{"id":"https://openalex.org/W4406457809","doi":"https://doi.org/10.1109/bigdata62323.2024.10825992","title":"A Deep Dive into Vector Stores: Classifying the Backbone of Retrieval-Augmented Generation","display_name":"A Deep Dive into Vector Stores: Classifying the Backbone of Retrieval-Augmented Generation","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406457809","doi":"https://doi.org/10.1109/bigdata62323.2024.10825992"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825992","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073268399","display_name":"Richard Shan","orcid":"https://orcid.org/0009-0000-7864-9270"},"institutions":[{"id":"https://openalex.org/I4210152011","display_name":"North Carolina School of Science and Mathematics","ror":"https://ror.org/03zbydc22","country_code":"US","type":"education","lineage":["https://openalex.org/I4210152011"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Richard Shan","raw_affiliation_strings":["North Carolina School of Science and Mathematics,Department of Data Science,Durham,NC,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina School of Science and Mathematics,Department of Data Science,Durham,NC,USA","institution_ids":["https://openalex.org/I4210152011"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5073268399"],"corresponding_institution_ids":["https://openalex.org/I4210152011"],"apc_list":null,"apc_paid":null,"fwci":1.2976,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8234227,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8831","last_page":"8833"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9939000010490417,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9929999709129333,"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/computer-science","display_name":"Computer science","score":0.7480360269546509},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4859515428543091},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4655841886997223}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7480360269546509},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4859515428543091},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4655841886997223}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825992","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W3174809957","https://openalex.org/W4391856025","https://openalex.org/W4392945187"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Vector":[0],"stores":[1,35],"represent":[2],"a":[3,29],"crucial":[4],"building":[5],"block":[6],"for":[7,22,93],"Retrieval-Augmented":[8],"Generation":[9],"(RAG),":[10],"efficiently":[11],"storing":[12],"and":[13,20,43,47,51,54,65,79,96,126],"retrieving":[14],"high-dimensional":[15],"embeddings":[16],"to":[17,104],"ensure":[18],"relevance":[19],"accuracy":[21],"generative":[23],"AI":[24],"applications.":[25],"This":[26],"paper":[27],"introduces":[28],"classification":[30],"scheme":[31],"that":[32],"categorizes":[33],"vector":[34,71,110],"into":[36],"four":[37],"main":[38],"classes":[39],"of":[40,68,108,115],"systems:":[41],"lightweight":[42],"local":[44],"solutions,":[45],"open-source":[46],"distributed":[48],"platforms,":[49],"cloud-native":[50],"commercial":[52],"services,":[53],"semantic/contextual":[55],"search-oriented":[56],"systems.":[57],"We":[58],"discuss":[59],"the":[60,84,106,109,113],"architectures,":[61],"capabilities,":[62],"strengths,":[63],"weaknesses,":[64],"use":[66],"cases":[67],"one":[69],"representative":[70],"database":[72],"in":[73],"each":[74],"category:":[75],"FAISS,":[76],"Milvus,":[77],"Pinecone,":[78],"Weaviate.":[80],"Practical":[81],"guidelines":[82],"on":[83,89,98],"implementation":[85],"are":[86,120],"presented,":[87],"focused":[88],"optimization":[90],"techniques,":[91],"strategies":[92],"data":[94],"management,":[95],"considerations":[97],"security.":[99],"Comparative":[100],"insights":[101],"enable":[102],"practitioners":[103],"align":[105],"selection":[107],"store":[111],"with":[112],"workflow":[114],"RAG":[116],"solutions.":[117],"Future":[118],"trends":[119],"explored,":[121],"such":[122],"as":[123],"hybrid":[124],"search":[125],"explainability.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-06-18T10:00:31.954636","created_date":"2025-10-10T00:00:00"}