{"id":"https://openalex.org/W4412376877","doi":"https://doi.org/10.1145/3726302.3730150","title":"Constructing and Evaluating Declarative RAG Pipelines in PyTerrier","display_name":"Constructing and Evaluating Declarative RAG Pipelines in PyTerrier","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412376877","doi":"https://doi.org/10.1145/3726302.3730150"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3730150","doi":"https://doi.org/10.1145/3726302.3730150","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730150","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730150","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730150","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057643560","display_name":"Craig Macdonald","orcid":"https://orcid.org/0000-0003-3143-279X","observed_orcids":["https://orcid.org/0000-0003-3143-279X"]},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Craig Macdonald","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-3143-279X","affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083649914","display_name":"Jinyuan Fang","orcid":"https://orcid.org/0000-0002-6886-5882","observed_orcids":["https://orcid.org/0000-0002-6886-5882"]},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jinyuan Fang","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-6886-5882","affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075770550","display_name":"Andrew Parry","orcid":"https://orcid.org/0000-0001-5446-8328","observed_orcids":["https://orcid.org/0000-0001-5446-8328"]},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew Parry","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-5446-8328","affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073342482","display_name":"Zaiqiao Meng","orcid":"https://orcid.org/0000-0001-5374-0318","observed_orcids":["https://orcid.org/0000-0001-5374-0318"]},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zaiqiao Meng","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-5374-0318","affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I7882870"],"apc_list":null,"apc_paid":null,"fwci":6.9969,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.97332801,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4035","last_page":"4040"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9648000001907349,"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"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9648000001907349,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.032600000500679016,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.9950000047683716},{"id":"https://openalex.org/keywords/re-ranking","display_name":"re-ranking","score":0.6600000262260437},{"id":"https://openalex.org/keywords/dense-retrievers","display_name":"dense retrievers","score":0.5669999718666077},{"id":"https://openalex.org/keywords/natural-questions","display_name":"Natural Questions","score":0.6019999980926514},{"id":"https://openalex.org/keywords/indexing-efficiency","display_name":"indexing efficiency","score":0.3580000102519989},{"id":"https://openalex.org/keywords/rag-evaluation","display_name":"RAG evaluation","score":0.4830000102519989}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6536731123924255},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.6305171847343445},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5710397958755493},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.181333988904953},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3726302.3730150","doi":"https://doi.org/10.1145/3726302.3730150","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730150","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730150","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.10802","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.10802","pdf_url":"https://arxiv.org/pdf/2506.10802","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":"pmh:oai:eprints.gla.ac.uk:352731","doi":null,"is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/3545.html>","pdf_url":"https://eprints.gla.ac.uk/352731/2/352731.pdf","source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["doaj"],"host_organization":"https://openalex.org/I4405259220","host_organization_name":"Institut Agama Islam Negeri Langsa","host_organization_lineage":["https://openalex.org/I4405259220"],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceedings"},{"id":"doi:10.48550/arxiv.2506.10802","doi":"https://doi.org/10.48550/arxiv.2506.10802","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.10802","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3726302.3730150","doi":"https://doi.org/10.1145/3726302.3730150","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730150","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730150","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412376877.pdf","grobid_xml":"https://content.openalex.org/works/W4412376877.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W2149427297","https://openalex.org/W2252136820","https://openalex.org/W2593864460","https://openalex.org/W2612431505","https://openalex.org/W2740321901","https://openalex.org/W2789566302","https://openalex.org/W2889787757","https://openalex.org/W2912924812","https://openalex.org/W2962985038","https://openalex.org/W3015883388","https://openalex.org/W3021397474","https://openalex.org/W3039017601","https://openalex.org/W3045745713","https://openalex.org/W3115947671","https://openalex.org/W3154280800","https://openalex.org/W3175980629","https://openalex.org/W3190126809","https://openalex.org/W3208821253","https://openalex.org/W3209981429","https://openalex.org/W4284706395","https://openalex.org/W4310923309","https://openalex.org/W4327644554","https://openalex.org/W4385570777","https://openalex.org/W4385571271","https://openalex.org/W4387430850","https://openalex.org/W4389520103","https://openalex.org/W4389520468","https://openalex.org/W4389984066","https://openalex.org/W4391244683","https://openalex.org/W4391376033","https://openalex.org/W4402671152","https://openalex.org/W4402671840","https://openalex.org/W4405252961","https://openalex.org/W4409167231","https://openalex.org/W4412376925","https://openalex.org/W4415158844"],"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":{"Search":[0],"engines":[1],"often":[2],"follow":[3],"a":[4,40],"pipeline":[5,33],"architecture,":[6,34,67],"where":[7,35],"complex":[8],"but":[9],"effective":[10],"reranking":[11],"components":[12],"are":[13],"used":[14],"to":[15,82,117],"refine":[16],"the":[17,32,36,44,47,64,69,102,120],"results":[18],"of":[19,31,71,104],"an":[20,28],"initial":[21],"retrieval.":[22],"Retrieval":[23],"augmented":[24],"generation":[25],"(RAG)":[26],"is":[27],"exciting":[29],"application":[30],"final":[37],"component":[38],"generates":[39],"coherent":[41],"answer":[42],"for":[43,77],"users":[45],"from":[46],"retrieved":[48],"documents.":[49],"In":[50],"this":[51],"demo":[52],"paper,":[53],"we":[54],"describe":[55],"how":[56,116],"such":[57],"RAG":[58,84,107],"pipelines":[59,108],"can":[60],"be":[61],"formulated":[62],"in":[63],"declarative":[65],"PyTerrier":[66,78,122],"and":[68,86,92,106,115,128,131],"advantages":[70],"doing":[72],"so.":[73],"Our":[74],"PyTerrier-RAG":[75],"extension":[76],"provides":[79],"easy":[80],"access":[81],"standard":[83,110],"datasets":[85,111],"evaluation":[87],"measures,":[88],"state-of-the-art":[89,125],"LLM":[90],"readers,":[91],"using":[93],"PyTerrier's":[94],"unique":[95],"operator":[96],"notation,":[97],"easy-to-build":[98],"pipelines.":[99],"We":[100],"demonstrate":[101],"succinctness":[103],"indexing":[105],"on":[109,119],"(including":[112],"Natural":[113],"Questions)":[114],"build":[118],"larger":[121],"ecosystem":[123],"with":[124],"sparse,":[126],"learned-sparse,":[127],"dense":[129],"retrievers,":[130],"other":[132],"neural":[133],"rankers.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}