Making Databases Searchable with Deep Context

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Jindal, Alekh, Qiao, Shi, Tripathi, Shivani, Debnath, Niloy, Singh, Kunal, Nema, Pushpanjali, Prakash, Sharath, Halder, Aditya, PR, Ronith, Mohammed, Sadiq, Hameed, Abdul, Hanswadkar, Karan, Kshitij, Ayush, Bhatt, Sarthak, Chatterjee, Rony, Pandey, Jyoti, Pavlopoulou, Christina, Shetye, Ravi
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912905941745664
author Jindal, Alekh
Qiao, Shi
Tripathi, Shivani
Debnath, Niloy
Singh, Kunal
Nema, Pushpanjali
Prakash, Sharath
Halder, Aditya
PR, Ronith
Mohammed, Sadiq
Hameed, Abdul
Hanswadkar, Karan
Kshitij, Ayush
Bhatt, Sarthak
Chatterjee, Rony
Pandey, Jyoti
Pavlopoulou, Christina
Shetye, Ravi
author_facet Jindal, Alekh
Qiao, Shi
Tripathi, Shivani
Debnath, Niloy
Singh, Kunal
Nema, Pushpanjali
Prakash, Sharath
Halder, Aditya
PR, Ronith
Mohammed, Sadiq
Hameed, Abdul
Hanswadkar, Karan
Kshitij, Ayush
Bhatt, Sarthak
Chatterjee, Rony
Pandey, Jyoti
Pavlopoulou, Christina
Shetye, Ravi
contents Databases are the most critical assets for enterprises, and yet they remain largely inaccessible to people who make the most important decisions. In this paper, we describe the Tursio search platform that builds an abstraction layer, aka semantic knowledge graph, over the underlying databases to make them searchable in natural language. Tursio infuses large language models (LLMs) into every part of the query processing stack, including data modeling, query compilation, query planning, and result reasoning. This allows Tursio to process natural language queries systematically using techniques from traditional query planning and rewriting, rather than black-box memorization. We describe the architecture of Tursio in detail and present a comprehensive evaluation on production workloads, and synthetic and realistic benchmarks. Our results show that Tursio achieves high accuracy while being efficient and scalable, making databases truly searchable for non-expert users.
format Preprint
id arxiv_https___arxiv_org_abs_2602_08320
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Making Databases Searchable with Deep Context
Jindal, Alekh
Qiao, Shi
Tripathi, Shivani
Debnath, Niloy
Singh, Kunal
Nema, Pushpanjali
Prakash, Sharath
Halder, Aditya
PR, Ronith
Mohammed, Sadiq
Hameed, Abdul
Hanswadkar, Karan
Kshitij, Ayush
Bhatt, Sarthak
Chatterjee, Rony
Pandey, Jyoti
Pavlopoulou, Christina
Shetye, Ravi
Databases
Databases are the most critical assets for enterprises, and yet they remain largely inaccessible to people who make the most important decisions. In this paper, we describe the Tursio search platform that builds an abstraction layer, aka semantic knowledge graph, over the underlying databases to make them searchable in natural language. Tursio infuses large language models (LLMs) into every part of the query processing stack, including data modeling, query compilation, query planning, and result reasoning. This allows Tursio to process natural language queries systematically using techniques from traditional query planning and rewriting, rather than black-box memorization. We describe the architecture of Tursio in detail and present a comprehensive evaluation on production workloads, and synthetic and realistic benchmarks. Our results show that Tursio achieves high accuracy while being efficient and scalable, making databases truly searchable for non-expert users.
title Making Databases Searchable with Deep Context
topic Databases
url https://arxiv.org/abs/2602.08320