The Future of Document Retrieval: Harnessing the Power of OpenAI and AWS Kendra
Bibliographic record
Abstract
In an era inundated with data, the quest for efficient and accurate information retrieval has become paramount for organizations. Traditional enterprise search methodologies, while foundational, grapple with challenges ranging from relevance issues to the complexities of everevolving linguistic nuances. This research delves into a transformative approach to enterprise search by integrating OpenAI's Foundation Model, a state-of-the-art AI model renowned for its profound linguistic understanding, with Amazon Web Services' Kendra, a machine learning-powered search platform. Our integrated system, showcased through a meticulously designed architecture, demonstrates a remarkable$92 \%$accuracy in document retrieval, outshining the$78{{\% }}$achieved by traditional methods. Furthermore, user feedback sessions accentuated the system's adeptness in natural language query processing and the heightened relevance of search results. This paper not only presents the fruits of melding advanced AI with robust search platforms but also paves the way for the future of intelligent enterprise search, emphasizing adaptability, continuous learning, and the promise of a search realm that's not just efficient but profoundly insightful.
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.008 | 0.029 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.006 | 0.005 |
| Science and technology studies | 0.002 | 0.005 |
| Scholarly communication | 0.015 | 0.036 |
| Open science | 0.002 | 0.008 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.007 | 0.004 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".