20240805143048-04'00'\", 'trapped': '', '_id': 'e254c679-f27c-4143-bcdd-a32f15e846e1', '_collection_name': 'ai-safety-sr-arctic-embed-l-recursive'}, page_content='• Accessibility and reasonable \\naccommodations \\n• AI actor credentials and qualifications \\n• Alignment to organizational values \\n• Auditing and assessment \\n• Change-management controls \\n• Commercial use \\n• Data provenance'),\n",
1227
- " Document(metadata={'source': 'https://www.whitehouse.gov/wp-content/uploads/2022/10/Blueprint-for-an-AI-Bill-of-Rights.pdf', 'file_path': 'https://www.whitehouse.gov/wp-content/uploads/2022/10/Blueprint-for-an-AI-Bill-of-Rights.pdf', 'page': 19, 'total_pages': 73, 'format': 'PDF 1.6', 'title': 'Blueprint for an AI Bill of Rights', 'author': '', 'subject': '', 'keywords': '', 'creator': 'Adobe Illustrator 26.3 (Macintosh)', 'producer': 'iLovePDF', 'creationDate': \"D:20220920133035-04'00'\", 'modDate': \"D:20221003104118-04'00'\", 'trapped': '', '_id': '2c07a476-9e85-425a-9a32-a053f1293ff2', '_collection_name': 'ai-safety-sr-arctic-embed-l-recursive'}, page_content='organization’s business processes or other activities, system goals, any human-run procedures that form a \\npart of the system, and specific performance expectations; a description of any data used to train machine \\nlearning models or for other purposes, including how data sources were processed and interpreted, a \\nsummary of what data might be missing, incomplete, or erroneous, and data relevancy justifications; the \\nresults of public consultation such as concerns raised and any decisions made due to these concerns; risk \\nidentification and management assessments and any steps taken to mitigate potential harms; the results of \\nperformance testing including, but not limited to, accuracy, differential demographic impact, resulting \\nerror rates (overall and per demographic group), and comparisons to previously deployed systems; \\nongoing monitoring procedures and regular performance testing reports, including monitoring frequency,'),\n",
1228
- " Document(metadata={'source': 'https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf', 'file_path': 'https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf', 'page': 51, 'total_pages': 64, 'format': 'PDF 1.6', 'title': 'Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile', 'author': 'National Institute of Standards and Technology', 'subject': '', 'keywords': '', 'creator': 'Acrobat PDFMaker 24 for Word', 'producer': 'Adobe PDF Library 24.2.159', 'creationDate': \"D:20240805141702-04'00'\", 'modDate': \"D:20240805143048-04'00'\", 'trapped': '', '_id': 'e08419ed-7e15-4a7d-a627-45b3bd5ebd78', '_collection_name': 'ai-safety-sr-arctic-embed-l-recursive'}, page_content='lifecycle and informed by representative AI Actors (see Figure 3 of the AI RMF). Until new and rigorous'),\n",
1229
- " Document(metadata={'source': 'https://www.whitehouse.gov/wp-content/uploads/2022/10/Blueprint-for-an-AI-Bill-of-Rights.pdf', 'file_path': 'https://www.whitehouse.gov/wp-content/uploads/2022/10/Blueprint-for-an-AI-Bill-of-Rights.pdf', 'page': 25, 'total_pages': 73, 'format': 'PDF 1.6', 'title': 'Blueprint for an AI Bill of Rights', 'author': '', 'subject': '', 'keywords': '', 'creator': 'Adobe Illustrator 26.3 (Macintosh)', 'producer': 'iLovePDF', 'creationDate': \"D:20220920133035-04'00'\", 'modDate': \"D:20221003104118-04'00'\", 'trapped': '', '_id': 'd9ebc600-4412-4f0a-890f-7836cb58f4a2', '_collection_name': 'ai-safety-sr-arctic-embed-l-recursive'}, page_content='for any resulting algorithmic discrimination. \\n26\\nAlgorithmic \\nDiscrimination \\nProtections'),\n",
1230
- " Document(metadata={'source': 'https://www.whitehouse.gov/wp-content/uploads/2022/10/Blueprint-for-an-AI-Bill-of-Rights.pdf', 'file_path': 'https://www.whitehouse.gov/wp-content/uploads/2022/10/Blueprint-for-an-AI-Bill-of-Rights.pdf', 'page': 0, 'total_pages': 73, 'format': 'PDF 1.6', 'title': 'Blueprint for an AI Bill of Rights', 'author': '', 'subject': '', 'keywords': '', 'creator': 'Adobe Illustrator 26.3 (Macintosh)', 'producer': 'iLovePDF', 'creationDate': \"D:20220920133035-04'00'\", 'modDate': \"D:20221003104118-04'00'\", 'trapped': '', '_id': 'dd370438-231c-41db-b7b1-b4f1e7673cf7', '_collection_name': 'ai-safety-sr-arctic-embed-l-recursive'}, page_content='BLUEPRINT FOR AN \\nAI BILL OF \\nRIGHTS \\nMAKING AUTOMATED \\nSYSTEMS WORK FOR \\nTHE AMERICAN PEOPLE \\nOCTOBER 2022'),\n",
1231
- " Document(metadata={'source': 'https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf', 'file_path': 'https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf', 'page': 38, 'total_pages': 64, 'format': 'PDF 1.6', 'title': 'Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile', 'author': 'National Institute of Standards and Technology', 'subject': '', 'keywords': '', 'creator': 'Acrobat PDFMaker 24 for Word', 'producer': 'Adobe PDF Library 24.2.159', 'creationDate': \"D:20240805141702-04'00'\", 'modDate': \"D:20240805143048-04'00'\", 'trapped': '', '_id': '7b595edf-6178-4a54-9e64-edfc1e18a497', '_collection_name': 'ai-safety-sr-arctic-embed-l-recursive'}, page_content='guide the design of provenance data-tracking techniques. \\nHuman-AI Configuration; \\nInformation Integrity \\nMS-2.10-003 Verify deduplication of GAI training data samples, particularly regarding synthetic \\ndata. \\nHarmful Bias and Homogenization \\nAI Actor Tasks: AI Deployment, AI Impact Assessment, Domain Experts, End-Users, Operation and Monitoring, TEVV'),\n",
1232
- " Document(metadata={'source': 'https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf', 'file_path': 'https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf', 'page': 59, 'total_pages': 64, 'format': 'PDF 1.6', 'title': 'Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile', 'author': 'National Institute of Standards and Technology', 'subject': '', 'keywords': '', 'creator': 'Acrobat PDFMaker 24 for Word', 'producer': 'Adobe PDF Library 24.2.159', 'creationDate': \"D:20240805141702-04'00'\", 'modDate': \"D:20240805143048-04'00'\", 'trapped': '', '_id': 'b8f6f44e-9ca6-4d28-956c-159f9aa284bb', '_collection_name': 'ai-safety-sr-arctic-embed-l-recursive'}, page_content='https://www.bloomberg.com/graphics/2023-generative-ai-bias/. \\nNational Institute of Standards and Technology (2024) Adversarial Machine Learning: A Taxonomy and \\nTerminology of Attacks and Mitigations https://csrc.nist.gov/pubs/ai/100/2/e2023/final \\nNational Institute of Standards and Technology (2023) AI Risk Management Framework. \\nhttps://www.nist.gov/itl/ai-risk-management-framework \\nNational Institute of Standards and Technology (2023) AI Risk Management Framework, Chapter 3: AI \\nRisks and Trustworthiness. \\nhttps://airc.nist.gov/AI_RMF_Knowledge_Base/AI_RMF/Foundational_Information/3-sec-characteristics \\nNational Institute of Standards and Technology (2023) AI Risk Management Framework, Chapter 6: AI \\nRMF Profiles. https://airc.nist.gov/AI_RMF_Knowledge_Base/AI_RMF/Core_And_Profiles/6-sec-profile \\nNational Institute of Standards and Technology (2023) AI Risk Management Framework, Appendix A: \\nDescriptions of AI Actor Tasks.'),\n",
1233
- " Document(metadata={'source': 'https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf', 'file_path': 'https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf', 'page': 57, 'total_pages': 64, 'format': 'PDF 1.6', 'title': 'Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile', 'author': 'National Institute of Standards and Technology', 'subject': '', 'keywords': '', 'creator': 'Acrobat PDFMaker 24 for Word', 'producer': 'Adobe PDF Library 24.2.159', 'creationDate': \"D:20240805141702-04'00'\", 'modDate': \"D:20240805143048-04'00'\", 'trapped': '', '_id': '38d650ed-d707-4289-8f97-6233a7dfb85a', '_collection_name': 'ai-safety-sr-arctic-embed-l-recursive'}, page_content='54 \\nAppendix B. References \\nAcemoglu, D. (2024) The Simple Macroeconomics of AI https://www.nber.org/papers/w32487 \\nAI Incident Database. https://incidentdatabase.ai/ \\nAtherton, D. (2024) Deepfakes and Child Safety: A Survey and Analysis of 2023 Incidents and Responses. \\nAI Incident Database. https://incidentdatabase.ai/blog/deepfakes-and-child-safety/ \\nBadyal, N. et al. (2023) Intentional Biases in LLM Responses. arXiv. https://arxiv.org/pdf/2311.07611 \\nBing Chat: Data Exfiltration Exploit Explained. Embrace The Red. \\nhttps://embracethered.com/blog/posts/2023/bing-chat-data-exfiltration-poc-and-fix/ \\nBommasani, R. et al. (2022) Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome \\nHomogenization? arXiv. https://arxiv.org/pdf/2211.13972 \\nBoyarskaya, M. et al. (2020) Overcoming Failures of Imagination in AI Infused System Development and \\nDeployment. arXiv. https://arxiv.org/pdf/2011.13416 \\nBrowne, D. et al. (2023) Securing the AI Pipeline. Mandiant.'),\n",
1234
- " Document(metadata={'source': 'https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf', 'file_path': 'https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf', 'page': 12, 'total_pages': 64, 'format': 'PDF 1.6', 'title': 'Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile', 'author': 'National Institute of Standards and Technology', 'subject': '', 'keywords': '', 'creator': 'Acrobat PDFMaker 24 for Word', 'producer': 'Adobe PDF Library 24.2.159', 'creationDate': \"D:20240805141702-04'00'\", 'modDate': \"D:20240805143048-04'00'\", 'trapped': '', '_id': 'd5048b39-7eb0-4c6f-b97a-083b66aa6ac2', '_collection_name': 'ai-safety-sr-arctic-embed-l-recursive'}, page_content='Priorities Related to Information Integrity Research and Development.')]"
1235
  ]
1236
  },
1237
- "execution_count": 28,
1238
  "metadata": {},
1239
  "output_type": "execute_result"
1240
  }
 
699
  },
700
  {
701
  "cell_type": "code",
702
+ "execution_count": 14,
703
  "metadata": {},
704
  "outputs": [
705
  {
706
  "data": {
707
  "text/plain": [
708
+ "['121c5a692bac4c508d5f3311982e25ec',\n",
709
+ " '002f32185b9047e89a538ae775a06e71',\n",
710
+ " 'a75c5035aab6408eb5345e460c469a10',\n",
711
+ " 'ca645e946ec542388be2bad2ded9a670',\n",
712
+ " '6c7ea28d623b4922817cd1c0b6d588be',\n",
713
+ " '7a62cd3d9905402bac4abb6821656d51',\n",
714
+ " '2b634384780b4b5eb37fe6e37abdff36',\n",
715
+ " 'bf0688dd9882476e81f754c1e24b0ca2',\n",
716
+ " '3cd98731f3d94931b3be136846f4c403',\n",
717
+ " 'b90b3ac01e304f2dadc116b2a0e424d9',\n",
718
+ " 'd689b544a6e94580b0c44168c0daa6e3',\n",
719
+ " '5acfb9a2c5004eb69af7e40d00894163',\n",
720
+ " '00266c03dc974d4bbe53bb0a70c8ffdb',\n",
721
+ " '9b412771249f493f9b6984df80c8b9d7',\n",
722
+ " '34ad696c6ad348ba9d3e16b99674afd8',\n",
723
+ " '5c369a7d85864bc2bcb8b01ce92ef144',\n",
724
+ " 'b09a0da6c4804f8f92566d4f634c0c09',\n",
725
+ " '54f8ae4b1813431a8a5d42bc85ef40a4',\n",
726
+ " 'a5bb3d08f7b04da0aa0fd89b51284b75',\n",
727
+ " '58e0fc7a8d6a46cebd9a5c390cb7feb7',\n",
728
+ " 'dae3c740827a4617b3807d439e9b4450',\n",
729
+ " '5fb9e3ae5bc349f3a36ab016df65cc5d',\n",
730
+ " '0d556bc654ad46beb3268c43c6bc4c70',\n",
731
+ " 'b76072d3981c49f6b99b2b5870ace24b',\n",
732
+ " '3ef94b3ff0054f8980194cb6cf5b5246',\n",
733
+ " '5c79ea68ce604c2c9ea088eaedc8c1b8',\n",
734
+ " '9a4c71068d984a3d9ff4eb5cd7b9bb69',\n",
735
+ " '5fc53a0ef85f4d80aac75952b90183a6',\n",
736
+ " '8512d11a7a35475d863a80661995960d',\n",
737
+ " 'dadf7b4ecc3044a3979586229620f6b1',\n",
738
+ " 'd19e5d5bea1f42eaa131a7709f541c15',\n",
739
+ " '8807e74854ed482c85f70fbcd3e0fd25',\n",
740
+ " '7a78ab1d944241669b0c470371e11ece',\n",
741
+ " 'ebb8c7a5269a4cd3b381fb0f27a0410d',\n",
742
+ " 'b3b76d7a4a04459d8af3205f7a3bc371',\n",
743
+ " 'ecf609ea871b43f58760c6a8c759c874',\n",
744
+ " '33395a8a33c446168b6fae1a86ec5ade',\n",
745
+ " '7e84113988574db393d01d8464ded41a',\n",
746
+ " 'd09c730d090745e389f67390b9288e66',\n",
747
+ " '52d609c4d6b946f39732f3adcc61b7dd',\n",
748
+ " '3c455596b95745e2991e68f4f86633aa',\n",
749
+ " '9d1df59c40d54e129e592cf3f7ba07cc',\n",
750
+ " '546517b8b36445bcad764869167d8b13',\n",
751
+ " '7f6df2f239624ce28e16226abbb1013e',\n",
752
+ " 'b7ddb0618be64951bc884a0b08b4785e',\n",
753
+ " 'ed2290d54b894f9e974fc639fa2bf19b',\n",
754
+ " 'f7f42618a932435eb6038a0c8e6df1f4',\n",
755
+ " '6048cd8eeae54b1c8e87048df4bed5a9',\n",
756
+ " '7639f613b33f47b2ba86e97bf774027e',\n",
757
+ " '351a338d896749da9a977e032454be1b',\n",
758
+ " '0a6df50e95d64eb0bdd2f075dd0c5c53',\n",
759
+ " 'b55b4e54d1904060be9962c543b8d794',\n",
760
+ " '9e8e5e215bc2468ea3c15c6a6e549db6',\n",
761
+ " '328ab50578a4476ba2c1ac9def847d6f',\n",
762
+ " '27f2110c7dbd4460adaa0082ade55e9e',\n",
763
+ " '82de6b7637644bb687c4c4ed43702f0f',\n",
764
+ " 'c40cd71355f74fe5a97c3d355849953a',\n",
765
+ " 'e795feff9bf540fc82565180c1c404b2',\n",
766
+ " '4b3f2a85c1a54b51bbbee08031f1a700',\n",
767
+ " 'bbce04c2a7404e699a178c1dc066f32d',\n",
768
+ " '7a604642146044b1bb5211f46529aecd',\n",
769
+ " 'b101f617e4af437dbf6a6efc9250773f',\n",
770
+ " 'f3944be0ef3641e58ba0500ae473d051',\n",
771
+ " '032d832f166e41999458d2d734285585',\n",
772
+ " 'c2f341e5dfb747cf897a26bd3d9ce8a5',\n",
773
+ " '2fd7f253d1874d25903f7f4524027ba3',\n",
774
+ " 'f2e16ddf0bd24e46887a04eb68fa3b03',\n",
775
+ " '92d9b1487ce64de3a739180f28de783e',\n",
776
+ " 'e6806550dbd44ff39f343ceae002e131',\n",
777
+ " '33d96eb04a5c480ca922dd5112a2f36e',\n",
778
+ " 'de3d52b4b41043f7b77f989ead551ae9',\n",
779
+ " '9b39fa8e69574b9284e0bdaeaaca9fd1',\n",
780
+ " '5262c603971d42e0afe79f639b7463f0',\n",
781
+ " 'e3c3a57e106248b3ad4fba41a06f85c6',\n",
782
+ " '8742b54cab6d4aceaf4447d1f799c855',\n",
783
+ " 'e438b7b43c144e3f8b98e23faf3c449d',\n",
784
+ " '66d122694c9746f78b0ae26105d040a2',\n",
785
+ " 'e567207a24f34c2a83f0cb4512d5fb27',\n",
786
+ " '919ce22b992a49e7a2c92defe3b2f96b',\n",
787
+ " '2a2bd59bf5514aafa07cc3abb424beb1',\n",
788
+ " '60c93a0ae6f24dfbbc5143e9f9961e2d',\n",
789
+ " 'fc060b95e10743ca9e8bc6edc656ee35',\n",
790
+ " '54d7a6bb68874eb3af3ec4b6dbe7cec8',\n",
791
+ " '89d0df2730514fc587a95649d2890806',\n",
792
+ " 'a075361c58b4457dac12f1131eb88c31',\n",
793
+ " '008f0fa293b245549d484e707d08739c',\n",
794
+ " 'c369ea7abc594f038975a8f968054475',\n",
795
+ " '603ccdebea51435db6949e7e3c0391a5',\n",
796
+ " '3e541cc4c93d4384ae7074aee06bb295',\n",
797
+ " '1c9615e8b4a441138dd6616cc3a2745b',\n",
798
+ " 'd8c644c1c8164de4a337e989f236f5a7',\n",
799
+ " 'e20acdea5abb4cbdbce50884d021b8f9',\n",
800
+ " '461c0d3aaa5f499ca8fc588a44da3476',\n",
801
+ " '844e763716b14f5b9fa33f9919f6551a',\n",
802
+ " '46f14ba87100473291cc91cbaf1b6bcf',\n",
803
+ " 'da6c6a307da84f33ba46850ad7891f14',\n",
804
+ " 'c0902cf4ad43420ea03d8acfd35b3ee5',\n",
805
+ " 'dc72a7ff20de475185da3f3a796ed460',\n",
806
+ " '7e89f1ffa2bd47e7a33311b6f1b05d71',\n",
807
+ " '92cd7c43858041c398e539d21428ed09',\n",
808
+ " '4afcc91ac38d4f56bd5c8f1daaa6403e',\n",
809
+ " 'a518f232bc074646be2a649ec2a70c24',\n",
810
+ " 'baeef46fd8624fb9a614920a9e9b85ad',\n",
811
+ " '4e51b278bcba4f54b92f31dc909c57ca',\n",
812
+ " '2c6ec92d5b124753b8fecfaf94bfaa9f',\n",
813
+ " 'c36c0b710ff2417db08911c73350adba',\n",
814
+ " '6837202efdd846448c3f558b14bc959c',\n",
815
+ " 'd0a7721e28d84791a8a845207702eeb2',\n",
816
+ " 'c5e9f15229e645388a1c49ee6c7fa130',\n",
817
+ " '2083ab5ae9e742c58f0af2a9186ef97b',\n",
818
+ " '6e0aea2220d342caa27e0feac64d01d3',\n",
819
+ " '9ea18afdef3547dca6d4ad32eadd2125',\n",
820
+ " '29521fefd69c444eb5f80620d512d4fe',\n",
821
+ " 'aa531ab886ff45c390d1f5a55acd07ba',\n",
822
+ " '3098b0f2521b42bdb9f4903794e25975',\n",
823
+ " '1fb7d98135a548dba2a20ef0dbf3fb26',\n",
824
+ " '4119bf9c3d784d8099838791f5967bb3',\n",
825
+ " 'e72cbae23d4c477c9c5f61ad8e06b64c',\n",
826
+ " '9f5301e38867447997d81d0d55c48202',\n",
827
+ " 'edf53fefbae8450bad25c4c79e290ad5',\n",
828
+ " '717212234a0e4c168e4184311e47f989',\n",
829
+ " 'ed707a1db68844d9bf0c964dfb601435',\n",
830
+ " '310cb802931241a2b2a9ba59cf81f24b',\n",
831
+ " '2f5db0b062e7448ba73a887447bdd762',\n",
832
+ " '569b66ff0a3a4ec18edf02a7e89b76f5',\n",
833
+ " 'e0752f5d428647219874d9eda82a90dc',\n",
834
+ " 'fe1bc71df1dc4cf980be8944bf4159d0',\n",
835
+ " '82cf387df613436ea88fe504624b0029',\n",
836
+ " '0ce366c53a3e4fbab1b503296e1bfacd',\n",
837
+ " 'c2f69d12c22d481aa3c260e4ceca474a',\n",
838
+ " '4b643d3909fa4001ad583b4852c12267',\n",
839
+ " '98adca050b84460ba13fe84d334d262f',\n",
840
+ " '7aca743c330e4bfda13eab171cde4f4a',\n",
841
+ " '62c6e288187a463b9843b1c96705c434',\n",
842
+ " '4a5cd4f3c20745d8ad69106d4c9c7873',\n",
843
+ " 'b4970473ee9c43f79a2111c2e462682f',\n",
844
+ " '069ef8c7679a44608c78ed9c1cc578fc',\n",
845
+ " 'be28417989184d959a17e83dd74a4fa3',\n",
846
+ " '692490e1b86b480fb28397134e65931f',\n",
847
+ " '0b7858fa5b744507aae6142c8f44bbca',\n",
848
+ " '6c244282774f4cc9b4c53249fb321416',\n",
849
+ " '57d609e2d1f74ea180e7423c25efa9dd',\n",
850
+ " '83aafd29463d4e97acda7366513e1c92',\n",
851
+ " 'cd42bb0e075f40a2bdf21f210e4b6dd6',\n",
852
+ " '89e3c753163545fe9acc49707dedc119',\n",
853
+ " '6cef261d45bf4460b746eef065a33060',\n",
854
+ " '945867bb10fb4132a6e674b1da2d4dff',\n",
855
+ " '55fb0e57c6e24e23b84ad181c86e563e',\n",
856
+ " '4594e6a3fa6d45509bdb71d0516654d5',\n",
857
+ " 'bf2bcecfbea44484859f0d22d88e318b',\n",
858
+ " 'ed75c0dd4c674b898594af8160f4de4b',\n",
859
+ " '939e15f652d94fa7898aefeb0ccdf743',\n",
860
+ " '5184f363a16f41f3a1bf2f0d2cab140e',\n",
861
+ " 'd36e09bc1e094f01ab9056af1c5f7233',\n",
862
+ " 'ea5ae52acda74822b86206ee57dad51d',\n",
863
+ " 'b5bab1ed0d13477ea1a13c439f5eceea',\n",
864
+ " '400b7b0e5d144ec0b5b6251c710018df',\n",
865
+ " '83835136db174c6cb75c5fd0491a3844',\n",
866
+ " '116a12a081cd4f7484a169167cb61e81',\n",
867
+ " '33d8cf806081466f9de11d9729ebe735',\n",
868
+ " '68f49c0ef23f4238914cd3de01c11d08',\n",
869
+ " '9c1fa3c6e44c4d4ba54d530f0c413e5e',\n",
870
+ " '5642eaadaf464c93951528567dcda83b',\n",
871
+ " 'e6d1b1da8ffb4c5d9d5646aeee6b676f',\n",
872
+ " '210a1e9af9544dc6898b3df55ff4d195',\n",
873
+ " '4aa122926eb24f39b2624760eced5439',\n",
874
+ " 'cd30b62880fb42e0916796ae7303966d',\n",
875
+ " '6ffd6a8e86b149d08cd5220355b75f8a',\n",
876
+ " 'aad9aaad19404082a2d4380ba6072ba3',\n",
877
+ " 'b657b944546b4fdf90f382f2727a7410',\n",
878
+ " 'dbb42f36c90944ebb153a5a6831969a1',\n",
879
+ " '2b8b61ab6e9d406ba6127352f997bcf9',\n",
880
+ " 'f5bb5fb5ab2947f29661e9efbdbed389',\n",
881
+ " 'ccf3a06d76564008a0c53192fe1b08b4',\n",
882
+ " '686564e69f5d48ccb89f67b118eae8ac',\n",
883
+ " '7512fc65000f4116a2fcb4440fe9d940',\n",
884
+ " '493a804f74ea4ce888f60908235add7f',\n",
885
+ " 'b588b0a2394b4d75af2564aa52b6e82d',\n",
886
+ " 'd3c1ec3bf4b74497988addcef097691d',\n",
887
+ " '3ef9aad90d234c0d8098908e3cfdb00f',\n",
888
+ " '8e8b67c7c7d347d5b4d0a74f18948cf3',\n",
889
+ " 'bf83810ffa8f48eda8a67f838c3a3790',\n",
890
+ " 'b5761f8b18cf4290ba72120d234b3b16',\n",
891
+ " 'eabef783ad3a4a108abdddb461ec6227',\n",
892
+ " '81e93b517dde488280eb9405fae4bc64',\n",
893
+ " 'b980e31df71f4693856663c0062f9400',\n",
894
+ " '27a53e5c4ef845e2973da2285e201af0',\n",
895
+ " '9afc58a3b66a4a878b86d8efada5c327',\n",
896
+ " 'f022fcf6e9764a98b8b7f29c613e9ec2',\n",
897
+ " '2c4ff6c4ba964a7f8b9ee0de935ede39',\n",
898
+ " '8e9c82c1ddae405585f76f2d8f90722a',\n",
899
+ " '35e5f4fb4b064d45bc0b8c1b8e2b40ad',\n",
900
+ " '50a56f35b0aa4828bcd1761af459d713',\n",
901
+ " '78b890fe451b45ab8813ef6683fb9238',\n",
902
+ " '4fa383c61d8048b4b97c3a913082814e',\n",
903
+ " 'f7bfed0d21a64c2592f4b6af6dd2467e',\n",
904
+ " 'e4752f805db64a57939d5afef0e42605',\n",
905
+ " 'a4454f51fc25489a9e72c158b3296049',\n",
906
+ " 'c0e2d33ebb4c4441991c6755792280c8',\n",
907
+ " '34cb50642b9e458d8c9e963e0fc5e5ff',\n",
908
+ " '65c3b0e8a8104d44b28fb1317594be56',\n",
909
+ " '51d6504c97ad4dd0afc8c57a7de177e8',\n",
910
+ " '34fe6fa26eff4f7b9837b357a227866a',\n",
911
+ " '11788bbf24214e25b858a513aeec8765',\n",
912
+ " '1f2201754a85417c8713a6cd8da98888',\n",
913
+ " 'c6ae1ab8a8474e77bbe3f5b899f9bf38',\n",
914
+ " 'f6bc5ba781e44def9f3fe10fb3dcdade',\n",
915
+ " '17996a19622742c9b56faa35bc2757e7',\n",
916
+ " 'b0f4226132d1400ea47d292ff752d194',\n",
917
+ " '5944753380674b07b382e17b05ecdcf4',\n",
918
+ " 'f4e0c2fcc428463981dc6d7c6c2512f6',\n",
919
+ " '16e2f85298544a42855bcc068144a784',\n",
920
+ " 'b08eb27465a14215810fde2eb905faa8',\n",
921
+ " 'bd4565df73a3477abf64947f0728dc4a',\n",
922
+ " 'd8081347a4ec49dba2d0511cff50a4a8',\n",
923
+ " '6337b6c11147465eaf80517a36a7418e',\n",
924
+ " 'b1f46b9dff6148fcb683de655cc3f9dc',\n",
925
+ " '55b55b45b0b04f51a2228383dfc5a253',\n",
926
+ " 'c4319f46001642e2a5f8c5c3f33950e3',\n",
927
+ " '529ca8731f6e4a81a2482e14772ccb03',\n",
928
+ " '420c28ea6da940258e6dc4a26a4a92e8',\n",
929
+ " '4a6c7f4753204d11bbf82b6b6927334c',\n",
930
+ " '567bcbe2e57445d9b11218b45f11cd16',\n",
931
+ " '4fc1340706b34e3c85d35de2674b454a',\n",
932
+ " '5e22b793389c4b8eb41144fd98b0b521',\n",
933
+ " '422afa67dc704ef98e73c9174ba9f068',\n",
934
+ " '9b9f99334e3a4e76b0bdd925b42e875e',\n",
935
+ " 'b2d27bb8740449bbb0ce62348d97395e',\n",
936
+ " '6519c95e8d50404cb9b5bdea4d297821',\n",
937
+ " 'e6334a7c25fb44f2b6d9045f278e4abe',\n",
938
+ " 'c373245dde1b461cbfa095b9b18abfae',\n",
939
+ " 'c4608345663d4dc486b6012eda75d794',\n",
940
+ " 'a105906191b7472389221b5c06010783',\n",
941
+ " '0cc26425cf6c43098b1a8fd5b007a512',\n",
942
+ " '5177e702bc5d40bc99727fc477f4545b',\n",
943
+ " 'b44c66794574478b8605891bf5d5e926',\n",
944
+ " '9765606e5b39414f89e66b4dded1d7d4',\n",
945
+ " 'ac73340beaaf4a3bbfb57f31f004ded2',\n",
946
+ " '18cc575566fc49f68e610bf2dbe5f880',\n",
947
+ " '8f5a1fcf8a294afe8757549b3413d6f5',\n",
948
+ " '5102373c597241dabfe3a6bdd34f85bd',\n",
949
+ " 'e3ffa5dd88b44f9caf4d9f61b50ff267',\n",
950
+ " 'ab0d0239fba94b3582007dc9589f42e5',\n",
951
+ " '6994b5e2d6644c959ed83c0905bbcb50',\n",
952
+ " '699397f2bcc647f086f84ac5c9ed8131',\n",
953
+ " '98e4fa984c964b898f07feb368f75543',\n",
954
+ " 'f3f85d5221244baaa093d70cb24bbc5e',\n",
955
+ " 'c952a6f7b6d54d618ef052aa9636c938',\n",
956
+ " '94943b542b86461bb97d625032c41b43',\n",
957
+ " '743e92b2b8c9477f9438a1c6d41f0ad5',\n",
958
+ " 'c336ef8865d54132ac4e95990d31116d',\n",
959
+ " '931e098ecfd74298a36293ae14e25c12',\n",
960
+ " '9ab1e997bb7c439fac6c64c550e133aa',\n",
961
+ " '8f1816f3cae949e5bfd45218220a2381',\n",
962
+ " '1d6c9b75663b4b589fe646ce363881c3',\n",
963
+ " '1fa97de63a3b48ba899399083e93a295',\n",
964
+ " '64e57865587e49a097e21be4018b5cfd',\n",
965
+ " 'da81d2629ea64187bda1979a4d45b007',\n",
966
+ " 'a07aa15f22a449a4a748f18079260b80',\n",
967
+ " '6c595e8e9844499e9ba5cedf523d3c2b',\n",
968
+ " 'a5e2e2d7ca3343b283c87ede1e30010a',\n",
969
+ " '2b9033b5e81a4fa1809f8e4af49203d6',\n",
970
+ " '5b6c20f9dd38438cb38a7a45d5a6d098',\n",
971
+ " 'ed35586e0cab4b8f90e4c0e63d08271f',\n",
972
+ " 'a0f78c1bf01644229d9a1075fae17d1d',\n",
973
+ " 'b0ec177b5fa34751a361500fb356ee08',\n",
974
+ " '968ae8754c1c4bb0a5ebe1f3c091e0ea',\n",
975
+ " '1f0b766c681f4700b77c049edb5e4ba5',\n",
976
+ " '98bbcbe02b194e13a60d97be3685e49d',\n",
977
+ " '827aa6145293483e8f5080fdb72bc7d2',\n",
978
+ " '8e2e826fd0fa48f5a94a8ff84cbffa55',\n",
979
+ " '6ed5e810a08d4bfa8ec4f6a55996ca48',\n",
980
+ " '287bf07be853465693375dc71b3db17b',\n",
981
+ " '6ad457d7e8f9457ab08364201ff331fd',\n",
982
+ " 'cc1991aef98f4602a58aea8decd79d79',\n",
983
+ " 'e7ee0d344154475597a235e7000ddc90',\n",
984
+ " 'b8d86ce7007642729185576238d0bda6',\n",
985
+ " '46824192c6f64abdba6ec39692da4602',\n",
986
+ " '3dd66e1f61c244b2bf68b6ac63fb3fbc',\n",
987
+ " '637aaee6ddd8485da7a5930211c00292',\n",
988
+ " '341d38f915704937905763a3f2b83301',\n",
989
+ " '8b0184734c684ec8a0f7e57240d89d5b',\n",
990
+ " '7e2ae0eae73d4812a1cac85ccd121116',\n",
991
+ " '7936fe08de634e00986820ed1dc1d61b',\n",
992
+ " '1e56d63bab5a47ebb278b7a34ea036dc',\n",
993
+ " 'fe189562bbf942ce9b8c07aa48b6c294',\n",
994
+ " 'ca3f7929b81e47ac949c81288b174922',\n",
995
+ " 'bb8240806c904acc83100bb2684615bf',\n",
996
+ " '3cc5f7b4dfd346f1ac0aad6c129fd6be',\n",
997
+ " 'bb8f244d648347d8ba1f56def0b9f711',\n",
998
+ " '77adc7a9925941399cd45d85acf996e3',\n",
999
+ " 'c945521c151043fc9afc43ed194c18cb',\n",
1000
+ " 'c4cc585e54134c0b84a131551b3e5600',\n",
1001
+ " '637c05441b704a4e8fbbf701cc9f39d1',\n",
1002
+ " '416d117f858f4516bd717e3a7c091b0d',\n",
1003
+ " '8ee7a2c95f724df6b11e3a87d2015d83',\n",
1004
+ " '05795d3b716e492a8165e12c5499bfaf',\n",
1005
+ " '55723a43913f40be894b13000f6f862d',\n",
1006
+ " 'bfbcc3c72f02466d94a1888c0d2ecf76',\n",
1007
+ " '48614898c1144b09bfb0f67e5b9912f6',\n",
1008
+ " '430ce9f53b004056b7ae307fe0ac5ac4',\n",
1009
+ " '9f3e5dbb8e3f4a7588b4d792a7f7c669',\n",
1010
+ " '832b75f29b294a8490ee52af63653488',\n",
1011
+ " '873735e98f9c49e9888974ec624f366f',\n",
1012
+ " 'c49e10e95ed4467cb94d3c3c9a0cb1b5',\n",
1013
+ " '05e147f622bd4b9a9c7626ccfb97e56d',\n",
1014
+ " '9527ddee0b844fb180ab2beb0fcbf1ab',\n",
1015
+ " 'e808323f62a84002ab2ffff554ed0c13',\n",
1016
+ " '138dbae7b585474996990c796dd45336',\n",
1017
+ " '70439b4ec2184c33a84c8181e51afaca',\n",
1018
+ " '6c735ef186b841cfad58a50e8a432b83',\n",
1019
+ " 'd9fda9111a9947a59d06b13903e8880a',\n",
1020
+ " '9af00700b03944149d162a43ea537679',\n",
1021
+ " 'd078b2b1157e42759162a7783e21e979',\n",
1022
+ " 'dfaa3b7c8ed84d4d829672cd5f07d2d0',\n",
1023
+ " '83378b748e7f40d18693cf0727bc7d99',\n",
1024
+ " 'db86a0f7238e444fa0aec9edba6a897f',\n",
1025
+ " '0add55af14574a7db9c51d2f0b850157',\n",
1026
+ " '16cba28af57e4c0ea0c436a68fd480c0',\n",
1027
+ " '893d3ddb31dc4a3995f7700c02ab602a',\n",
1028
+ " 'f0daacb57cce423fa9acba3020bb1959',\n",
1029
+ " 'db8a522dca6b4e00b24921661783fa91',\n",
1030
+ " '4cefde807c5f4e40b32bcd34aefbb5b0',\n",
1031
+ " '738f9ff5304544d492675979e6b7f164',\n",
1032
+ " '4e6746e719814cef9ece1d3583d7e711',\n",
1033
+ " '633ece730cef4eb5983c18a7d2cd6aec',\n",
1034
+ " '2a3731dfdd884f838ea83e160666dcd5',\n",
1035
+ " '81f76060783840ec934bc12ff07bd176',\n",
1036
+ " 'd8464d763db5479692095ed9cd7cdcf3',\n",
1037
+ " 'd225bce351bf43d08a9a00ec5cddd83d',\n",
1038
+ " '9c45c389ca4141de9e021687bd69bba3',\n",
1039
+ " 'b96823a406f948298e52f80838af180f',\n",
1040
+ " '7b246971337e4bfa9364956b4a694835',\n",
1041
+ " '0e53eefaadf64881aae56d77e262fa9f',\n",
1042
+ " '8c1fccd23b7b40fabd6c83c1d3d26297',\n",
1043
+ " 'dde4c7a526c64395914be75d8c353573',\n",
1044
+ " '4bd8dbb9d409400b8f83e3dc14e63e63',\n",
1045
+ " '75e8d73b68e84d4eb272c1a842298f89',\n",
1046
+ " '3b7403e3471c4c96831a5eca4b2ae7ee',\n",
1047
+ " 'd0ec477e69af4415b055570a302ee3d3',\n",
1048
+ " 'b672ce011f584caeb171d63816e41439',\n",
1049
+ " '48dec8799957472ea51d60c81183e54a',\n",
1050
+ " '298a6aa9d7e741e59c36a023d6bcd219',\n",
1051
+ " '29c816ad23534ac2879315aba075b63d',\n",
1052
+ " 'da282571fc60419caf365def5c5356bc',\n",
1053
+ " '8279402a063c4201ae32c00d2aa69fce',\n",
1054
+ " '2aaac3605f424cada3a3dc62a654e414',\n",
1055
+ " '77940e5c28c841c59a78226ece301486',\n",
1056
+ " 'b73719d51fca4aa4a86443643a4e144e',\n",
1057
+ " '99bc97d433384e5685683bedb1ce9dd8',\n",
1058
+ " '72a661727cce40009b899e7abe6ef2b9',\n",
1059
+ " '953dfc85b64d4eff85a1a2d1a7fda668',\n",
1060
+ " 'd6bef59412b64e23b1519941858aca7c',\n",
1061
+ " '8345b2c9697e420e83f41d5d0b2e2e65',\n",
1062
+ " '32a58421fe184b21b0c91fdcf729f9c0',\n",
1063
+ " 'f4041d29fe0a4304a2b527fe21a50700',\n",
1064
+ " '9f6c704b0f024fac97c8aa450fa9f978',\n",
1065
+ " '9cb98fcbfcb54703b203de9ce9d2251c',\n",
1066
+ " 'dc8a9026deb54e4c8aa98ee90d76176b',\n",
1067
+ " '07d71b8d4bd04091b9c45e840c07dbf6',\n",
1068
+ " '43b9f91df5f84ac7bb2e071527817665',\n",
1069
+ " '9b2e77a7bd07496ab08c99ec6ba978cc',\n",
1070
+ " '4e51c4bcd7b74204a19de52585164ad5',\n",
1071
+ " 'ac7930b407464b41a4096ebd4c60a501',\n",
1072
+ " 'd43737cb401140d680aedd6506dcfe3e',\n",
1073
+ " '2af6b3f7d066414f8d610154633204c4',\n",
1074
+ " '354a4a082a48444ca48a357a240c3e3f',\n",
1075
+ " 'd59cd90793884dc4a61352be5720f36a',\n",
1076
+ " '497a69d3209c43deb21765254c236399',\n",
1077
+ " '71818ba634014a4c9288f288600e7e00',\n",
1078
+ " 'ce315225b22a4d97927af2a23934df7a',\n",
1079
+ " '965c225e4ba54101a8aa5ab8092f42c8',\n",
1080
+ " 'aae00d4e25df49e08e0c6dad88d8699c',\n",
1081
+ " '5c693f7864de4196abed1407d7804c40',\n",
1082
+ " 'bb18e0fc15e040b4b6d069db7e79b0e4',\n",
1083
+ " 'b8d936502a0b4081b8a7c5062002dc9f',\n",
1084
+ " 'a059ca68ebf4412480f60e39ae5636d8',\n",
1085
+ " '7fb9fcb63b4b44fba1208f0f5c92a4fe',\n",
1086
+ " '702ca4a6e0144e80a48c94af01ae120d',\n",
1087
+ " 'a58d50523f1042fabb2a04373642009b',\n",
1088
+ " '5ab2815403f44432be2e60ebceae306f',\n",
1089
+ " '486a1a60eb214a2aa6ad519204607b02',\n",
1090
+ " '6462f9318c154a199edab5eeb3ef0e10',\n",
1091
+ " '481f28f5a16e49b380c51a100074b69a',\n",
1092
+ " 'da778678ac5c44cd856ccb6bd3fc9c78',\n",
1093
+ " '41976f6def6649c8a2ef3c2e448b3416',\n",
1094
+ " 'bc1092398c944d8eb17c25628aef0c95',\n",
1095
+ " '78c9585658f6477ab754acf43c9dd4de',\n",
1096
+ " 'ba925aba480346d48d8a4c2d2b7fe5bc',\n",
1097
+ " 'bdb9aa5f50184056911720f4ab28dd83',\n",
1098
+ " 'a79a7c015bad45a6adb84a4f6ef2f041',\n",
1099
+ " '44c129acd19d4356b1e0e1d912e68761',\n",
1100
+ " '7011616949b34d52a682db6dd9c615a8',\n",
1101
+ " '5e52a63a8bf342a18210b6c8049fcfb2',\n",
1102
+ " 'e558e510794842a7a4a103dd878bff80',\n",
1103
+ " 'c3bf3329ef484097a74c8cd0bf73856b',\n",
1104
+ " '649985412b114192bc333e07ba123899',\n",
1105
+ " '52ed79b8e1f34fb8953be287491a6656',\n",
1106
+ " 'f7ffe18d81f044d9840c626538caf7de',\n",
1107
+ " '72a456d82f8a48bfb051830114c2eafd',\n",
1108
+ " '6f6314a34a81410f9b2331067812676b',\n",
1109
+ " 'c9ace6fa0bd84b5c84ca0d99c297b3dd',\n",
1110
+ " '26c8bb91b95d4255a5e8f258e0503f5c',\n",
1111
+ " 'd3a8dce28c9540f6b59fd50d04377742',\n",
1112
+ " 'f81efc93d3bf4778b730f731748ce38c',\n",
1113
+ " 'd46c618f64d845f587909a6afc1f9f87',\n",
1114
+ " '31f9e8bccd6e4f6fa6dbf45e2b3a00c3',\n",
1115
+ " '969f7c2de2af43f6bfcf4b2068c16e12',\n",
1116
+ " '2b37e809f4cf483f87e21841d34c0b5c',\n",
1117
+ " '72bf28784d8d4b7abac394760dfc0534',\n",
1118
+ " 'b7188da450224041a8525ff29c90ef6b',\n",
1119
+ " 'ffaa7164b8b74a8391ca47aeb5e3a8a1',\n",
1120
+ " '77de90a2dd03450bbe824c75014db2fd',\n",
1121
+ " '56387f48e2ac468e8dad50302e409034',\n",
1122
+ " '54dbf8ad95344089a9b7334691a5cbff',\n",
1123
+ " '17024cfc2b7b4be58535184c21a2dbf0',\n",
1124
+ " '3c3dfacf03f94b5dbcf2ffc6ae89f41b',\n",
1125
+ " '8f29dfd951904e8d9fccf91f4c63ad3e',\n",
1126
+ " '864c43aafbbb4ca2af4a592819815a92',\n",
1127
+ " '77c8c4fb1a4947bdac35a95c8d54ee69',\n",
1128
+ " 'c418af9237e043059e55fc32a9c8d8a9',\n",
1129
+ " 'e737bbaa4ecb4f30a5ae74d8761ba07b',\n",
1130
+ " '51da226a308e43d5a23230cef89d2081',\n",
1131
+ " 'bc7079053fb44364b04efb4330424f70',\n",
1132
+ " '7096ee7a944c4583bc524da2f401fb32',\n",
1133
+ " '908682550c3b40689b7addec79bb1ab6',\n",
1134
+ " '850d2af5f9e442cdbb24540494a23806',\n",
1135
+ " '8e02955c059b4651b4cf1c22066b4a34',\n",
1136
+ " '81243ae08d024071afb1ec5353c8e26e',\n",
1137
+ " 'f0618e80d85a42c9bddf76b2c31c5ed0',\n",
1138
+ " '0eed183adf2e4e9e8ec35722c099d26d',\n",
1139
+ " 'e1a402e148d3490db51a0db71a221274',\n",
1140
+ " '71514cf17a4f42e7b85b2e13587896c4',\n",
1141
+ " '0cd46157f72d4a6eaedbf3fee6894a5c',\n",
1142
+ " 'bf7066f624494571a1c70692881a24e2',\n",
1143
+ " 'bdcf49161ad24acfb91061776c48469a',\n",
1144
+ " '363044f36bfb427baecae1292e51342a',\n",
1145
+ " 'f6c4453768d8466497083ac7309cdbdd',\n",
1146
+ " '07ad398bfe104cc28dc6cd9f4ab7eda9',\n",
1147
+ " '69a34390fb6c44029429ae53dfd7ca28',\n",
1148
+ " 'd336aec2ce584ec285b7860172b93bd3',\n",
1149
+ " '50e34f1577634025aa4b591884f44852',\n",
1150
+ " '6ece31fed1ab464c920f5ecdf049e056',\n",
1151
+ " 'de379d13bea14465ad64cf651c6fff54',\n",
1152
+ " '397419238b854030be0a73e05010c3b5',\n",
1153
+ " '33ce9e98f4564069b439032ccbf8bc80',\n",
1154
+ " '21660dd58bf5479c86745cff321216f8',\n",
1155
+ " 'bb1354030ad24a9e8d0e641247081f4e',\n",
1156
+ " 'a8bdcd2e3ff548e0ace28546c0cb5c92',\n",
1157
+ " '25ec9107756247238f1ac529490bc5dc',\n",
1158
+ " '19a5e4f5fa1b497a9282c3cbdabfadf4',\n",
1159
+ " '01aff872548943ee92b9c2509be90b07',\n",
1160
+ " '6710b7c907a049acb54740e54d39b6c1',\n",
1161
+ " 'fa64dc8082d8414ba9493193140fe086',\n",
1162
+ " '6ec7b20e1e534ff98fe4a772ce2787ec',\n",
1163
+ " '4560bef431a44aada978802d34ce3a9e',\n",
1164
+ " '8b4ba9865b084a0ebe837922e328ad88',\n",
1165
+ " '4490baffe8984c7ca1b3f2797bf704cc',\n",
1166
+ " '020feb5abce74457856b67c6544cc6ea',\n",
1167
+ " '66be146104b2420d81ffa672539571ab',\n",
1168
+ " 'ade42916d91246a29a520205ea74cd3e',\n",
1169
+ " '61dcde64c41f41faa405c274282a191b',\n",
1170
+ " 'e22d3f9fc0f44502bacc72110643cd3c',\n",
1171
+ " 'e758edb904dc40afb095e83f92151a3a',\n",
1172
+ " '234f7a12a5954d169e5c9ec10d78d745',\n",
1173
+ " 'b939f1cd82d64f8b903a0e138ef95587']"
1174
  ]
1175
  },
1176
+ "execution_count": 14,
1177
  "metadata": {},
1178
  "output_type": "execute_result"
1179
  }
 
1206
  },
1207
  {
1208
  "cell_type": "code",
1209
+ "execution_count": 15,
1210
  "metadata": {},
1211
  "outputs": [],
1212
  "source": [
 
1216
  },
1217
  {
1218
  "cell_type": "code",
1219
+ "execution_count": 16,
1220
  "metadata": {},
1221
  "outputs": [
1222
  {
1223
  "data": {
1224
  "text/plain": [
1225
+ "[Document(metadata={'source': 'https://www.whitehouse.gov/wp-content/uploads/2022/10/Blueprint-for-an-AI-Bill-of-Rights.pdf', 'file_path': 'https://www.whitehouse.gov/wp-content/uploads/2022/10/Blueprint-for-an-AI-Bill-of-Rights.pdf', 'page': 11, 'total_pages': 73, 'format': 'PDF 1.6', 'title': 'Blueprint for an AI Bill of Rights', 'author': '', 'subject': '', 'keywords': '', 'creator': 'Adobe Illustrator 26.3 (Macintosh)', 'producer': 'iLovePDF', 'creationDate': \"D:20220920133035-04'00'\", 'modDate': \"D:20221003104118-04'00'\", 'trapped': '', '_id': '9d1df59c-40d5-4e12-9e59-2cf3f7ba07cc', '_collection_name': 'ai-safety-ft-arctic-embed-l-recursive'}, page_content='FROM \\nPRINCIPLES \\nTO PRACTICE \\nA TECHINCAL COMPANION TO\\nTHE Blueprint for an \\nAI BILL OF RIGHTS\\n12'),\n",
1226
+ " Document(metadata={'source': 'https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf', 'file_path': 'https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf', 'page': 50, 'total_pages': 64, 'format': 'PDF 1.6', 'title': 'Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile', 'author': 'National Institute of Standards and Technology', 'subject': '', 'keywords': '', 'creator': 'Acrobat PDFMaker 24 for Word', 'producer': 'Adobe PDF Library 24.2.159', 'creationDate': \"D:20240805141702-04'00'\", 'modDate': \"D:20240805143048-04'00'\", 'trapped': '', '_id': 'e737bbaa-4ecb-4f30-a5ae-74d8761ba07b', '_collection_name': 'ai-safety-ft-arctic-embed-l-recursive'}, page_content='• Accessibility and reasonable \\naccommodations \\n• AI actor credentials and qualifications \\n• Alignment to organizational values \\n• Auditing and assessment \\n• Change-management controls \\n• Commercial use \\n• Data provenance'),\n",
1227
+ " Document(metadata={'source': 'https://www.whitehouse.gov/wp-content/uploads/2022/10/Blueprint-for-an-AI-Bill-of-Rights.pdf', 'file_path': 'https://www.whitehouse.gov/wp-content/uploads/2022/10/Blueprint-for-an-AI-Bill-of-Rights.pdf', 'page': 19, 'total_pages': 73, 'format': 'PDF 1.6', 'title': 'Blueprint for an AI Bill of Rights', 'author': '', 'subject': '', 'keywords': '', 'creator': 'Adobe Illustrator 26.3 (Macintosh)', 'producer': 'iLovePDF', 'creationDate': \"D:20220920133035-04'00'\", 'modDate': \"D:20221003104118-04'00'\", 'trapped': '', '_id': 'e6806550-dbd4-4ff3-9f34-3ceae002e131', '_collection_name': 'ai-safety-ft-arctic-embed-l-recursive'}, page_content='organization’s business processes or other activities, system goals, any human-run procedures that form a \\npart of the system, and specific performance expectations; a description of any data used to train machine \\nlearning models or for other purposes, including how data sources were processed and interpreted, a \\nsummary of what data might be missing, incomplete, or erroneous, and data relevancy justifications; the \\nresults of public consultation such as concerns raised and any decisions made due to these concerns; risk \\nidentification and management assessments and any steps taken to mitigate potential harms; the results of \\nperformance testing including, but not limited to, accuracy, differential demographic impact, resulting \\nerror rates (overall and per demographic group), and comparisons to previously deployed systems; \\nongoing monitoring procedures and regular performance testing reports, including monitoring frequency,'),\n",
1228
+ " Document(metadata={'source': 'https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf', 'file_path': 'https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf', 'page': 51, 'total_pages': 64, 'format': 'PDF 1.6', 'title': 'Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile', 'author': 'National Institute of Standards and Technology', 'subject': '', 'keywords': '', 'creator': 'Acrobat PDFMaker 24 for Word', 'producer': 'Adobe PDF Library 24.2.159', 'creationDate': \"D:20240805141702-04'00'\", 'modDate': \"D:20240805143048-04'00'\", 'trapped': '', '_id': '90868255-0c3b-4068-9b7a-ddec79bb1ab6', '_collection_name': 'ai-safety-ft-arctic-embed-l-recursive'}, page_content='lifecycle and informed by representative AI Actors (see Figure 3 of the AI RMF). Until new and rigorous'),\n",
1229
+ " Document(metadata={'source': 'https://www.whitehouse.gov/wp-content/uploads/2022/10/Blueprint-for-an-AI-Bill-of-Rights.pdf', 'file_path': 'https://www.whitehouse.gov/wp-content/uploads/2022/10/Blueprint-for-an-AI-Bill-of-Rights.pdf', 'page': 25, 'total_pages': 73, 'format': 'PDF 1.6', 'title': 'Blueprint for an AI Bill of Rights', 'author': '', 'subject': '', 'keywords': '', 'creator': 'Adobe Illustrator 26.3 (Macintosh)', 'producer': 'iLovePDF', 'creationDate': \"D:20220920133035-04'00'\", 'modDate': \"D:20221003104118-04'00'\", 'trapped': '', '_id': '46f14ba8-7100-4732-91cc-91cbaf1b6bcf', '_collection_name': 'ai-safety-ft-arctic-embed-l-recursive'}, page_content='for any resulting algorithmic discrimination. \\n26\\nAlgorithmic \\nDiscrimination \\nProtections'),\n",
1230
+ " Document(metadata={'source': 'https://www.whitehouse.gov/wp-content/uploads/2022/10/Blueprint-for-an-AI-Bill-of-Rights.pdf', 'file_path': 'https://www.whitehouse.gov/wp-content/uploads/2022/10/Blueprint-for-an-AI-Bill-of-Rights.pdf', 'page': 0, 'total_pages': 73, 'format': 'PDF 1.6', 'title': 'Blueprint for an AI Bill of Rights', 'author': '', 'subject': '', 'keywords': '', 'creator': 'Adobe Illustrator 26.3 (Macintosh)', 'producer': 'iLovePDF', 'creationDate': \"D:20220920133035-04'00'\", 'modDate': \"D:20221003104118-04'00'\", 'trapped': '', '_id': '121c5a69-2bac-4c50-8d5f-3311982e25ec', '_collection_name': 'ai-safety-ft-arctic-embed-l-recursive'}, page_content='BLUEPRINT FOR AN \\nAI BILL OF \\nRIGHTS \\nMAKING AUTOMATED \\nSYSTEMS WORK FOR \\nTHE AMERICAN PEOPLE \\nOCTOBER 2022'),\n",
1231
+ " Document(metadata={'source': 'https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf', 'file_path': 'https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf', 'page': 38, 'total_pages': 64, 'format': 'PDF 1.6', 'title': 'Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile', 'author': 'National Institute of Standards and Technology', 'subject': '', 'keywords': '', 'creator': 'Acrobat PDFMaker 24 for Word', 'producer': 'Adobe PDF Library 24.2.159', 'creationDate': \"D:20240805141702-04'00'\", 'modDate': \"D:20240805143048-04'00'\", 'trapped': '', '_id': 'bc109239-8c94-4d8e-b17c-25628aef0c95', '_collection_name': 'ai-safety-ft-arctic-embed-l-recursive'}, page_content='guide the design of provenance data-tracking techniques. \\nHuman-AI Configuration; \\nInformation Integrity \\nMS-2.10-003 Verify deduplication of GAI training data samples, particularly regarding synthetic \\ndata. \\nHarmful Bias and Homogenization \\nAI Actor Tasks: AI Deployment, AI Impact Assessment, Domain Experts, End-Users, Operation and Monitoring, TEVV'),\n",
1232
+ " Document(metadata={'source': 'https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf', 'file_path': 'https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf', 'page': 59, 'total_pages': 64, 'format': 'PDF 1.6', 'title': 'Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile', 'author': 'National Institute of Standards and Technology', 'subject': '', 'keywords': '', 'creator': 'Acrobat PDFMaker 24 for Word', 'producer': 'Adobe PDF Library 24.2.159', 'creationDate': \"D:20240805141702-04'00'\", 'modDate': \"D:20240805143048-04'00'\", 'trapped': '', '_id': 'fa64dc80-82d8-414b-a949-3193140fe086', '_collection_name': 'ai-safety-ft-arctic-embed-l-recursive'}, page_content='https://www.bloomberg.com/graphics/2023-generative-ai-bias/. \\nNational Institute of Standards and Technology (2024) Adversarial Machine Learning: A Taxonomy and \\nTerminology of Attacks and Mitigations https://csrc.nist.gov/pubs/ai/100/2/e2023/final \\nNational Institute of Standards and Technology (2023) AI Risk Management Framework. \\nhttps://www.nist.gov/itl/ai-risk-management-framework \\nNational Institute of Standards and Technology (2023) AI Risk Management Framework, Chapter 3: AI \\nRisks and Trustworthiness. \\nhttps://airc.nist.gov/AI_RMF_Knowledge_Base/AI_RMF/Foundational_Information/3-sec-characteristics \\nNational Institute of Standards and Technology (2023) AI Risk Management Framework, Chapter 6: AI \\nRMF Profiles. https://airc.nist.gov/AI_RMF_Knowledge_Base/AI_RMF/Core_And_Profiles/6-sec-profile \\nNational Institute of Standards and Technology (2023) AI Risk Management Framework, Appendix A: \\nDescriptions of AI Actor Tasks.'),\n",
1233
+ " Document(metadata={'source': 'https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf', 'file_path': 'https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf', 'page': 57, 'total_pages': 64, 'format': 'PDF 1.6', 'title': 'Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile', 'author': 'National Institute of Standards and Technology', 'subject': '', 'keywords': '', 'creator': 'Acrobat PDFMaker 24 for Word', 'producer': 'Adobe PDF Library 24.2.159', 'creationDate': \"D:20240805141702-04'00'\", 'modDate': \"D:20240805143048-04'00'\", 'trapped': '', '_id': '39741923-8b85-4030-be0a-73e05010c3b5', '_collection_name': 'ai-safety-ft-arctic-embed-l-recursive'}, page_content='54 \\nAppendix B. References \\nAcemoglu, D. (2024) The Simple Macroeconomics of AI https://www.nber.org/papers/w32487 \\nAI Incident Database. https://incidentdatabase.ai/ \\nAtherton, D. (2024) Deepfakes and Child Safety: A Survey and Analysis of 2023 Incidents and Responses. \\nAI Incident Database. https://incidentdatabase.ai/blog/deepfakes-and-child-safety/ \\nBadyal, N. et al. (2023) Intentional Biases in LLM Responses. arXiv. https://arxiv.org/pdf/2311.07611 \\nBing Chat: Data Exfiltration Exploit Explained. Embrace The Red. \\nhttps://embracethered.com/blog/posts/2023/bing-chat-data-exfiltration-poc-and-fix/ \\nBommasani, R. et al. (2022) Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome \\nHomogenization? arXiv. https://arxiv.org/pdf/2211.13972 \\nBoyarskaya, M. et al. (2020) Overcoming Failures of Imagination in AI Infused System Development and \\nDeployment. arXiv. https://arxiv.org/pdf/2011.13416 \\nBrowne, D. et al. (2023) Securing the AI Pipeline. Mandiant.'),\n",
1234
+ " Document(metadata={'source': 'https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf', 'file_path': 'https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf', 'page': 12, 'total_pages': 64, 'format': 'PDF 1.6', 'title': 'Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile', 'author': 'National Institute of Standards and Technology', 'subject': '', 'keywords': '', 'creator': 'Acrobat PDFMaker 24 for Word', 'producer': 'Adobe PDF Library 24.2.159', 'creationDate': \"D:20240805141702-04'00'\", 'modDate': \"D:20240805143048-04'00'\", 'trapped': '', '_id': 'e808323f-62a8-4002-ab2f-fff554ed0c13', '_collection_name': 'ai-safety-ft-arctic-embed-l-recursive'}, page_content='Priorities Related to Information Integrity Research and Development.')]"
1235
  ]
1236
  },
1237
+ "execution_count": 16,
1238
  "metadata": {},
1239
  "output_type": "execute_result"
1240
  }
Tasks/deliverables.md CHANGED
@@ -20,8 +20,10 @@ From the past experience and also in doing this mid term project, I understood o
20
 
21
  ***Deliverable 1*** Build a prototype and deploy to a Hugging Face Space, and include the public URL link to your space create a short (< 2 min) loom video demonstrating some initial testing inputs and outputs.
22
 
23
- HF URL:
24
- Loom Video:
 
 
25
 
26
  ***Deliverable 2*** How did you choose your stack, and why did you select each tool the way you did?
27
 
 
20
 
21
  ***Deliverable 1*** Build a prototype and deploy to a Hugging Face Space, and include the public URL link to your space create a short (< 2 min) loom video demonstrating some initial testing inputs and outputs.
22
 
23
+ HF URL: https://huggingface.co/spaces/jeevanions/SafeGuardAI
24
+ Git URL: https://huggingface.co/spaces/jeevanions/SafeGuardAI/tree/main
25
+ Loom Video: https://www.loom.com/share/ea8acb321d264431bbec3ccb40040222?sid=63168de0-609f-49ac-b901-2e857753d063
26
+
27
 
28
  ***Deliverable 2*** How did you choose your stack, and why did you select each tool the way you did?
29