{"id":"W4392384312","doi":"10.1145/3616855.3635691","title":"Vector Search with OpenAI Embeddings: Lucene Is All You Need","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Universitas Brawijaya","keywords":"Computer science; Ranking (information retrieval); Encoder; Information retrieval; Architecture; Artificial intelligence; Data mining; Geography; Operating system","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001832191,0.001782067,0.001195783,0.00144761,0.0009846977,0.003388074,0.002780543,0.00191001,0.0399992],"category_scores_gemma":[0.01348245,0.000726535,0.000890805,0.001920071,0.001105419,0.009778759,0.003552376,0.002792018,0.0315145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009559254,"about_ca_system_score_gemma":0.001111516,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009623748,"about_ca_topic_score_gemma":0.02325784,"domain_scores_codex":[0.9976367,0.0005404787,0.000148376,0.00044112,0.0009891038,0.0002441378],"domain_scores_gemma":[0.9961458,0.001332658,0.000116199,0.001494601,0.0007155306,0.0001949901],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001638468,0.0007687,0.003122593,0.001419852,0.0002759467,0.0008080768,0.0006791344,0.02260099,0.02129619,0.02884819,0.4908368,0.427705],"study_design_scores_gemma":[0.0006749767,0.001079033,0.003251785,0.0004109311,0.00009877181,0.0008313289,0.0007548376,0.4781065,0.07069214,0.06556775,0.3781836,0.0003484339],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.06391831,0.003803242,0.3669608,0.004106849,0.00181484,0.0007706538,0.03525756,0.4499768,0.07339091],"genre_scores_gemma":[0.2999482,0.001563133,0.5216472,0.002520954,0.0003193204,0.001245577,0.0892548,0.0303852,0.0531157],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.0399992,"threshold_uncertainty_score":0.1338107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01888909085561529,"score_gpt":0.3146775010715027,"score_spread":0.2957884102158874,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}