Bridging the Gap: Enabling Natural Language Queries for NoSQL Databases through Text-to-NoSQL Translation

2025-02-16

AI Summary

To address the challenge that non-technical users face in directly querying NoSQL databases, this paper proposes an end-to-end natural language-to-NoSQL query translation method. We formally define the Text-to-NoSQL task for the first time and introduce TEND—the first large-scale, open-source benchmark dataset comprising over 12,000 high-quality natural language–NoSQL query pairs. We propose SMART, a multi-step reasoning framework integrating small language models (SLMs) with retrieval-augmented generation (RAG), enhanced by automated data synthesis and execution-level evaluation. Experiments on TEND demonstrate substantial improvements in query accuracy and executability, establishing a new state-of-the-art (SOTA) baseline and enabling seamless interaction with real-world NoSQL systems. Our core contributions span four dimensions: (1) formal task definition, (2) construction of the first large-scale Text-to-NoSQL benchmark, (3) design of a lightweight yet effective SLM-RAG framework, and (4) introduction of an execution-grounded evaluation paradigm.

Technology Category

• Natural Language Processing: Question Answering
• Data Mining & Knowledge Management: Intelligent Query Processing
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs

Abstract

NoSQL databases have become increasingly popular due to their outstanding performance in handling large-scale, unstructured, and semi-structured data, highlighting the need for user-friendly interfaces to bridge the gap between non-technical users and complex database queries. In this paper, we introduce the Text-to-NoSQL task, which aims to convert natural language queries into NoSQL queries, thereby lowering the technical barrier for non-expert users. To promote research in this area, we developed a novel automated dataset construction process and released a large-scale and open-source dataset for this task, named TEND (short for Text-to-NoSQL Dataset). Additionally, we designed a SLM (Small Language Model)-assisted and RAG (Retrieval-augmented Generation)-assisted multi-step framework called SMART, which is specifically designed for Text-to-NoSQL conversion. To ensure comprehensive evaluation of the models, we also introduced a detailed set of metrics that assess the model's performance from both the query itself and its execution results. Our experimental results demonstrate the effectiveness of our approach and establish a benchmark for future research in this emerging field. We believe that our contributions will pave the way for more accessible and intuitive interactions with NoSQL databases.

Problem

• Convert natural language to NoSQL queries
• Develop automated dataset construction process
• Design multi-step framework for Text-to-NoSQL conversion

Innovation

• Text-to-NoSQL task introduced
• SMART framework for conversion
• Open-source dataset TEND created