{"id":"https://openalex.org/W7203673516","doi":"https://doi.org/10.48550/arxiv.2608.15994","title":"Building An Integrated Vector Database System in PostgreSQL","display_name":"Building An Integrated Vector Database System in PostgreSQL","publication_year":2026,"publication_date":"2026-08-17","ids":{"openalex":"https://openalex.org/W7203673516","doi":"https://doi.org/10.48550/arxiv.2608.15994"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.15994","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.15994","pdf_url":"https://arxiv.org/pdf/2608.15994","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.15994","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147409191","display_name":"Jiayi Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu, Jiayi","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101189420","display_name":"Te Guo","orcid":"https://orcid.org/0009-0002-5626-1501","observed_orcids":["https://orcid.org/0009-0002-5626-1501"]},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guo, Te","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5147394566","display_name":"Jianguo Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Jianguo","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9545999765396118,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9545999765396118,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.03720000013709068,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0006000000284984708,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/vector-databases","display_name":"vector databases","score":0.6779999732971191},{"id":"https://openalex.org/keywords/postgresql","display_name":"PostgreSQL","score":0.546999990940094},{"id":"https://openalex.org/keywords/vector-search","display_name":"vector search","score":0.8669999837875366},{"id":"https://openalex.org/keywords/vector-index","display_name":"vector index","score":0.7099999785423279},{"id":"https://openalex.org/keywords/pgvector","display_name":"pgvector","score":0.5260000228881836},{"id":"https://openalex.org/keywords/crash-recovery","display_name":"crash recovery","score":0.9909999966621399}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7439000010490417},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6850000023841858},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.6669999957084656},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6136000156402588},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.5062000155448914},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.4648999869823456},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4510999917984009},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44029998779296875},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.4203000068664551},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4154999852180481},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4081000089645386},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.4018999934196472},{"id":"https://openalex.org/C84511453","wikidata":"https://www.wikidata.org/wiki/Q2914952","display_name":"Concurrency control","level":3,"score":0.35530000925064087},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C92087593","wikidata":"https://www.wikidata.org/wiki/Q427389","display_name":"Vector (molecular biology)","level":4,"score":0.3140999972820282},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C2779599972","wikidata":"https://www.wikidata.org/wiki/Q82231","display_name":"NoSQL","level":3,"score":0.2874000072479248},{"id":"https://openalex.org/C161824985","wikidata":"https://www.wikidata.org/wiki/Q919509","display_name":"Vector processor","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.27559998631477356},{"id":"https://openalex.org/C150495011","wikidata":"https://www.wikidata.org/wiki/Q128392","display_name":"Concurrent computing","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C59276292","wikidata":"https://www.wikidata.org/wiki/Q580427","display_name":"Database index","level":3,"score":0.27079999446868896},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2637999951839447},{"id":"https://openalex.org/C107535962","wikidata":"https://www.wikidata.org/wiki/Q2459880","display_name":"Database tuning","level":4,"score":0.26330000162124634},{"id":"https://openalex.org/C24394798","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database management system","level":3,"score":0.259799987077713},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.15994","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.15994","pdf_url":"https://arxiv.org/pdf/2608.15994","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.15994","doi":"https://doi.org/10.48550/arxiv.2608.15994","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.15994","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.15994","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.15994","pdf_url":"https://arxiv.org/pdf/2608.15994","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203673516.pdf","grobid_xml":"https://content.openalex.org/works/W7203673516.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4400910146","https://openalex.org/W4404181049","https://openalex.org/W7160150469","https://openalex.org/W4414267113","https://openalex.org/W7162412425","https://openalex.org/W4413417017","https://openalex.org/W7212525462","https://openalex.org/W7223560955","https://openalex.org/W4400641571","https://openalex.org/W7161709845"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"PostgreSQL-V":[3,49,84,116,123,145,152,169,174,200],"2.0,":[4,117],"a":[5,35,97,202],"scalable":[6],"integrated":[7],"vector":[8,15,22,41,57,65,73,130,208],"database":[9,209],"system":[10],"inside":[11,210],"PostgreSQL.":[12,211],"Existing":[13],"PostgreSQL-based":[14],"search":[16,66],"systems":[17],"such":[18],"as":[19],"pgvector":[20],"embed":[21],"indexes":[23],"into":[24,172],"PostgreSQL's":[25,61,135],"page-oriented":[26],"storage":[27,62],"engine,":[28,63],"incurring":[29],"significant":[30],"overhead":[31],"that":[32,70,83,89],"leads":[33],"to":[34,69,140,182],"huge":[36],"performance":[37,67],"gap":[38],"with":[39,105],"specialized":[40],"databases.":[42],"In":[43],"our":[44],"earlier":[45],"work,":[46],"we":[47,81],"introduced":[48],"1.0,":[50],"which":[51,118],"addresses":[52],"this":[53],"issue":[54],"by":[55],"separating":[56],"index":[58,74,106,162,187],"structures":[59],"from":[60],"enabling":[64],"close":[68],"of":[71,144,160],"native":[72],"libraries":[75],"while":[76,147,168],"preserving":[77,186],"SQL":[78],"compatibility.":[79],"However,":[80],"find":[82],"1.0":[85,146],"has":[86],"three":[87,121],"limitations":[88],"matter":[90],"for":[91],"real-world":[92],"workloads:":[93],"it":[94],"only":[95],"supports":[96],"single":[98],"connection":[99],"(without":[100],"concurrency),":[101],"recovery":[102,156],"time":[103],"grows":[104,171],"size,":[107,163],"and":[108,132,206],"physical":[109,176,180],"replication":[110,177,181],"is":[111],"unsupported.":[112],"We":[113],"further":[114],"present":[115],"closes":[119],"all":[120],"gaps.":[122],"2.0's":[124,153,175],"concurrency":[125],"support":[126,178],"enables":[127],"fully":[128,203],"concurrent":[129,150],"searches":[131],"updates":[133],"across":[134],"multi-process":[136],"backends,":[137],"delivering":[138],"up":[139],"36.4x":[141],"the":[142,183,193],"throughput":[143],"serving":[148],"32":[149],"clients.":[151],"fast":[154],"crash":[155],"keeps":[157],"cost":[158],"independent":[159],"total":[161],"remaining":[164],"near":[165],"20":[166],"ms":[167],"1.0's":[170],"seconds-scale.":[173],"extends":[179],"decoupled":[184],"index,":[185],"consistency":[188],"on":[189],"standbys":[190],"without":[191],"burdening":[192],"primary":[194],"node.":[195],"Together,":[196],"these":[197],"advances":[198],"make":[199],"2.0":[201],"concurrent,":[204],"crash-resilient,":[205],"replication-ready":[207]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-19T00:00:00"}