Datrics Text2SQL: A Framework for Natural Language to SQL Query Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gladkykh, Tetiana, Kirykov, Kyrylo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916793903218688
author Gladkykh, Tetiana
Kirykov, Kyrylo
author_facet Gladkykh, Tetiana
Kirykov, Kyrylo
contents Text-to-SQL systems enable users to query databases using natural language, democratizing access to data analytics. However, they face challenges in understanding ambiguous phrasing, domain-specific vocabulary, and complex schema relationships. This paper introduces Datrics Text2SQL, a Retrieval-Augmented Generation (RAG)-based framework designed to generate accurate SQL queries by leveraging structured documentation, example-based learning, and domain-specific rules. The system builds a rich Knowledge Base from database documentation and question-query examples, which are stored as vector embeddings and retrieved through semantic similarity. It then uses this context to generate syntactically correct and semantically aligned SQL code. The paper details the architecture, training methodology, and retrieval logic, highlighting how the system bridges the gap between user intent and database structure without requiring SQL expertise.
format Preprint
id arxiv_https___arxiv_org_abs_2506_12234
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Datrics Text2SQL: A Framework for Natural Language to SQL Query Generation
Gladkykh, Tetiana
Kirykov, Kyrylo
Databases
Artificial Intelligence
Computation and Language
H.2.3; I.2.7
Text-to-SQL systems enable users to query databases using natural language, democratizing access to data analytics. However, they face challenges in understanding ambiguous phrasing, domain-specific vocabulary, and complex schema relationships. This paper introduces Datrics Text2SQL, a Retrieval-Augmented Generation (RAG)-based framework designed to generate accurate SQL queries by leveraging structured documentation, example-based learning, and domain-specific rules. The system builds a rich Knowledge Base from database documentation and question-query examples, which are stored as vector embeddings and retrieved through semantic similarity. It then uses this context to generate syntactically correct and semantically aligned SQL code. The paper details the architecture, training methodology, and retrieval logic, highlighting how the system bridges the gap between user intent and database structure without requiring SQL expertise.
title Datrics Text2SQL: A Framework for Natural Language to SQL Query Generation
topic Databases
Artificial Intelligence
Computation and Language
H.2.3; I.2.7
url https://arxiv.org/abs/2506.12234