MétaCan
Menu
Back to cohort
Record W4392384312 · doi:10.1145/3616855.3635691

Vector Search with OpenAI Embeddings: Lucene Is All You Need

2024· article· en· W4392384312 on OpenAlexafffund
Jasper Xian, Tommaso Teofili, Ronak Pradeep, Jimmy Lin

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicAdvanced Text Analysis Techniques
Canadian institutionsUniversity of Waterloo
FundersNatural Sciences and Engineering Research Council of CanadaUniversitas Brawijaya
KeywordsComputer scienceRanking (information retrieval)EncoderInformation retrievalArchitectureArtificial intelligenceData miningGeographyOperating system

Abstract

fetched live from OpenAlex

We provide a reproducible, end-to-end demonstration of vector search with OpenAI embeddings using Lucene on the popular MS MARCO passage ranking test collection. The main goal of our work is to challenge the prevailing narrative that a dedicated vector store is necessary to take advantage of recent advances in deep neural networks as applied to search. Quite the contrary, we show that hierarchical navigable small-world network (HNSW) indexes in Lucene are adequate to provide vector search capabilities in a standard bi-encoder architecture. This suggests that, from a simple cost-benefit analysis, there does not appear to be a compelling reason to introduce a dedicated vector store into a modern "AI stack" for search, since such applications have already received substantial investments in existing, widely deployed infrastructure.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.013
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: Not applicable
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.040
Threshold uncertainty score0.134

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.013
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.002
Science and technology studies0.0010.001
Scholarly communication0.0030.010
Open science0.0030.004
Research integrity0.0020.003
Insufficient payload (model declined to judge)0.0400.032

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.019
GPT teacher head0.315
Teacher spread0.296 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designNot applicable
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations30
Published2024
Admission routes2
Has abstractyes

Explore more

Same topicAdvanced Text Analysis TechniquesFrench-language works237,207