SlideShare a Scribd company logo
© 2023, Amazon Web Services, Inc. or its affiliates.
© 2023, Amazon Web Services, Inc. or its affiliates.
Jonathan Katz
Principal Product Manager – Technical
Amazon RDS Open Source
Vectors are the new JSON
or "Going beyond the Page"
© 2023, Amazon Web Services, Inc. or its affiliates.
© 2023, Amazon Web Services, Inc. or its affiliates.
Vectors are the new JSON
2
© 2023, Amazon Web Services, Inc. or its affiliates.
© 2023, Amazon Web Services, Inc. or its affiliates.
Magnitude
© 2023, Amazon Web Services, Inc. or its affiliates.
Direction
© 2023, Amazon Web Services, Inc. or its affiliates.
Why use vectors?
• Math
• Physics
• Maps
• Artificial intelligence / machine learning
6
© 2023, Amazon Web Services, Inc. or its affiliates. 7
© 2023, Amazon Web Services, Inc. or its affiliates. 8
0.003049829158165096,0.18639789248165428,0.25620939279058064,0.8474032584483915,0.728909751352397,0.5150510395040762,0.4462516533698704,0.5236709561811317,0.23075271031726885,0.2372686347975339,0.9375801900227572,0.9064239595
240302,0.4651187831953436,0.26254337449177356,0.8550190813318466,0.9841195123557434,0.8949629761265854,0.3042150462800528,0.057239707391303796,0.10891993000094757,0.6202587844948866,0.7137745836868454,0.06048318180182832,0.72
75440976627969,0.9478888345354122,0.8075292635669378,0.006104610242815056,0.723315680514812,0.8404533531441913,0.25125447598935935,0.7878795080344219,0.2611767393761504,0.7249823457880282,0.5664013738334184,0.6664423050495287
,0.047870779146162334,0.6024105618756934,0.28159282587919066,0.2603034349390896,0.2542046099573376,0.3327296553204988,0.2429052644111387,0.06034160939414335,0.0704690858202035,0.07525846779974898,0.5113090488711158,0.17784307
958376644,0.008055114879436331,0.7253841358982029,0.5892576733958386,0.031036548480514625,0.8514886217774027,0.5359628134105705,0.23253434065398793,0.9932524820134176,0.290096698529549,0.061493269072208534,0.19796591975942945
,0.5745454363733558,0.10500231825551154,0.8749785303875726,0.16050691467961897,0.6607092358366629,0.6959470185805223,0.8304841585326201,0.9906126039820897,0.37756396267006664,0.24750520102363893,0.7688257200202528,0.229018785
4669945,0.7383023205335917,0.9526504517225298,0.6702366304370244,0.12340838272000454,0.837277567807817,0.13355887990899973,0.16756984658473328,0.020480357387445025,0.7102474499378957,0.47830720614514277,0.7584869382921582,0.3
3627673352437526,0.33973495270900855,0.8041895249569642,0.8477249425000863,0.1840268911963996,0.6614288138464417,0.0733066286605144,0.1540691524669242,0.027117438127323368,0.8556511309682406,0.8365708233650331,0.9148876865925
715,0.27809873307734634,0.9847176522094117,0.8341376068583024,0.4884153769148796,0.49402832531031393,0.9759849942839054,0.3024687238313639,0.3054492792959067,0.9631850034636251,0.6306196638541337,0.25281927918295466,0.9633999
981843218,0.8556476268707236,0.35436292433753636,0.9181200874584725,0.5330211011157004,0.3659282554036771,0.5191548141957298,0.9933155783239833,0.6985272342940974,0.13341211270217812,0.14939654682403614,0.6996626768527356,0.1
5274920318616836,0.7375454247353765,0.12547466888770487,0.020867445809852114,0.08862531355325842,0.8594089835042844,0.467169285835908,0.3259292275603194,0.6754817412472605,0.23752820683506926,0.9235739428656018,0.600996868196
102,0.9826246759026915,0.3596323121373821,0.9926429393046163,0.45436365848015825,0.9537925268703233,0.7878438072069436,0.32655451673684865,0.18200719773833995,0.17466165185684446,0.5548376371379398,0.968462058702201,0.4360127
9039461005,0.3831529322604226,0.463364825678358,0.9972517349699217,0.3281245329407163,0.9106631366236755,0.7198211244102204,0.4306104787062708,0.23199225425841163,0.6140834474634502,0.811014846466751,0.91963436283595,0.679995
246870515,0.8567318394809504,0.14683252560984172,0.14260090503150025,0.8465205833865603,0.8549052513061426,0.8231241188837579,0.41924114155588654,0.38507506362948263,0.25006575098701234,0.0699639742348559,0.9833550311307562,0
.2605607961817462,0.259751219897133,0.02974752594215957,0.4000184436063705,0.56251539587252,0.7588095331041487,0.5247394729399737,0.6386582169689774,0.6753040885419601,0.34278485901716493,0.32020485063128845,0.425275092637406
26,0.14547296876436278,0.9141495998126814,0.040762738089558326,0.32204932557293375,0.8561755675889025,0.83711470922659,0.6558611621265165,0.9120719749549835,0.8783390682648751,0.8461287182939046,0.19516388006501373,0.90823287
55599889,0.5057372708578178,0.9256808350182766,0.7941729566984499,0.6312156320217639,0.3372050641335811,0.45407002325999457,0.0907182103421924,0.300577230348992,0.8878090275893804,0.3114290718440529,0.5082835005874564,0.90912
65859289592,0.5889511705440604,0.0731643995090181,0.7648932788544478,0.07398910725642338,0.37532303126425504,0.16537776734281096,0.5569586346091491,0.41320471229252576,0.5076657196988315,0.16068925028316272,0.3847130576569562
,0.43543125218091916,0.20087330502095924,0.5937208155983953,0.8364121127564523,0.1689155375268001,0.826672536335348,0.5184907315083152,0.8372109994079331,0.3265766880792995,0.4516165540976509,0.8988998457554018,0.728577359563
8751,0.5046728999487016,0.7202643135137343,0.09277559449311212,0.9863765116823693,0.05656950793722615,0.26912621193846675,0.574617488821012,0.6496403434996161,0.9496949766656257,0.08131020257688348,0.447922842165589,0.4348822
0063391125,0.1975887454376135,0.28999679910503673,0.6710527089809872,0.1981560761511254,0.7203622407001546,0.6892261426735438,0.5979394664255508,0.10251205002051123,0.601888419029919,0.5944410266337989,0.8940782482579479,0.10
38290594697493,0.32220747530470817,0.14736676773501856,0.9973485966907916,0.3130935141094717,0.30621340760343685,0.8178173879797406,0.5610692958400634,0.386045815840081,0.967519534919262,0.8097180412961045,0.14271245221528517
,0.3678693154775097,0.7779673784677215,0.6239712961871895,0.3259315559082765,0.7455054482396442,0.962644104725257,0.9138400820508927,0.4166565532574751,0.775627551221465,0.4272355508432639,0.43946813542828167,0.40726595029018
85,0.23280199025453285,0.9544162732488246,0.7903299555340588,0.518175708676786,0.40854152359527873,0.559741640565548,0.20424190854972935,0.9061262547687292,0.6645701182166341,0.9417612949664544,0.3286445198182655,0.0661663600
3648324,0.8575535235888658,0.9780448942056097,0.906878474768515,0.6836150303737369,0.09081361022805723,0.2563514823662274,0.8449437256183039,0.7375439247910052,0.17226960846450723,0.251759683310226,0.8416976841571362,0.183602
27348457414,0.8562937493383949,0.2953087294177408,0.11968508369259823,0.6069678436358927,0.9877152267663867,0.27230669196485735,0.8499940280590259,0.5321402710719028,0.4443626806404417,0.6492937309038496,0.6510203249326985,0.
19211109959844208,0.763934356818897,0.08368129338246888,0.28924073707477405,0.22268720990674495,0.3433845445499948,0.4109245245673492,0.1046155910313864,0.07657503894720463,0.49429763722934084,0.13795127372135596,0.1117575707
5977444,0.7050411510649539,0.6338950210353609,0.8713185455257246,0.5313368061200201,0.8819643864984599,0.7745177804106511,0.0626726238350983,0.22828785567392273,0.23592504355521982,0.8589077320621961,0.516653944907091,0.17131
219226574146,0.7913014103977858,0.5667533726397558,0.7471386821577681,0.28212564092399006,0.420452513398736,0.010283762019302145,0.22199748716045065,0.5662042042191722,0.7878722539548519,0.3418149766672123,0.05535447442751717
5,0.06587915283929746,0.9762432269886503,0.14083836839100528,0.8062479029933911,0.2610934713032229,0.26676251460956024,0.5373702653937364,0.7558546584516677,0.07565204292131611,0.3857456900574263,0.19486676744174147,0.6598951
373903503,0.5931976468336408,0.7007532126076583,0.431177727629251,0.32196004461643213,0.11636923570781832,0.26736440608024026,0.13902869217847424,0.9863974946645726,0.9367183779619204,0.5979123544639506,0.5957612994500785,0.1
007942253443872,0.4471694956922043,0.49227738044253755,0.3710392323565692,0.3083302449968812,0.30142992133120217,0.07513135879123212,0.0745710871699039,0.9753584092028262,0.6872321449386298,0.3013690191998748,0.68537127879475
08,0.2810608194143924,0.36719324243578555,0.9900196745730696,0.2995581604401316,0.05118911786611591,0.5901006755335594,0.9354925337581719,0.7831827067647659,0.5295572826622958,0.877399749074879,0.7229849844585559,0.5562242064
95262,0.08759996663518166,0.8385113135143705,0.5823150253024991,0.42793924572137954,0.17803833592182627,0.8114191217912143,0.3819904481571612,0.4945896490589128,0.3632353117172471,0.21192990341563345,0.7642874853025248,0.8687
117951383279,0.9775246638275519,0.9094460166851484,0.41439450351180795,0.7831566479261092,0.4166401099689523,0.8354457950736922,0.6448210109227475,0.07988475871585266,0.4529530027371038,0.9327107284948788,0.3534428053282923,0
.5078262077374696,0.6347768993059759,0.7313667268301707,0.11353959666563895,0.6990197817254433,0.28936586970647227,0.5078392143333978,0.7013959445391791,0.32886143696090997,0.9758973704822864,0.56380401177503,0.92651892607582
2,0.2838770887574107,0.25579145412399384,0.5262181909728092,0.756940652780294,0.7263718105964934,0.20790256344214697,0.29173264616980177,0.6237096498334083,0.6551044316369179,0.32577973645615543,0.8475413310666333,0.531446259
9579386,0.8884261026200484,0.9193022839479994,0.4274562716916215,0.4232826990646217,0.6428614697740933,0.29516246105833943,0.49128289620072607,0.766792234884953,0.9257844666811827,0.217110898687352,0.7351022356386885,0.801423
2451978316,0.5136552177138505,0.1204561525036354,0.5906654571634355,0.4669067015637509,0.13337295607131594,0.4644932295617963,0.49771730573777617,0.006138980193121313,0.7179200071510401,0.4054289273828431,0.13075866432562222,
0.285819886194453,0.9610065864773567,0.6307008303612776,0.9317299086944182,0.32493745347351677,0.36938322317655903,0.9487034160287919,0.8956663435211674,0.576950512486242,0.2044998575366499,0.8268154915267445,0.93399007412639
53,0.5287662643860003,0.04401588702004133,0.031869671118101905,0.10932950531859476,0.9015072253500662,0.6831864617088179,0.3830433812043026,0.10929357802114836,0.5483989715204345,0.06937497005475635,0.17543350260351076,0.9702
931680744307,0.31830118555081555,0.33100272148012166,0.3867797932939965,0.9452420923577414,0.10448864271452152,0.4644021363303388,0.41902724092989274,0.6528552076589271,0.8329300403970947,0.19567210841596605,0.945391035696346
2,0.07648646003400117,0.7088000320729222,0.08525142339897585,0.7926614929870937,0.37533575924477347,0.9712075380467198,0.314161010077175,0.5636365544597624,0.8118455267394573,0.18167043282866047,0.33447618370067644,0.53739801
77527073,0.8207760090494212,0.5598771155060618,0.812458723315661,0.9328809520319652,0.48548827391470795,0.589538317374938,0.9989134212732473,0.8066754110779186,0.5361955264216469,0.44706185290136347,0.8638674649651144,0.11772
212031853257,0.7373123094378364,0.2964179382954839,0.3958614710526014,0.033620851569537535,0.9336075991629791,0.07556724910015333,0.3323710034423364,0.5953882717517018,0.5278470851785038,0.6444871267215646,0.02765478052902281
5,0.8850327220213501,0.16931234747461232,0.5340673362608825,0.02628332727484306,0.8542332140725506,0.5494555230603417,0.6314945868437789,0.3714973660250145,0.7393204833479103,0.48755770442043556,0.9543687133889094,0.492261579
0703624,0.28988577702968144,0.7083030437722719,0.8364820479067632,0.26442432836035223,0.923539740473899,0.5804786632967982,0.8973611414769564,0.19090029594385172,0.9510858616975355,0.5205083047693755,0.7603556975149317,0.5825
186251699712,0.5237620021321732,0.1382955047996397,0.6759274053081654,0.7125068099176595,0.28196614561746003,0.5910852667039386,0.6941303825773772,0.5590181096403093,0.44337019902363295,0.0420720293796073,0.39999920949987455,
0.4152904743104564,0.3835150394646547,0.8257315199272988,0.20520912672005664,0.13770565792973244,0.525472587292029,0.5859051326757871,0.8971099388662438,0.49808119463056144,0.47418305344412204,0.6632131152031171,0.34084957549
33867,0.2159830200386672,0.9784792267668365,0.7062373744186736,0.5612091756778526,0.055825554989286985,0.16807129411874655,0.41004145527270097,0.688008043203375,0.4962868413950652,0.04798678592732131,0.44305450369300203,0.613
1679288963952,0.1084916435499288,0.9088673748726279,0.7093331164130028,0.5000408976944115,0.9350131149208245,0.8634689880409212,0.7610502159510695,0.2183175929625989,0.9426464930280254,0.398670585712793,0.2821887816279194,0.2
0328208191184416,0.4548741358447934,0.6548715754290697,0.4184107296671691,0.3995297162154898,0.35985286475851197,0.14307473061241183,0.3426227796135173,0.7303046335724659,0.6696198440279808,0.0820622313135857,0.78669208302376
25,0.7087577215211311,0.5871649173453939,0.29735360309864234,0.5060200361378087,0.291713126771036,0.8593132510665988,0.2491874611967546,0.3973333635200156,0.17562578418895924,0.6723851134095646,0.8433206332882293,0.5862925569
757031,0.39460302185096197,0.3298574619385626,0.08633999822822602,0.5186693958933226,0.13856413475384244,0.16037753045039338,0.7524108020739817,0.4083528740397604,0.14336197236726633,0.5922296134590717,0.17254185951185264,0.2
5187672624444346,0.18215411670198733,0.726615554336707,0.19775948066525473,0.6502171988473684,0.11727720046996382,0.504884864310899,0.7468997428055957,0.47510705275687926,0.5537603917188179,0.23027474644279167,0.0665294161855
5985,0.7729963399649726,0.4094521145359735,0.6370513839150114,0.6088910155676217,0.4621325659011113,0.11319174753695194,0.341564487945039,0.9934636465304294,0.297227753569981,0.7328244053776913,0.6311450999071475,0.8440901108
017158,0.15514797351432819,0.08104602596240085,0.49662481729486174,0.8876186901886598,0.04044740877096942,0.8516169198563475,0.26929077648597755,0.8282467066551362,0.8809442986462663,0.5945587511571162,0.4381976893835038,0.45
645891923005877,0.4435954618268134,0.9803416732282741,0.28194380839847,0.7604786292220354,0.7654898505617886,0.3541891007560096,0.011414697414370067,0.5449695861628214,0.7827950459053703,0.2075164240522085,0.6758649278280906,
0.0554439805055722,0.22402408179082656,0.44984092489657,0.20142611099850072,0.2021725378636603,0.8882387955223372,0.4475422979857555,0.5042078339514582,0.2847085559918412,0.6820903566163103,0.7925305807392036,0.62322889648881
49,0.2634052122838142,0.9733630373009099,0.9017300092991363,0.5532375674290826,0.9991261787887424,0.11750396889071268,0.44547741255642137,0.8039341980687489,0.8939500761340611,0.3151848911928674,0.5182512914343462,0.378205264
5958096,0.6869011397829183,0.10407205957183052,0.5480067699689997,0.6338475706109143,0.9780782242518598,0.8206228388017074,0.4808312104378487,0.485162738616598,0.32610349576788167,0.7849523968684302,0.4563195194072378,0.30511
80678214003,0.4572974238537455,0.9638166279484572,0.32728609759492855,0.22600814737325337,0.47575953999646003,0.606858294386381,0.18709606637543885,0.9053451016853451,0.7225714493761046,0.1859076951207861,0.9015509000938309,0
.15081182034774443,0.6162413221106817,0.7058872551659015,0.2430669685977378,0.5884148017294031,0.9475041161074529,0.6114365999460425,0.9766288110478101,0.14447912926772588,0.497530656902228,0.551571242000545,0.424096282623402
5,0.9059704151167303,0.8129579833153429,0.8544592783288429,0.050935102703213886,0.6640650997798936,0.5830346238565767,0.8278167869285475,0.28298784896973217,0.450304101090115,0.41830426007102517,0.7626792333938361,0.516796149
1617277,0.7885632739167967,0.2869811219339624,0.5577234652871645,0.4721387833806787,0.43309028577887787,0.3004770094749887,0.17933809587426808,0.12740368744490382,0.5947491456227318,0.595024606540278,0.1638395722206205,0.3453
285042793155,0.20426355588516643,0.38923130948650453,0.19030229808697285,0.44731342822910136,0.5806663041043443,0.8305436981410423,0.49623415203229726
© 2023, Amazon Web Services, Inc. or its affiliates.
Dimensionality
• Machine learning algorithms create vector embeddings of "many
dimensionalities"
§ 256
§ 384
§ 768
§ 1536
§ 2048
§ 60K+
• Dimensionality keeps information about a particular attribute
9
© 2023, Amazon Web Services, Inc. or its affiliates.
Searching vector embeddings
• Vector normalization
§ Magnitude of 1
• Distance function
§ Euclidean distance (L2)
§ Cosine distance (cosine similarity)
§ Inner product
§ Taxicab / Manhattan (L1)
§ Chebyshev (L-inf)
10
© 2023, Amazon Web Services, Inc. or its affiliates.
K-nearest neighbor
SELECT *
FROM table
ORDER BY $VECTOR <-> embedding -- distance
LIMIT 5; -- k
11
© 2023, Amazon Web Services, Inc. or its affiliates. 12
100,000
© 2023, Amazon Web Services, Inc. or its affiliates. 13
1,000,000
© 2023, Amazon Web Services, Inc. or its affiliates. 14
100,000,000
© 2023, Amazon Web Services, Inc. or its affiliates. 15
1,000,000,000
© 2023, Amazon Web Services, Inc. or its affiliates.
Vector indexing methods
• ~20 years of modern research searching high dimensionality vectors
§ FAISS – open-source library of vector search algorithms
§ Leverage CPU/GPU acceleration
• "Approximate nearest neighbor" (ANN)
§ Tradeoff on performance / recall
• IVF FLAT (inverted indexes)
• HNSW (Hierarchical inverted small worlds)
16
© 2023, Amazon Web Services, Inc. or its affiliates.
pgvector
• Open source extension that provides vector data type, distance
operations, and indexing
• IVF FLAT index
• Can adjust performance / recall tradeoff through "probes"
• Connectors to interface with many programming languages
17
© 2023, Amazon Web Services, Inc. or its affiliates.
Quick recap on vectors in machine learning
• Vectors encode information about objects (text, images, videos)
• Vectors can have high dimensionality
• "Similarity search" is a popular operation
• Data sets can become very large
• Indexing techniques that can accelerate search at cost of "recall"
18
© 2023, Amazon Web Services, Inc. or its affiliates.
© 2023, Amazon Web Services, Inc. or its affiliates.
Going beyond the page
19
© 2023, Amazon Web Services, Inc. or its affiliates.
How big is a PostgreSQL page?
20
8192*
8192 – sizeof(page header)
© 2023, Amazon Web Services, Inc. or its affiliates.
How big is a 1536 dimensional vector?
21
1536 * 4 + 8 = 6152
© 2023, Amazon Web Services, Inc. or its affiliates.
How big is a 2048 dimensional vector?
22
2048 * 4 + 8 = 8200
X
© 2023, Amazon Web Services, Inc. or its affiliates. 23
But we can TOAST!
© 2023, Amazon Web Services, Inc. or its affiliates. 24
But we can TOAST (an index)!
X
© 2023, Amazon Web Services, Inc. or its affiliates.
What does this mean?
• PostgreSQL can only index vectors up to a certain dimensionality
without reduction
• Query plan costing becomes something developers need to worry
about
§ Cost of a sequential scan on a toasted column vs. index page
25
© 2023, Amazon Web Services, Inc. or its affiliates.
What can we do?
• Native support for vector operations in PostgreSQL – Functions / data types
• Mechanisms for managing vector data that goes beyond the page
• Performance: Indexing methods. Query plan costing. Parallelism (builds and
queries)
• Build on CPU acceleration work.
§ GPU acceleration – extension?
• Contribute to extensions (e.g. pgvector) / vice versa
26
© 2023, Amazon Web Services, Inc. or its affiliates.
© 2023, Amazon Web Services, Inc. or its affiliates.
Thank you!
27

More Related Content

What's hot

PostgreSQL
PostgreSQLPostgreSQL
[pgday.Seoul 2022] PostgreSQL with Google Cloud
[pgday.Seoul 2022] PostgreSQL with Google Cloud[pgday.Seoul 2022] PostgreSQL with Google Cloud
[pgday.Seoul 2022] PostgreSQL with Google Cloud
PgDay.Seoul
 
Amazon OpenSearch Deep dive - 내부구조, 성능최적화 그리고 스케일링
Amazon OpenSearch Deep dive - 내부구조, 성능최적화 그리고 스케일링Amazon OpenSearch Deep dive - 내부구조, 성능최적화 그리고 스케일링
Amazon OpenSearch Deep dive - 내부구조, 성능최적화 그리고 스케일링
Amazon Web Services Korea
 
Linux tuning to improve PostgreSQL performance
Linux tuning to improve PostgreSQL performanceLinux tuning to improve PostgreSQL performance
Linux tuning to improve PostgreSQL performance
PostgreSQL-Consulting
 
Amazon S3 Best Practice and Tuning for Hadoop/Spark in the Cloud
Amazon S3 Best Practice and Tuning for Hadoop/Spark in the CloudAmazon S3 Best Practice and Tuning for Hadoop/Spark in the Cloud
Amazon S3 Best Practice and Tuning for Hadoop/Spark in the Cloud
Noritaka Sekiyama
 
The Art of Database Experiments – PostgresConf Silicon Valley 2018 / San Jose
The Art of Database Experiments – PostgresConf Silicon Valley 2018 / San JoseThe Art of Database Experiments – PostgresConf Silicon Valley 2018 / San Jose
The Art of Database Experiments – PostgresConf Silicon Valley 2018 / San Jose
Nikolay Samokhvalov
 
2020.02.06 우리는 왜 glue를 버렸나?
2020.02.06 우리는 왜 glue를 버렸나?2020.02.06 우리는 왜 glue를 버렸나?
2020.02.06 우리는 왜 glue를 버렸나?
Thomas Hyun (동현) Park
 
데브시스터즈 데이터 레이크 구축 이야기 : Data Lake architecture case study (박주홍 데이터 분석 및 인프라 팀...
데브시스터즈 데이터 레이크 구축 이야기 : Data Lake architecture case study (박주홍 데이터 분석 및 인프라 팀...데브시스터즈 데이터 레이크 구축 이야기 : Data Lake architecture case study (박주홍 데이터 분석 및 인프라 팀...
데브시스터즈 데이터 레이크 구축 이야기 : Data Lake architecture case study (박주홍 데이터 분석 및 인프라 팀...
Amazon Web Services Korea
 
Trino: A Ludicrously Fast Query Engine - Pulsar Summit NA 2021
Trino: A Ludicrously Fast Query Engine - Pulsar Summit NA 2021Trino: A Ludicrously Fast Query Engine - Pulsar Summit NA 2021
Trino: A Ludicrously Fast Query Engine - Pulsar Summit NA 2021
StreamNative
 
PostgreSQL: Advanced indexing
PostgreSQL: Advanced indexingPostgreSQL: Advanced indexing
PostgreSQL: Advanced indexing
Hans-Jürgen Schönig
 
EMR 플랫폼 기반의 Spark 워크로드 실행 최적화 방안 - 정세웅, AWS 솔루션즈 아키텍트:: AWS Summit Online Ko...
EMR 플랫폼 기반의 Spark 워크로드 실행 최적화 방안 - 정세웅, AWS 솔루션즈 아키텍트::  AWS Summit Online Ko...EMR 플랫폼 기반의 Spark 워크로드 실행 최적화 방안 - 정세웅, AWS 솔루션즈 아키텍트::  AWS Summit Online Ko...
EMR 플랫폼 기반의 Spark 워크로드 실행 최적화 방안 - 정세웅, AWS 솔루션즈 아키텍트:: AWS Summit Online Ko...
Amazon Web Services Korea
 
[AWS Builders] Effective AWS Glue
[AWS Builders] Effective AWS Glue[AWS Builders] Effective AWS Glue
[AWS Builders] Effective AWS Glue
Amazon Web Services Korea
 
Amazon Timestream 시계열 데이터 전용 DB 소개 :: 변규현 - AWS Community Day 2019
Amazon Timestream 시계열 데이터 전용 DB 소개 :: 변규현 - AWS Community Day 2019Amazon Timestream 시계열 데이터 전용 DB 소개 :: 변규현 - AWS Community Day 2019
Amazon Timestream 시계열 데이터 전용 DB 소개 :: 변규현 - AWS Community Day 2019
AWSKRUG - AWS한국사용자모임
 
FOSSASIA - MySQL Cookbook 4e Journey APR 2023.pdf
FOSSASIA - MySQL Cookbook 4e Journey APR 2023.pdfFOSSASIA - MySQL Cookbook 4e Journey APR 2023.pdf
FOSSASIA - MySQL Cookbook 4e Journey APR 2023.pdf
Alkin Tezuysal
 
Amazon DynamoDB 키 디자인 패턴
Amazon DynamoDB 키 디자인 패턴Amazon DynamoDB 키 디자인 패턴
Amazon DynamoDB 키 디자인 패턴
Amazon Web Services Korea
 
Amazon DynamoDB Under the Hood: How We Built a Hyper-Scale Database (DAT321) ...
Amazon DynamoDB Under the Hood: How We Built a Hyper-Scale Database (DAT321) ...Amazon DynamoDB Under the Hood: How We Built a Hyper-Scale Database (DAT321) ...
Amazon DynamoDB Under the Hood: How We Built a Hyper-Scale Database (DAT321) ...
Amazon Web Services
 
Apache doris (incubating) introduction
Apache doris (incubating) introductionApache doris (incubating) introduction
Apache doris (incubating) introduction
leanderlee2
 
[Pgday.Seoul 2020] SQL Tuning
[Pgday.Seoul 2020] SQL Tuning[Pgday.Seoul 2020] SQL Tuning
[Pgday.Seoul 2020] SQL Tuning
PgDay.Seoul
 
Kubernetes Forum Seoul 2019: Re-architecting Data Platform with Kubernetes
Kubernetes Forum Seoul 2019: Re-architecting Data Platform with KubernetesKubernetes Forum Seoul 2019: Re-architecting Data Platform with Kubernetes
Kubernetes Forum Seoul 2019: Re-architecting Data Platform with Kubernetes
SeungYong Oh
 
Optimizing Kubernetes Resource Requests/Limits for Cost-Efficiency and Latenc...
Optimizing Kubernetes Resource Requests/Limits for Cost-Efficiency and Latenc...Optimizing Kubernetes Resource Requests/Limits for Cost-Efficiency and Latenc...
Optimizing Kubernetes Resource Requests/Limits for Cost-Efficiency and Latenc...
Henning Jacobs
 

What's hot (20)

PostgreSQL
PostgreSQLPostgreSQL
PostgreSQL
 
[pgday.Seoul 2022] PostgreSQL with Google Cloud
[pgday.Seoul 2022] PostgreSQL with Google Cloud[pgday.Seoul 2022] PostgreSQL with Google Cloud
[pgday.Seoul 2022] PostgreSQL with Google Cloud
 
Amazon OpenSearch Deep dive - 내부구조, 성능최적화 그리고 스케일링
Amazon OpenSearch Deep dive - 내부구조, 성능최적화 그리고 스케일링Amazon OpenSearch Deep dive - 내부구조, 성능최적화 그리고 스케일링
Amazon OpenSearch Deep dive - 내부구조, 성능최적화 그리고 스케일링
 
Linux tuning to improve PostgreSQL performance
Linux tuning to improve PostgreSQL performanceLinux tuning to improve PostgreSQL performance
Linux tuning to improve PostgreSQL performance
 
Amazon S3 Best Practice and Tuning for Hadoop/Spark in the Cloud
Amazon S3 Best Practice and Tuning for Hadoop/Spark in the CloudAmazon S3 Best Practice and Tuning for Hadoop/Spark in the Cloud
Amazon S3 Best Practice and Tuning for Hadoop/Spark in the Cloud
 
The Art of Database Experiments – PostgresConf Silicon Valley 2018 / San Jose
The Art of Database Experiments – PostgresConf Silicon Valley 2018 / San JoseThe Art of Database Experiments – PostgresConf Silicon Valley 2018 / San Jose
The Art of Database Experiments – PostgresConf Silicon Valley 2018 / San Jose
 
2020.02.06 우리는 왜 glue를 버렸나?
2020.02.06 우리는 왜 glue를 버렸나?2020.02.06 우리는 왜 glue를 버렸나?
2020.02.06 우리는 왜 glue를 버렸나?
 
데브시스터즈 데이터 레이크 구축 이야기 : Data Lake architecture case study (박주홍 데이터 분석 및 인프라 팀...
데브시스터즈 데이터 레이크 구축 이야기 : Data Lake architecture case study (박주홍 데이터 분석 및 인프라 팀...데브시스터즈 데이터 레이크 구축 이야기 : Data Lake architecture case study (박주홍 데이터 분석 및 인프라 팀...
데브시스터즈 데이터 레이크 구축 이야기 : Data Lake architecture case study (박주홍 데이터 분석 및 인프라 팀...
 
Trino: A Ludicrously Fast Query Engine - Pulsar Summit NA 2021
Trino: A Ludicrously Fast Query Engine - Pulsar Summit NA 2021Trino: A Ludicrously Fast Query Engine - Pulsar Summit NA 2021
Trino: A Ludicrously Fast Query Engine - Pulsar Summit NA 2021
 
PostgreSQL: Advanced indexing
PostgreSQL: Advanced indexingPostgreSQL: Advanced indexing
PostgreSQL: Advanced indexing
 
EMR 플랫폼 기반의 Spark 워크로드 실행 최적화 방안 - 정세웅, AWS 솔루션즈 아키텍트:: AWS Summit Online Ko...
EMR 플랫폼 기반의 Spark 워크로드 실행 최적화 방안 - 정세웅, AWS 솔루션즈 아키텍트::  AWS Summit Online Ko...EMR 플랫폼 기반의 Spark 워크로드 실행 최적화 방안 - 정세웅, AWS 솔루션즈 아키텍트::  AWS Summit Online Ko...
EMR 플랫폼 기반의 Spark 워크로드 실행 최적화 방안 - 정세웅, AWS 솔루션즈 아키텍트:: AWS Summit Online Ko...
 
[AWS Builders] Effective AWS Glue
[AWS Builders] Effective AWS Glue[AWS Builders] Effective AWS Glue
[AWS Builders] Effective AWS Glue
 
Amazon Timestream 시계열 데이터 전용 DB 소개 :: 변규현 - AWS Community Day 2019
Amazon Timestream 시계열 데이터 전용 DB 소개 :: 변규현 - AWS Community Day 2019Amazon Timestream 시계열 데이터 전용 DB 소개 :: 변규현 - AWS Community Day 2019
Amazon Timestream 시계열 데이터 전용 DB 소개 :: 변규현 - AWS Community Day 2019
 
FOSSASIA - MySQL Cookbook 4e Journey APR 2023.pdf
FOSSASIA - MySQL Cookbook 4e Journey APR 2023.pdfFOSSASIA - MySQL Cookbook 4e Journey APR 2023.pdf
FOSSASIA - MySQL Cookbook 4e Journey APR 2023.pdf
 
Amazon DynamoDB 키 디자인 패턴
Amazon DynamoDB 키 디자인 패턴Amazon DynamoDB 키 디자인 패턴
Amazon DynamoDB 키 디자인 패턴
 
Amazon DynamoDB Under the Hood: How We Built a Hyper-Scale Database (DAT321) ...
Amazon DynamoDB Under the Hood: How We Built a Hyper-Scale Database (DAT321) ...Amazon DynamoDB Under the Hood: How We Built a Hyper-Scale Database (DAT321) ...
Amazon DynamoDB Under the Hood: How We Built a Hyper-Scale Database (DAT321) ...
 
Apache doris (incubating) introduction
Apache doris (incubating) introductionApache doris (incubating) introduction
Apache doris (incubating) introduction
 
[Pgday.Seoul 2020] SQL Tuning
[Pgday.Seoul 2020] SQL Tuning[Pgday.Seoul 2020] SQL Tuning
[Pgday.Seoul 2020] SQL Tuning
 
Kubernetes Forum Seoul 2019: Re-architecting Data Platform with Kubernetes
Kubernetes Forum Seoul 2019: Re-architecting Data Platform with KubernetesKubernetes Forum Seoul 2019: Re-architecting Data Platform with Kubernetes
Kubernetes Forum Seoul 2019: Re-architecting Data Platform with Kubernetes
 
Optimizing Kubernetes Resource Requests/Limits for Cost-Efficiency and Latenc...
Optimizing Kubernetes Resource Requests/Limits for Cost-Efficiency and Latenc...Optimizing Kubernetes Resource Requests/Limits for Cost-Efficiency and Latenc...
Optimizing Kubernetes Resource Requests/Limits for Cost-Efficiency and Latenc...
 

Similar to Vectors are the new JSON in PostgreSQL

Vectors are the new JSON in PostgreSQL (SCaLE 21x)
Vectors are the new JSON in PostgreSQL (SCaLE 21x)Vectors are the new JSON in PostgreSQL (SCaLE 21x)
Vectors are the new JSON in PostgreSQL (SCaLE 21x)
Jonathan Katz
 
Revolutionizing API Development: Collaborative Workflows with Postman
Revolutionizing API Development: Collaborative Workflows with PostmanRevolutionizing API Development: Collaborative Workflows with Postman
Revolutionizing API Development: Collaborative Workflows with Postman
Postman
 
[Keynote] Data Driven Organizations with AWS Data - 발표자: Agnes Panosian, Head...
[Keynote] Data Driven Organizations with AWS Data - 발표자: Agnes Panosian, Head...[Keynote] Data Driven Organizations with AWS Data - 발표자: Agnes Panosian, Head...
[Keynote] Data Driven Organizations with AWS Data - 발표자: Agnes Panosian, Head...
Amazon Web Services Korea
 
Single View of Data
Single View of DataSingle View of Data
Single View of Data
confluent
 
AWS reInvent 2022 reCap AI/ML and Data
AWS reInvent 2022 reCap AI/ML and DataAWS reInvent 2022 reCap AI/ML and Data
AWS reInvent 2022 reCap AI/ML and Data
Chris Fregly
 
Re:cap día 1 del Aws Re:Invent 2023 - AWS UG Chile
Re:cap día 1 del Aws Re:Invent 2023 - AWS UG ChileRe:cap día 1 del Aws Re:Invent 2023 - AWS UG Chile
Re:cap día 1 del Aws Re:Invent 2023 - AWS UG Chile
Alvaro Garcia
 
Generative Artificial Intelligence for Macro-Fiscal Risks.pdf
Generative Artificial Intelligencefor Macro-Fiscal Risks.pdfGenerative Artificial Intelligencefor Macro-Fiscal Risks.pdf
Generative Artificial Intelligence for Macro-Fiscal Risks.pdf
Alex Barbosa Coqueiro
 
AWS Lambda Powertools walkthrough.pdf
AWS Lambda Powertools walkthrough.pdfAWS Lambda Powertools walkthrough.pdf
AWS Lambda Powertools walkthrough.pdf
Heitor Lessa
 
Get More from your Data: Accelerate Time-to-Value and Reduce TCO with Conflue...
Get More from your Data: Accelerate Time-to-Value and Reduce TCO with Conflue...Get More from your Data: Accelerate Time-to-Value and Reduce TCO with Conflue...
Get More from your Data: Accelerate Time-to-Value and Reduce TCO with Conflue...
HostedbyConfluent
 
[Keynote] Accelerating Business Outcomes with AWS Data - 발표자: Saeed Gharadagh...
[Keynote] Accelerating Business Outcomes with AWS Data - 발표자: Saeed Gharadagh...[Keynote] Accelerating Business Outcomes with AWS Data - 발표자: Saeed Gharadagh...
[Keynote] Accelerating Business Outcomes with AWS Data - 발표자: Saeed Gharadagh...
Amazon Web Services Korea
 
커머스 스타트업의 효율적인 데이터 분석 플랫폼 구축기 - 하지양 데이터 엔지니어, 발란 / 강웅석 데이터 엔지니어, 크로키닷컴 :: AWS...
커머스 스타트업의 효율적인 데이터 분석 플랫폼 구축기 - 하지양 데이터 엔지니어, 발란 / 강웅석 데이터 엔지니어, 크로키닷컴 :: AWS...커머스 스타트업의 효율적인 데이터 분석 플랫폼 구축기 - 하지양 데이터 엔지니어, 발란 / 강웅석 데이터 엔지니어, 크로키닷컴 :: AWS...
커머스 스타트업의 효율적인 데이터 분석 플랫폼 구축기 - 하지양 데이터 엔지니어, 발란 / 강웅석 데이터 엔지니어, 크로키닷컴 :: AWS...
Amazon Web Services Korea
 
Unveiling the Inner Workings of Apache Kafka® with Flamegraphs with Christo L...
Unveiling the Inner Workings of Apache Kafka® with Flamegraphs with Christo L...Unveiling the Inner Workings of Apache Kafka® with Flamegraphs with Christo L...
Unveiling the Inner Workings of Apache Kafka® with Flamegraphs with Christo L...
HostedbyConfluent
 
Better Together: Delivering Graph Value with AWS & Neo4j - Antony Prasad The...
Better Together:  Delivering Graph Value with AWS & Neo4j - Antony Prasad The...Better Together:  Delivering Graph Value with AWS & Neo4j - Antony Prasad The...
Better Together: Delivering Graph Value with AWS & Neo4j - Antony Prasad The...
Neo4j
 
Are you ready for AI? Is AI ready for you?
Are you ready for AI? Is AI ready for you?Are you ready for AI? Is AI ready for you?
Are you ready for AI? Is AI ready for you?
KonfHubTechConferenc
 
Building observability to increase resiliency.pdf
Building observability to increase resiliency.pdfBuilding observability to increase resiliency.pdf
Building observability to increase resiliency.pdf
Nimas Hayu Merlina Anggarini
 
Better Together: Delivering Graph Value with AWS & Neo4j - Antony Prasad Thev...
Better Together: Delivering Graph Value with AWS & Neo4j - Antony Prasad Thev...Better Together: Delivering Graph Value with AWS & Neo4j - Antony Prasad Thev...
Better Together: Delivering Graph Value with AWS & Neo4j - Antony Prasad Thev...
Neo4j
 
Build Developer Experience Teams for Open Source
Build Developer Experience Teams for Open SourceBuild Developer Experience Teams for Open Source
Build Developer Experience Teams for Open Source
All Things Open
 
From Insights to Action, How to build and maintain a Data Driven Organization...
From Insights to Action, How to build and maintain a Data Driven Organization...From Insights to Action, How to build and maintain a Data Driven Organization...
From Insights to Action, How to build and maintain a Data Driven Organization...
Amazon Web Services Korea
 
Design, Build, and Modernize Your Web Applications with AWS
Design, Build, and Modernize Your Web Applications with AWSDesign, Build, and Modernize Your Web Applications with AWS
Design, Build, and Modernize Your Web Applications with AWS
Irene Luong
 
NEW LAUNCH! Introducing Amazon SageMaker - MCL365 - re:Invent 2017
NEW LAUNCH! Introducing Amazon SageMaker - MCL365 - re:Invent 2017NEW LAUNCH! Introducing Amazon SageMaker - MCL365 - re:Invent 2017
NEW LAUNCH! Introducing Amazon SageMaker - MCL365 - re:Invent 2017
Amazon Web Services
 

Similar to Vectors are the new JSON in PostgreSQL (20)

Vectors are the new JSON in PostgreSQL (SCaLE 21x)
Vectors are the new JSON in PostgreSQL (SCaLE 21x)Vectors are the new JSON in PostgreSQL (SCaLE 21x)
Vectors are the new JSON in PostgreSQL (SCaLE 21x)
 
Revolutionizing API Development: Collaborative Workflows with Postman
Revolutionizing API Development: Collaborative Workflows with PostmanRevolutionizing API Development: Collaborative Workflows with Postman
Revolutionizing API Development: Collaborative Workflows with Postman
 
[Keynote] Data Driven Organizations with AWS Data - 발표자: Agnes Panosian, Head...
[Keynote] Data Driven Organizations with AWS Data - 발표자: Agnes Panosian, Head...[Keynote] Data Driven Organizations with AWS Data - 발표자: Agnes Panosian, Head...
[Keynote] Data Driven Organizations with AWS Data - 발표자: Agnes Panosian, Head...
 
Single View of Data
Single View of DataSingle View of Data
Single View of Data
 
AWS reInvent 2022 reCap AI/ML and Data
AWS reInvent 2022 reCap AI/ML and DataAWS reInvent 2022 reCap AI/ML and Data
AWS reInvent 2022 reCap AI/ML and Data
 
Re:cap día 1 del Aws Re:Invent 2023 - AWS UG Chile
Re:cap día 1 del Aws Re:Invent 2023 - AWS UG ChileRe:cap día 1 del Aws Re:Invent 2023 - AWS UG Chile
Re:cap día 1 del Aws Re:Invent 2023 - AWS UG Chile
 
Generative Artificial Intelligence for Macro-Fiscal Risks.pdf
Generative Artificial Intelligencefor Macro-Fiscal Risks.pdfGenerative Artificial Intelligencefor Macro-Fiscal Risks.pdf
Generative Artificial Intelligence for Macro-Fiscal Risks.pdf
 
AWS Lambda Powertools walkthrough.pdf
AWS Lambda Powertools walkthrough.pdfAWS Lambda Powertools walkthrough.pdf
AWS Lambda Powertools walkthrough.pdf
 
Get More from your Data: Accelerate Time-to-Value and Reduce TCO with Conflue...
Get More from your Data: Accelerate Time-to-Value and Reduce TCO with Conflue...Get More from your Data: Accelerate Time-to-Value and Reduce TCO with Conflue...
Get More from your Data: Accelerate Time-to-Value and Reduce TCO with Conflue...
 
[Keynote] Accelerating Business Outcomes with AWS Data - 발표자: Saeed Gharadagh...
[Keynote] Accelerating Business Outcomes with AWS Data - 발표자: Saeed Gharadagh...[Keynote] Accelerating Business Outcomes with AWS Data - 발표자: Saeed Gharadagh...
[Keynote] Accelerating Business Outcomes with AWS Data - 발표자: Saeed Gharadagh...
 
커머스 스타트업의 효율적인 데이터 분석 플랫폼 구축기 - 하지양 데이터 엔지니어, 발란 / 강웅석 데이터 엔지니어, 크로키닷컴 :: AWS...
커머스 스타트업의 효율적인 데이터 분석 플랫폼 구축기 - 하지양 데이터 엔지니어, 발란 / 강웅석 데이터 엔지니어, 크로키닷컴 :: AWS...커머스 스타트업의 효율적인 데이터 분석 플랫폼 구축기 - 하지양 데이터 엔지니어, 발란 / 강웅석 데이터 엔지니어, 크로키닷컴 :: AWS...
커머스 스타트업의 효율적인 데이터 분석 플랫폼 구축기 - 하지양 데이터 엔지니어, 발란 / 강웅석 데이터 엔지니어, 크로키닷컴 :: AWS...
 
Unveiling the Inner Workings of Apache Kafka® with Flamegraphs with Christo L...
Unveiling the Inner Workings of Apache Kafka® with Flamegraphs with Christo L...Unveiling the Inner Workings of Apache Kafka® with Flamegraphs with Christo L...
Unveiling the Inner Workings of Apache Kafka® with Flamegraphs with Christo L...
 
Better Together: Delivering Graph Value with AWS & Neo4j - Antony Prasad The...
Better Together:  Delivering Graph Value with AWS & Neo4j - Antony Prasad The...Better Together:  Delivering Graph Value with AWS & Neo4j - Antony Prasad The...
Better Together: Delivering Graph Value with AWS & Neo4j - Antony Prasad The...
 
Are you ready for AI? Is AI ready for you?
Are you ready for AI? Is AI ready for you?Are you ready for AI? Is AI ready for you?
Are you ready for AI? Is AI ready for you?
 
Building observability to increase resiliency.pdf
Building observability to increase resiliency.pdfBuilding observability to increase resiliency.pdf
Building observability to increase resiliency.pdf
 
Better Together: Delivering Graph Value with AWS & Neo4j - Antony Prasad Thev...
Better Together: Delivering Graph Value with AWS & Neo4j - Antony Prasad Thev...Better Together: Delivering Graph Value with AWS & Neo4j - Antony Prasad Thev...
Better Together: Delivering Graph Value with AWS & Neo4j - Antony Prasad Thev...
 
Build Developer Experience Teams for Open Source
Build Developer Experience Teams for Open SourceBuild Developer Experience Teams for Open Source
Build Developer Experience Teams for Open Source
 
From Insights to Action, How to build and maintain a Data Driven Organization...
From Insights to Action, How to build and maintain a Data Driven Organization...From Insights to Action, How to build and maintain a Data Driven Organization...
From Insights to Action, How to build and maintain a Data Driven Organization...
 
Design, Build, and Modernize Your Web Applications with AWS
Design, Build, and Modernize Your Web Applications with AWSDesign, Build, and Modernize Your Web Applications with AWS
Design, Build, and Modernize Your Web Applications with AWS
 
NEW LAUNCH! Introducing Amazon SageMaker - MCL365 - re:Invent 2017
NEW LAUNCH! Introducing Amazon SageMaker - MCL365 - re:Invent 2017NEW LAUNCH! Introducing Amazon SageMaker - MCL365 - re:Invent 2017
NEW LAUNCH! Introducing Amazon SageMaker - MCL365 - re:Invent 2017
 

More from Jonathan Katz

Looking ahead at PostgreSQL 15
Looking ahead at PostgreSQL 15Looking ahead at PostgreSQL 15
Looking ahead at PostgreSQL 15
Jonathan Katz
 
Build a Complex, Realtime Data Management App with Postgres 14!
Build a Complex, Realtime Data Management App with Postgres 14!Build a Complex, Realtime Data Management App with Postgres 14!
Build a Complex, Realtime Data Management App with Postgres 14!
Jonathan Katz
 
High Availability PostgreSQL on OpenShift...and more!
High Availability PostgreSQL on OpenShift...and more!High Availability PostgreSQL on OpenShift...and more!
High Availability PostgreSQL on OpenShift...and more!
Jonathan Katz
 
Get Your Insecure PostgreSQL Passwords to SCRAM
Get Your Insecure PostgreSQL Passwords to SCRAMGet Your Insecure PostgreSQL Passwords to SCRAM
Get Your Insecure PostgreSQL Passwords to SCRAM
Jonathan Katz
 
Safely Protect PostgreSQL Passwords - Tell Others to SCRAM
Safely Protect PostgreSQL Passwords - Tell Others to SCRAMSafely Protect PostgreSQL Passwords - Tell Others to SCRAM
Safely Protect PostgreSQL Passwords - Tell Others to SCRAM
Jonathan Katz
 
Operating PostgreSQL at Scale with Kubernetes
Operating PostgreSQL at Scale with KubernetesOperating PostgreSQL at Scale with Kubernetes
Operating PostgreSQL at Scale with Kubernetes
Jonathan Katz
 
Building a Complex, Real-Time Data Management Application
Building a Complex, Real-Time Data Management ApplicationBuilding a Complex, Real-Time Data Management Application
Building a Complex, Real-Time Data Management Application
Jonathan Katz
 
Using PostgreSQL With Docker & Kubernetes - July 2018
Using PostgreSQL With Docker & Kubernetes - July 2018Using PostgreSQL With Docker & Kubernetes - July 2018
Using PostgreSQL With Docker & Kubernetes - July 2018
Jonathan Katz
 
An Introduction to Using PostgreSQL with Docker & Kubernetes
An Introduction to Using PostgreSQL with Docker & KubernetesAn Introduction to Using PostgreSQL with Docker & Kubernetes
An Introduction to Using PostgreSQL with Docker & Kubernetes
Jonathan Katz
 
Developing and Deploying Apps with the Postgres FDW
Developing and Deploying Apps with the Postgres FDWDeveloping and Deploying Apps with the Postgres FDW
Developing and Deploying Apps with the Postgres FDW
Jonathan Katz
 
On Beyond (PostgreSQL) Data Types
On Beyond (PostgreSQL) Data TypesOn Beyond (PostgreSQL) Data Types
On Beyond (PostgreSQL) Data Types
Jonathan Katz
 
Accelerating Local Search with PostgreSQL (KNN-Search)
Accelerating Local Search with PostgreSQL (KNN-Search)Accelerating Local Search with PostgreSQL (KNN-Search)
Accelerating Local Search with PostgreSQL (KNN-Search)
Jonathan Katz
 
Webscale PostgreSQL - JSONB and Horizontal Scaling Strategies
Webscale PostgreSQL - JSONB and Horizontal Scaling StrategiesWebscale PostgreSQL - JSONB and Horizontal Scaling Strategies
Webscale PostgreSQL - JSONB and Horizontal Scaling Strategies
Jonathan Katz
 
Indexing Complex PostgreSQL Data Types
Indexing Complex PostgreSQL Data TypesIndexing Complex PostgreSQL Data Types
Indexing Complex PostgreSQL Data Types
Jonathan Katz
 

More from Jonathan Katz (14)

Looking ahead at PostgreSQL 15
Looking ahead at PostgreSQL 15Looking ahead at PostgreSQL 15
Looking ahead at PostgreSQL 15
 
Build a Complex, Realtime Data Management App with Postgres 14!
Build a Complex, Realtime Data Management App with Postgres 14!Build a Complex, Realtime Data Management App with Postgres 14!
Build a Complex, Realtime Data Management App with Postgres 14!
 
High Availability PostgreSQL on OpenShift...and more!
High Availability PostgreSQL on OpenShift...and more!High Availability PostgreSQL on OpenShift...and more!
High Availability PostgreSQL on OpenShift...and more!
 
Get Your Insecure PostgreSQL Passwords to SCRAM
Get Your Insecure PostgreSQL Passwords to SCRAMGet Your Insecure PostgreSQL Passwords to SCRAM
Get Your Insecure PostgreSQL Passwords to SCRAM
 
Safely Protect PostgreSQL Passwords - Tell Others to SCRAM
Safely Protect PostgreSQL Passwords - Tell Others to SCRAMSafely Protect PostgreSQL Passwords - Tell Others to SCRAM
Safely Protect PostgreSQL Passwords - Tell Others to SCRAM
 
Operating PostgreSQL at Scale with Kubernetes
Operating PostgreSQL at Scale with KubernetesOperating PostgreSQL at Scale with Kubernetes
Operating PostgreSQL at Scale with Kubernetes
 
Building a Complex, Real-Time Data Management Application
Building a Complex, Real-Time Data Management ApplicationBuilding a Complex, Real-Time Data Management Application
Building a Complex, Real-Time Data Management Application
 
Using PostgreSQL With Docker & Kubernetes - July 2018
Using PostgreSQL With Docker & Kubernetes - July 2018Using PostgreSQL With Docker & Kubernetes - July 2018
Using PostgreSQL With Docker & Kubernetes - July 2018
 
An Introduction to Using PostgreSQL with Docker & Kubernetes
An Introduction to Using PostgreSQL with Docker & KubernetesAn Introduction to Using PostgreSQL with Docker & Kubernetes
An Introduction to Using PostgreSQL with Docker & Kubernetes
 
Developing and Deploying Apps with the Postgres FDW
Developing and Deploying Apps with the Postgres FDWDeveloping and Deploying Apps with the Postgres FDW
Developing and Deploying Apps with the Postgres FDW
 
On Beyond (PostgreSQL) Data Types
On Beyond (PostgreSQL) Data TypesOn Beyond (PostgreSQL) Data Types
On Beyond (PostgreSQL) Data Types
 
Accelerating Local Search with PostgreSQL (KNN-Search)
Accelerating Local Search with PostgreSQL (KNN-Search)Accelerating Local Search with PostgreSQL (KNN-Search)
Accelerating Local Search with PostgreSQL (KNN-Search)
 
Webscale PostgreSQL - JSONB and Horizontal Scaling Strategies
Webscale PostgreSQL - JSONB and Horizontal Scaling StrategiesWebscale PostgreSQL - JSONB and Horizontal Scaling Strategies
Webscale PostgreSQL - JSONB and Horizontal Scaling Strategies
 
Indexing Complex PostgreSQL Data Types
Indexing Complex PostgreSQL Data TypesIndexing Complex PostgreSQL Data Types
Indexing Complex PostgreSQL Data Types
 

Recently uploaded

Mind map of terminologies used in context of Generative AI
Mind map of terminologies used in context of Generative AIMind map of terminologies used in context of Generative AI
Mind map of terminologies used in context of Generative AI
Kumud Singh
 
Video Streaming: Then, Now, and in the Future
Video Streaming: Then, Now, and in the FutureVideo Streaming: Then, Now, and in the Future
Video Streaming: Then, Now, and in the Future
Alpen-Adria-Universität
 
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex ProofszkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
Alex Pruden
 
RESUME BUILDER APPLICATION Project for students
RESUME BUILDER APPLICATION Project for studentsRESUME BUILDER APPLICATION Project for students
RESUME BUILDER APPLICATION Project for students
KAMESHS29
 
National Security Agency - NSA mobile device best practices
National Security Agency - NSA mobile device best practicesNational Security Agency - NSA mobile device best practices
National Security Agency - NSA mobile device best practices
Quotidiano Piemontese
 
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdfObservability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Paige Cruz
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance
 
GridMate - End to end testing is a critical piece to ensure quality and avoid...
GridMate - End to end testing is a critical piece to ensure quality and avoid...GridMate - End to end testing is a critical piece to ensure quality and avoid...
GridMate - End to end testing is a critical piece to ensure quality and avoid...
ThomasParaiso2
 
Microsoft - Power Platform_G.Aspiotis.pdf
Microsoft - Power Platform_G.Aspiotis.pdfMicrosoft - Power Platform_G.Aspiotis.pdf
Microsoft - Power Platform_G.Aspiotis.pdf
Uni Systems S.M.S.A.
 
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Albert Hoitingh
 
GraphSummit Singapore | The Art of the Possible with Graph - Q2 2024
GraphSummit Singapore | The Art of the  Possible with Graph - Q2 2024GraphSummit Singapore | The Art of the  Possible with Graph - Q2 2024
GraphSummit Singapore | The Art of the Possible with Graph - Q2 2024
Neo4j
 
Pushing the limits of ePRTC: 100ns holdover for 100 days
Pushing the limits of ePRTC: 100ns holdover for 100 daysPushing the limits of ePRTC: 100ns holdover for 100 days
Pushing the limits of ePRTC: 100ns holdover for 100 days
Adtran
 
PCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase TeamPCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase Team
ControlCase
 
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
SOFTTECHHUB
 
Artificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopmentArtificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopment
Octavian Nadolu
 
UiPath Test Automation using UiPath Test Suite series, part 6
UiPath Test Automation using UiPath Test Suite series, part 6UiPath Test Automation using UiPath Test Suite series, part 6
UiPath Test Automation using UiPath Test Suite series, part 6
DianaGray10
 
20240607 QFM018 Elixir Reading List May 2024
20240607 QFM018 Elixir Reading List May 202420240607 QFM018 Elixir Reading List May 2024
20240607 QFM018 Elixir Reading List May 2024
Matthew Sinclair
 
The Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and SalesThe Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and Sales
Laura Byrne
 
Introduction to CHERI technology - Cybersecurity
Introduction to CHERI technology - CybersecurityIntroduction to CHERI technology - Cybersecurity
Introduction to CHERI technology - Cybersecurity
mikeeftimakis1
 
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
Neo4j
 

Recently uploaded (20)

Mind map of terminologies used in context of Generative AI
Mind map of terminologies used in context of Generative AIMind map of terminologies used in context of Generative AI
Mind map of terminologies used in context of Generative AI
 
Video Streaming: Then, Now, and in the Future
Video Streaming: Then, Now, and in the FutureVideo Streaming: Then, Now, and in the Future
Video Streaming: Then, Now, and in the Future
 
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex ProofszkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
 
RESUME BUILDER APPLICATION Project for students
RESUME BUILDER APPLICATION Project for studentsRESUME BUILDER APPLICATION Project for students
RESUME BUILDER APPLICATION Project for students
 
National Security Agency - NSA mobile device best practices
National Security Agency - NSA mobile device best practicesNational Security Agency - NSA mobile device best practices
National Security Agency - NSA mobile device best practices
 
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdfObservability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
 
GridMate - End to end testing is a critical piece to ensure quality and avoid...
GridMate - End to end testing is a critical piece to ensure quality and avoid...GridMate - End to end testing is a critical piece to ensure quality and avoid...
GridMate - End to end testing is a critical piece to ensure quality and avoid...
 
Microsoft - Power Platform_G.Aspiotis.pdf
Microsoft - Power Platform_G.Aspiotis.pdfMicrosoft - Power Platform_G.Aspiotis.pdf
Microsoft - Power Platform_G.Aspiotis.pdf
 
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
 
GraphSummit Singapore | The Art of the Possible with Graph - Q2 2024
GraphSummit Singapore | The Art of the  Possible with Graph - Q2 2024GraphSummit Singapore | The Art of the  Possible with Graph - Q2 2024
GraphSummit Singapore | The Art of the Possible with Graph - Q2 2024
 
Pushing the limits of ePRTC: 100ns holdover for 100 days
Pushing the limits of ePRTC: 100ns holdover for 100 daysPushing the limits of ePRTC: 100ns holdover for 100 days
Pushing the limits of ePRTC: 100ns holdover for 100 days
 
PCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase TeamPCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase Team
 
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
 
Artificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopmentArtificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopment
 
UiPath Test Automation using UiPath Test Suite series, part 6
UiPath Test Automation using UiPath Test Suite series, part 6UiPath Test Automation using UiPath Test Suite series, part 6
UiPath Test Automation using UiPath Test Suite series, part 6
 
20240607 QFM018 Elixir Reading List May 2024
20240607 QFM018 Elixir Reading List May 202420240607 QFM018 Elixir Reading List May 2024
20240607 QFM018 Elixir Reading List May 2024
 
The Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and SalesThe Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and Sales
 
Introduction to CHERI technology - Cybersecurity
Introduction to CHERI technology - CybersecurityIntroduction to CHERI technology - Cybersecurity
Introduction to CHERI technology - Cybersecurity
 
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
 

Vectors are the new JSON in PostgreSQL

  • 1. © 2023, Amazon Web Services, Inc. or its affiliates. © 2023, Amazon Web Services, Inc. or its affiliates. Jonathan Katz Principal Product Manager – Technical Amazon RDS Open Source Vectors are the new JSON or "Going beyond the Page"
  • 2. © 2023, Amazon Web Services, Inc. or its affiliates. © 2023, Amazon Web Services, Inc. or its affiliates. Vectors are the new JSON 2
  • 3. © 2023, Amazon Web Services, Inc. or its affiliates.
  • 4. © 2023, Amazon Web Services, Inc. or its affiliates. Magnitude
  • 5. © 2023, Amazon Web Services, Inc. or its affiliates. Direction
  • 6. © 2023, Amazon Web Services, Inc. or its affiliates. Why use vectors? • Math • Physics • Maps • Artificial intelligence / machine learning 6
  • 7. © 2023, Amazon Web Services, Inc. or its affiliates. 7
  • 8. © 2023, Amazon Web Services, Inc. or its affiliates. 8 0.003049829158165096,0.18639789248165428,0.25620939279058064,0.8474032584483915,0.728909751352397,0.5150510395040762,0.4462516533698704,0.5236709561811317,0.23075271031726885,0.2372686347975339,0.9375801900227572,0.9064239595 240302,0.4651187831953436,0.26254337449177356,0.8550190813318466,0.9841195123557434,0.8949629761265854,0.3042150462800528,0.057239707391303796,0.10891993000094757,0.6202587844948866,0.7137745836868454,0.06048318180182832,0.72 75440976627969,0.9478888345354122,0.8075292635669378,0.006104610242815056,0.723315680514812,0.8404533531441913,0.25125447598935935,0.7878795080344219,0.2611767393761504,0.7249823457880282,0.5664013738334184,0.6664423050495287 ,0.047870779146162334,0.6024105618756934,0.28159282587919066,0.2603034349390896,0.2542046099573376,0.3327296553204988,0.2429052644111387,0.06034160939414335,0.0704690858202035,0.07525846779974898,0.5113090488711158,0.17784307 958376644,0.008055114879436331,0.7253841358982029,0.5892576733958386,0.031036548480514625,0.8514886217774027,0.5359628134105705,0.23253434065398793,0.9932524820134176,0.290096698529549,0.061493269072208534,0.19796591975942945 ,0.5745454363733558,0.10500231825551154,0.8749785303875726,0.16050691467961897,0.6607092358366629,0.6959470185805223,0.8304841585326201,0.9906126039820897,0.37756396267006664,0.24750520102363893,0.7688257200202528,0.229018785 4669945,0.7383023205335917,0.9526504517225298,0.6702366304370244,0.12340838272000454,0.837277567807817,0.13355887990899973,0.16756984658473328,0.020480357387445025,0.7102474499378957,0.47830720614514277,0.7584869382921582,0.3 3627673352437526,0.33973495270900855,0.8041895249569642,0.8477249425000863,0.1840268911963996,0.6614288138464417,0.0733066286605144,0.1540691524669242,0.027117438127323368,0.8556511309682406,0.8365708233650331,0.9148876865925 715,0.27809873307734634,0.9847176522094117,0.8341376068583024,0.4884153769148796,0.49402832531031393,0.9759849942839054,0.3024687238313639,0.3054492792959067,0.9631850034636251,0.6306196638541337,0.25281927918295466,0.9633999 981843218,0.8556476268707236,0.35436292433753636,0.9181200874584725,0.5330211011157004,0.3659282554036771,0.5191548141957298,0.9933155783239833,0.6985272342940974,0.13341211270217812,0.14939654682403614,0.6996626768527356,0.1 5274920318616836,0.7375454247353765,0.12547466888770487,0.020867445809852114,0.08862531355325842,0.8594089835042844,0.467169285835908,0.3259292275603194,0.6754817412472605,0.23752820683506926,0.9235739428656018,0.600996868196 102,0.9826246759026915,0.3596323121373821,0.9926429393046163,0.45436365848015825,0.9537925268703233,0.7878438072069436,0.32655451673684865,0.18200719773833995,0.17466165185684446,0.5548376371379398,0.968462058702201,0.4360127 9039461005,0.3831529322604226,0.463364825678358,0.9972517349699217,0.3281245329407163,0.9106631366236755,0.7198211244102204,0.4306104787062708,0.23199225425841163,0.6140834474634502,0.811014846466751,0.91963436283595,0.679995 246870515,0.8567318394809504,0.14683252560984172,0.14260090503150025,0.8465205833865603,0.8549052513061426,0.8231241188837579,0.41924114155588654,0.38507506362948263,0.25006575098701234,0.0699639742348559,0.9833550311307562,0 .2605607961817462,0.259751219897133,0.02974752594215957,0.4000184436063705,0.56251539587252,0.7588095331041487,0.5247394729399737,0.6386582169689774,0.6753040885419601,0.34278485901716493,0.32020485063128845,0.425275092637406 26,0.14547296876436278,0.9141495998126814,0.040762738089558326,0.32204932557293375,0.8561755675889025,0.83711470922659,0.6558611621265165,0.9120719749549835,0.8783390682648751,0.8461287182939046,0.19516388006501373,0.90823287 55599889,0.5057372708578178,0.9256808350182766,0.7941729566984499,0.6312156320217639,0.3372050641335811,0.45407002325999457,0.0907182103421924,0.300577230348992,0.8878090275893804,0.3114290718440529,0.5082835005874564,0.90912 65859289592,0.5889511705440604,0.0731643995090181,0.7648932788544478,0.07398910725642338,0.37532303126425504,0.16537776734281096,0.5569586346091491,0.41320471229252576,0.5076657196988315,0.16068925028316272,0.3847130576569562 ,0.43543125218091916,0.20087330502095924,0.5937208155983953,0.8364121127564523,0.1689155375268001,0.826672536335348,0.5184907315083152,0.8372109994079331,0.3265766880792995,0.4516165540976509,0.8988998457554018,0.728577359563 8751,0.5046728999487016,0.7202643135137343,0.09277559449311212,0.9863765116823693,0.05656950793722615,0.26912621193846675,0.574617488821012,0.6496403434996161,0.9496949766656257,0.08131020257688348,0.447922842165589,0.4348822 0063391125,0.1975887454376135,0.28999679910503673,0.6710527089809872,0.1981560761511254,0.7203622407001546,0.6892261426735438,0.5979394664255508,0.10251205002051123,0.601888419029919,0.5944410266337989,0.8940782482579479,0.10 38290594697493,0.32220747530470817,0.14736676773501856,0.9973485966907916,0.3130935141094717,0.30621340760343685,0.8178173879797406,0.5610692958400634,0.386045815840081,0.967519534919262,0.8097180412961045,0.14271245221528517 ,0.3678693154775097,0.7779673784677215,0.6239712961871895,0.3259315559082765,0.7455054482396442,0.962644104725257,0.9138400820508927,0.4166565532574751,0.775627551221465,0.4272355508432639,0.43946813542828167,0.40726595029018 85,0.23280199025453285,0.9544162732488246,0.7903299555340588,0.518175708676786,0.40854152359527873,0.559741640565548,0.20424190854972935,0.9061262547687292,0.6645701182166341,0.9417612949664544,0.3286445198182655,0.0661663600 3648324,0.8575535235888658,0.9780448942056097,0.906878474768515,0.6836150303737369,0.09081361022805723,0.2563514823662274,0.8449437256183039,0.7375439247910052,0.17226960846450723,0.251759683310226,0.8416976841571362,0.183602 27348457414,0.8562937493383949,0.2953087294177408,0.11968508369259823,0.6069678436358927,0.9877152267663867,0.27230669196485735,0.8499940280590259,0.5321402710719028,0.4443626806404417,0.6492937309038496,0.6510203249326985,0. 19211109959844208,0.763934356818897,0.08368129338246888,0.28924073707477405,0.22268720990674495,0.3433845445499948,0.4109245245673492,0.1046155910313864,0.07657503894720463,0.49429763722934084,0.13795127372135596,0.1117575707 5977444,0.7050411510649539,0.6338950210353609,0.8713185455257246,0.5313368061200201,0.8819643864984599,0.7745177804106511,0.0626726238350983,0.22828785567392273,0.23592504355521982,0.8589077320621961,0.516653944907091,0.17131 219226574146,0.7913014103977858,0.5667533726397558,0.7471386821577681,0.28212564092399006,0.420452513398736,0.010283762019302145,0.22199748716045065,0.5662042042191722,0.7878722539548519,0.3418149766672123,0.05535447442751717 5,0.06587915283929746,0.9762432269886503,0.14083836839100528,0.8062479029933911,0.2610934713032229,0.26676251460956024,0.5373702653937364,0.7558546584516677,0.07565204292131611,0.3857456900574263,0.19486676744174147,0.6598951 373903503,0.5931976468336408,0.7007532126076583,0.431177727629251,0.32196004461643213,0.11636923570781832,0.26736440608024026,0.13902869217847424,0.9863974946645726,0.9367183779619204,0.5979123544639506,0.5957612994500785,0.1 007942253443872,0.4471694956922043,0.49227738044253755,0.3710392323565692,0.3083302449968812,0.30142992133120217,0.07513135879123212,0.0745710871699039,0.9753584092028262,0.6872321449386298,0.3013690191998748,0.68537127879475 08,0.2810608194143924,0.36719324243578555,0.9900196745730696,0.2995581604401316,0.05118911786611591,0.5901006755335594,0.9354925337581719,0.7831827067647659,0.5295572826622958,0.877399749074879,0.7229849844585559,0.5562242064 95262,0.08759996663518166,0.8385113135143705,0.5823150253024991,0.42793924572137954,0.17803833592182627,0.8114191217912143,0.3819904481571612,0.4945896490589128,0.3632353117172471,0.21192990341563345,0.7642874853025248,0.8687 117951383279,0.9775246638275519,0.9094460166851484,0.41439450351180795,0.7831566479261092,0.4166401099689523,0.8354457950736922,0.6448210109227475,0.07988475871585266,0.4529530027371038,0.9327107284948788,0.3534428053282923,0 .5078262077374696,0.6347768993059759,0.7313667268301707,0.11353959666563895,0.6990197817254433,0.28936586970647227,0.5078392143333978,0.7013959445391791,0.32886143696090997,0.9758973704822864,0.56380401177503,0.92651892607582 2,0.2838770887574107,0.25579145412399384,0.5262181909728092,0.756940652780294,0.7263718105964934,0.20790256344214697,0.29173264616980177,0.6237096498334083,0.6551044316369179,0.32577973645615543,0.8475413310666333,0.531446259 9579386,0.8884261026200484,0.9193022839479994,0.4274562716916215,0.4232826990646217,0.6428614697740933,0.29516246105833943,0.49128289620072607,0.766792234884953,0.9257844666811827,0.217110898687352,0.7351022356386885,0.801423 2451978316,0.5136552177138505,0.1204561525036354,0.5906654571634355,0.4669067015637509,0.13337295607131594,0.4644932295617963,0.49771730573777617,0.006138980193121313,0.7179200071510401,0.4054289273828431,0.13075866432562222, 0.285819886194453,0.9610065864773567,0.6307008303612776,0.9317299086944182,0.32493745347351677,0.36938322317655903,0.9487034160287919,0.8956663435211674,0.576950512486242,0.2044998575366499,0.8268154915267445,0.93399007412639 53,0.5287662643860003,0.04401588702004133,0.031869671118101905,0.10932950531859476,0.9015072253500662,0.6831864617088179,0.3830433812043026,0.10929357802114836,0.5483989715204345,0.06937497005475635,0.17543350260351076,0.9702 931680744307,0.31830118555081555,0.33100272148012166,0.3867797932939965,0.9452420923577414,0.10448864271452152,0.4644021363303388,0.41902724092989274,0.6528552076589271,0.8329300403970947,0.19567210841596605,0.945391035696346 2,0.07648646003400117,0.7088000320729222,0.08525142339897585,0.7926614929870937,0.37533575924477347,0.9712075380467198,0.314161010077175,0.5636365544597624,0.8118455267394573,0.18167043282866047,0.33447618370067644,0.53739801 77527073,0.8207760090494212,0.5598771155060618,0.812458723315661,0.9328809520319652,0.48548827391470795,0.589538317374938,0.9989134212732473,0.8066754110779186,0.5361955264216469,0.44706185290136347,0.8638674649651144,0.11772 212031853257,0.7373123094378364,0.2964179382954839,0.3958614710526014,0.033620851569537535,0.9336075991629791,0.07556724910015333,0.3323710034423364,0.5953882717517018,0.5278470851785038,0.6444871267215646,0.02765478052902281 5,0.8850327220213501,0.16931234747461232,0.5340673362608825,0.02628332727484306,0.8542332140725506,0.5494555230603417,0.6314945868437789,0.3714973660250145,0.7393204833479103,0.48755770442043556,0.9543687133889094,0.492261579 0703624,0.28988577702968144,0.7083030437722719,0.8364820479067632,0.26442432836035223,0.923539740473899,0.5804786632967982,0.8973611414769564,0.19090029594385172,0.9510858616975355,0.5205083047693755,0.7603556975149317,0.5825 186251699712,0.5237620021321732,0.1382955047996397,0.6759274053081654,0.7125068099176595,0.28196614561746003,0.5910852667039386,0.6941303825773772,0.5590181096403093,0.44337019902363295,0.0420720293796073,0.39999920949987455, 0.4152904743104564,0.3835150394646547,0.8257315199272988,0.20520912672005664,0.13770565792973244,0.525472587292029,0.5859051326757871,0.8971099388662438,0.49808119463056144,0.47418305344412204,0.6632131152031171,0.34084957549 33867,0.2159830200386672,0.9784792267668365,0.7062373744186736,0.5612091756778526,0.055825554989286985,0.16807129411874655,0.41004145527270097,0.688008043203375,0.4962868413950652,0.04798678592732131,0.44305450369300203,0.613 1679288963952,0.1084916435499288,0.9088673748726279,0.7093331164130028,0.5000408976944115,0.9350131149208245,0.8634689880409212,0.7610502159510695,0.2183175929625989,0.9426464930280254,0.398670585712793,0.2821887816279194,0.2 0328208191184416,0.4548741358447934,0.6548715754290697,0.4184107296671691,0.3995297162154898,0.35985286475851197,0.14307473061241183,0.3426227796135173,0.7303046335724659,0.6696198440279808,0.0820622313135857,0.78669208302376 25,0.7087577215211311,0.5871649173453939,0.29735360309864234,0.5060200361378087,0.291713126771036,0.8593132510665988,0.2491874611967546,0.3973333635200156,0.17562578418895924,0.6723851134095646,0.8433206332882293,0.5862925569 757031,0.39460302185096197,0.3298574619385626,0.08633999822822602,0.5186693958933226,0.13856413475384244,0.16037753045039338,0.7524108020739817,0.4083528740397604,0.14336197236726633,0.5922296134590717,0.17254185951185264,0.2 5187672624444346,0.18215411670198733,0.726615554336707,0.19775948066525473,0.6502171988473684,0.11727720046996382,0.504884864310899,0.7468997428055957,0.47510705275687926,0.5537603917188179,0.23027474644279167,0.0665294161855 5985,0.7729963399649726,0.4094521145359735,0.6370513839150114,0.6088910155676217,0.4621325659011113,0.11319174753695194,0.341564487945039,0.9934636465304294,0.297227753569981,0.7328244053776913,0.6311450999071475,0.8440901108 017158,0.15514797351432819,0.08104602596240085,0.49662481729486174,0.8876186901886598,0.04044740877096942,0.8516169198563475,0.26929077648597755,0.8282467066551362,0.8809442986462663,0.5945587511571162,0.4381976893835038,0.45 645891923005877,0.4435954618268134,0.9803416732282741,0.28194380839847,0.7604786292220354,0.7654898505617886,0.3541891007560096,0.011414697414370067,0.5449695861628214,0.7827950459053703,0.2075164240522085,0.6758649278280906, 0.0554439805055722,0.22402408179082656,0.44984092489657,0.20142611099850072,0.2021725378636603,0.8882387955223372,0.4475422979857555,0.5042078339514582,0.2847085559918412,0.6820903566163103,0.7925305807392036,0.62322889648881 49,0.2634052122838142,0.9733630373009099,0.9017300092991363,0.5532375674290826,0.9991261787887424,0.11750396889071268,0.44547741255642137,0.8039341980687489,0.8939500761340611,0.3151848911928674,0.5182512914343462,0.378205264 5958096,0.6869011397829183,0.10407205957183052,0.5480067699689997,0.6338475706109143,0.9780782242518598,0.8206228388017074,0.4808312104378487,0.485162738616598,0.32610349576788167,0.7849523968684302,0.4563195194072378,0.30511 80678214003,0.4572974238537455,0.9638166279484572,0.32728609759492855,0.22600814737325337,0.47575953999646003,0.606858294386381,0.18709606637543885,0.9053451016853451,0.7225714493761046,0.1859076951207861,0.9015509000938309,0 .15081182034774443,0.6162413221106817,0.7058872551659015,0.2430669685977378,0.5884148017294031,0.9475041161074529,0.6114365999460425,0.9766288110478101,0.14447912926772588,0.497530656902228,0.551571242000545,0.424096282623402 5,0.9059704151167303,0.8129579833153429,0.8544592783288429,0.050935102703213886,0.6640650997798936,0.5830346238565767,0.8278167869285475,0.28298784896973217,0.450304101090115,0.41830426007102517,0.7626792333938361,0.516796149 1617277,0.7885632739167967,0.2869811219339624,0.5577234652871645,0.4721387833806787,0.43309028577887787,0.3004770094749887,0.17933809587426808,0.12740368744490382,0.5947491456227318,0.595024606540278,0.1638395722206205,0.3453 285042793155,0.20426355588516643,0.38923130948650453,0.19030229808697285,0.44731342822910136,0.5806663041043443,0.8305436981410423,0.49623415203229726
  • 9. © 2023, Amazon Web Services, Inc. or its affiliates. Dimensionality • Machine learning algorithms create vector embeddings of "many dimensionalities" § 256 § 384 § 768 § 1536 § 2048 § 60K+ • Dimensionality keeps information about a particular attribute 9
  • 10. © 2023, Amazon Web Services, Inc. or its affiliates. Searching vector embeddings • Vector normalization § Magnitude of 1 • Distance function § Euclidean distance (L2) § Cosine distance (cosine similarity) § Inner product § Taxicab / Manhattan (L1) § Chebyshev (L-inf) 10
  • 11. © 2023, Amazon Web Services, Inc. or its affiliates. K-nearest neighbor SELECT * FROM table ORDER BY $VECTOR <-> embedding -- distance LIMIT 5; -- k 11
  • 12. © 2023, Amazon Web Services, Inc. or its affiliates. 12 100,000
  • 13. © 2023, Amazon Web Services, Inc. or its affiliates. 13 1,000,000
  • 14. © 2023, Amazon Web Services, Inc. or its affiliates. 14 100,000,000
  • 15. © 2023, Amazon Web Services, Inc. or its affiliates. 15 1,000,000,000
  • 16. © 2023, Amazon Web Services, Inc. or its affiliates. Vector indexing methods • ~20 years of modern research searching high dimensionality vectors § FAISS – open-source library of vector search algorithms § Leverage CPU/GPU acceleration • "Approximate nearest neighbor" (ANN) § Tradeoff on performance / recall • IVF FLAT (inverted indexes) • HNSW (Hierarchical inverted small worlds) 16
  • 17. © 2023, Amazon Web Services, Inc. or its affiliates. pgvector • Open source extension that provides vector data type, distance operations, and indexing • IVF FLAT index • Can adjust performance / recall tradeoff through "probes" • Connectors to interface with many programming languages 17
  • 18. © 2023, Amazon Web Services, Inc. or its affiliates. Quick recap on vectors in machine learning • Vectors encode information about objects (text, images, videos) • Vectors can have high dimensionality • "Similarity search" is a popular operation • Data sets can become very large • Indexing techniques that can accelerate search at cost of "recall" 18
  • 19. © 2023, Amazon Web Services, Inc. or its affiliates. © 2023, Amazon Web Services, Inc. or its affiliates. Going beyond the page 19
  • 20. © 2023, Amazon Web Services, Inc. or its affiliates. How big is a PostgreSQL page? 20 8192* 8192 – sizeof(page header)
  • 21. © 2023, Amazon Web Services, Inc. or its affiliates. How big is a 1536 dimensional vector? 21 1536 * 4 + 8 = 6152
  • 22. © 2023, Amazon Web Services, Inc. or its affiliates. How big is a 2048 dimensional vector? 22 2048 * 4 + 8 = 8200 X
  • 23. © 2023, Amazon Web Services, Inc. or its affiliates. 23 But we can TOAST!
  • 24. © 2023, Amazon Web Services, Inc. or its affiliates. 24 But we can TOAST (an index)! X
  • 25. © 2023, Amazon Web Services, Inc. or its affiliates. What does this mean? • PostgreSQL can only index vectors up to a certain dimensionality without reduction • Query plan costing becomes something developers need to worry about § Cost of a sequential scan on a toasted column vs. index page 25
  • 26. © 2023, Amazon Web Services, Inc. or its affiliates. What can we do? • Native support for vector operations in PostgreSQL – Functions / data types • Mechanisms for managing vector data that goes beyond the page • Performance: Indexing methods. Query plan costing. Parallelism (builds and queries) • Build on CPU acceleration work. § GPU acceleration – extension? • Contribute to extensions (e.g. pgvector) / vice versa 26
  • 27. © 2023, Amazon Web Services, Inc. or its affiliates. © 2023, Amazon Web Services, Inc. or its affiliates. Thank you! 27