{"id":"https://openalex.org/W4411800339","doi":"https://doi.org/10.1109/ccgrid64434.2025.00065","title":"Streamrag: a Lock-Aware and Traffic-Aware Query Coordinator in Stream-Based Rag Systems","display_name":"Streamrag: a Lock-Aware and Traffic-Aware Query Coordinator in Stream-Based Rag Systems","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4411800339","doi":"https://doi.org/10.1109/ccgrid64434.2025.00065"},"language":"en","primary_location":{"id":"doi:10.1109/ccgrid64434.2025.00065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccgrid64434.2025.00065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 25th International Symposium on Cluster, Cloud and Internet Computing (CCGrid)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103182667","display_name":"Yeonwoo Jeong","orcid":"https://orcid.org/0000-0003-4653-115X"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yeonwoo Jeong","raw_affiliation_strings":["Sogang University,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sogang University,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030505483","display_name":"Kyuli Park","orcid":"https://orcid.org/0009-0001-2404-3430"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyuli Park","raw_affiliation_strings":["Sogang University,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sogang University,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101413142","display_name":"Sungyong Park","orcid":"https://orcid.org/0000-0002-0309-1820"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungyong Park","raw_affiliation_strings":["Sogang University,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sogang University,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I148751991"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148751991"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14984028,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"01","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":1.0,"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/T11478","display_name":"Caching and Content Delivery","score":1.0,"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9991999864578247,"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/T12288","display_name":"Optimization and Search Problems","score":0.9977999925613403,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8559706211090088},{"id":"https://openalex.org/keywords/lock","display_name":"Lock (firearm)","score":0.7243353128433228},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.4132842719554901},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3643302023410797},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.32124871015548706}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8559706211090088},{"id":"https://openalex.org/C174839445","wikidata":"https://www.wikidata.org/wiki/Q1134386","display_name":"Lock (firearm)","level":2,"score":0.7243353128433228},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.4132842719554901},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3643302023410797},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.32124871015548706},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ccgrid64434.2025.00065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccgrid64434.2025.00065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 25th International Symposium on Cluster, Cloud and Internet Computing (CCGrid)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2038412523","https://openalex.org/W2105232714","https://openalex.org/W2124509324","https://openalex.org/W2326236514","https://openalex.org/W2542459869","https://openalex.org/W2566979091","https://openalex.org/W2753910905","https://openalex.org/W2896457183","https://openalex.org/W2926234975","https://openalex.org/W2963469388","https://openalex.org/W2963963993","https://openalex.org/W3003257820","https://openalex.org/W3145124555","https://openalex.org/W3174809957","https://openalex.org/W4292779060","https://openalex.org/W4293024115","https://openalex.org/W4312285477","https://openalex.org/W4322718191","https://openalex.org/W4379654636","https://openalex.org/W4387321071","https://openalex.org/W4389609661","https://openalex.org/W4391376033","https://openalex.org/W4400525811","https://openalex.org/W4402733341","https://openalex.org/W4404133408","https://openalex.org/W4404534210","https://openalex.org/W4404767572","https://openalex.org/W4404783698","https://openalex.org/W6731596640","https://openalex.org/W6777399232"],"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/W1554494913"],"abstract_inverted_index":{"Stream-based":[0],"retrieval":[1,14],"augmented":[2],"generation":[3],"(RAG)":[4],"systems":[5,30],"integrate":[6],"stream":[7],"processing":[8],"engines":[9],"(SPEs)":[10],"with":[11],"real-time":[12,142,173],"document":[13],"to":[15,76,114,119],"support":[16],"dynamic":[17],"indexing":[18,70,81],"and":[19,38,47,82,100,122,135,148,154,161,170,192],"search":[20,83],"over":[21],"unstructured":[22],"datasets.":[23],"However,":[24],"efficiently":[25],"executing":[26],"queries":[27],"in":[28,59,72],"these":[29,56,128],"is":[31,41],"challenging,":[32],"as":[33],"seamless":[34],"coordination":[35,138],"between":[36,55,152],"SPEs":[37,65,99,153],"vector":[39,73,91,155],"databases":[40,92],"essential":[42],"for":[43,106],"maintaining":[44],"low":[45],"latency":[46,183],"high":[48],"throughput.":[49],"The":[50],"lack":[51,93],"of":[52,68,144,172],"mutual":[53],"awareness":[54],"components":[57],"results":[58,177],"two":[60],"major":[61],"performance":[62,169,197],"bottlenecks.":[63],"First,":[64],"are":[66],"unaware":[67],"ongoing":[69],"operations":[71,84],"databases,":[74],"leading":[75,118],"metadata":[77,145],"lock":[78,146],"contention":[79],"when":[80],"overlap,":[85],"which":[86],"increases":[87],"query":[88,96,124,137,149,159],"latency.":[89],"Second,":[90],"visibility":[94],"into":[95],"traffic":[97,115,150,200],"from":[98],"rely":[101],"solely":[102],"on":[103],"internal":[104],"metrics":[105,151],"scaling.":[107],"As":[108],"a":[109,133],"result,":[110],"they":[111],"respond":[112],"reactively":[113],"spikes,":[116],"often":[117],"instance":[120,164],"overload":[121],"delayed":[123],"processing.":[125],"To":[126],"address":[127],"issues,":[129],"we":[130],"propose":[131],"StreamRAG,":[132],"lock-aware":[134],"traffic-aware":[136],"mechanism":[139],"that":[140,179],"facilitates":[141],"exchange":[143],"statuses":[147],"databases.":[156],"By":[157],"optimizing":[158],"routing":[160],"enabling":[162],"proactive":[163],"scaling,":[165],"StreamRAG":[166],"enhances":[167],"the":[168,188],"scalability":[171],"RAG":[174],"systems.":[175],"Experimental":[176],"demonstrate":[178],"Streamrag":[180],"reduces":[181],"tail":[182],"by":[184],"up":[185],"to$4":[186],"\\times$at":[187],"99":[189],"th":[190],"percentile":[191],"significantly":[193],"improves":[194],"overall":[195],"system":[196],"under":[198],"varying":[199],"conditions.":[201]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}