{"id":"https://openalex.org/W7162395424","doi":"https://doi.org/10.1016/j.softx.2026.102742","title":"cairnsearch: A privacy-first hybrid search and local RAG system for personal document collections","display_name":"cairnsearch: A privacy-first hybrid search and local RAG system for personal document collections","publication_year":2026,"publication_date":"2026-05-27","ids":{"openalex":"https://openalex.org/W7162395424","doi":"https://doi.org/10.1016/j.softx.2026.102742"},"language":"en","primary_location":{"id":"doi:10.1016/j.softx.2026.102742","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.softx.2026.102742","pdf_url":null,"source":{"id":"https://openalex.org/S2506067282","display_name":"SoftwareX","issn_l":"2352-7110","issn":["2352-7110"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SoftwareX","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1016/j.softx.2026.102742","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Muhammad Waqas","orcid":"https://orcid.org/0009-0000-9794-1461"},"institutions":[{"id":"https://openalex.org/I4210135633","display_name":"Dallas Independent School District","ror":"https://ror.org/03s538y47","country_code":"US","type":"education","lineage":["https://openalex.org/I4210135633"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Muhammad Waqas","raw_affiliation_strings":["Independent Researcher, Dallas Tx, USA"],"raw_orcid":"https://orcid.org/0009-0000-9794-1461","affiliations":[{"raw_affiliation_string":"Independent Researcher, Dallas Tx, USA","institution_ids":["https://openalex.org/I4210135633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210135633"],"apc_list":{"value":500,"currency":"USD","value_usd":500},"apc_paid":{"value":500,"currency":"USD","value_usd":500},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94114318,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"102742","last_page":"102742"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.2549000084400177,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.2549000084400177,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12607","display_name":"Personal Information Management and User Behavior","score":0.2053000032901764,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.1404000073671341,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/information-system","display_name":"Information system","score":0.29789999127388},{"id":"https://openalex.org/keywords/personally-identifiable-information","display_name":"Personally identifiable information","score":0.25859999656677246},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.25110000371932983},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.23649999499320984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7645000219345093},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4207000136375427},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39430001378059387},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26820001006126404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25920000672340393},{"id":"https://openalex.org/C169093310","wikidata":"https://www.wikidata.org/wiki/Q3702971","display_name":"Personally identifiable information","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.25110000371932983},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.23649999499320984},{"id":"https://openalex.org/C2988424471","wikidata":"https://www.wikidata.org/wiki/Q193395","display_name":"Information storage","level":2,"score":0.23409999907016754}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.softx.2026.102742","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.softx.2026.102742","pdf_url":null,"source":{"id":"https://openalex.org/S2506067282","display_name":"SoftwareX","issn_l":"2352-7110","issn":["2352-7110"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SoftwareX","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.softx.2026.102742","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.softx.2026.102742","pdf_url":null,"source":{"id":"https://openalex.org/S2506067282","display_name":"SoftwareX","issn_l":"2352-7110","issn":["2352-7110"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SoftwareX","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"cairnsearch":[0],"is":[1,90,157],"an":[2,61],"open-source":[3],"document":[4],"search":[5,43,113],"and":[6,25,33,44,101,128,142,154],"question-answering":[7],"system":[8],"that":[9],"runs":[10],"entirely":[11],"on":[12],"the":[13,65,83,137,145],"user\u2019s":[14],"machine.":[15],"It":[16],"indexes":[17],"PDFs":[18],"(including":[19],"scanned":[20],"ones":[21],"via":[22],"OCR),":[23],"Word":[24],"Excel":[26],"files,":[27],"CSV,":[28],"plain":[29],"text,":[30],"Markdown,":[31],"HTML,":[32],"images":[34],"into":[35],"a":[36,45,58,72,93,97,102,121,131],"single":[37],"SQLite":[38],"FTS5":[39],"index":[40,48],"for":[41,49],"lexical":[42],"NumPy-backed":[46],"vector":[47],"dense":[50],"retrieval.":[51],"The":[52,86,105],"two":[53],"signals":[54],"are":[55,69,108],"fused":[56],"with":[57,78],"weighted":[59],"sum;":[60],"optional":[62],"cross-encoder":[63],"reranks":[64],"top":[66],"candidates.":[67],"Questions":[68],"answered":[70],"by":[71],"local":[73],"LLM":[74],"served":[75],"through":[76],"Ollama,":[77],"citations":[79],"pointing":[80],"back":[81],"to":[82,112,120],"source":[84],"chunks.":[85],"same":[87],"core":[88],"engine":[89],"exposed":[91],"as":[92],"FastAPI":[94],"web":[95],"service,":[96],"single-page":[98],"browser":[99],"UI,":[100],"Typer":[103],"CLI.":[104],"intended":[106],"users":[107],"people":[109],"who":[110],"need":[111],"or":[114],"query":[115],"documents":[116],"they":[117],"cannot":[118],"send":[119],"cloud":[122],"service:":[123],"lawyers,":[124],"clinicians,":[125],"journalists,":[126],"researchers,":[127],"anyone":[129],"managing":[130],"personal":[132],"archive.":[133],"This":[134],"paper":[135],"describes":[136],"system\u2019s":[138],"architecture,":[139],"its":[140],"ingestion":[141],"retrieval":[143],"pipeline,":[144],"built-in":[146],"safeguards":[147],"(PII":[148],"detection,":[149],"extraction":[150],"guardrails,":[151],"failed-file":[152],"quarantine),":[153],"how":[155],"it":[156],"deployed":[158],"in":[159],"practice.":[160]},"counts_by_year":[],"updated_date":"2026-05-28T06:12:49.907903","created_date":"2026-05-25T00:00:00"}
