iPDB -- Optimizing SQL Queries with ML and LLM Predicates

2026-01-23

AI Summary

This work addresses the limitations of traditional SQL and relational databases in efficiently supporting semantic queries for machine learning (ML) and large language models (LLMs), which often necessitate complex engineering and data migration. To overcome this, the paper proposes iPDB, a system that natively integrates ML/LLM inference capabilities within the database by extending SQL syntax to support semantic projection, selection, join, and grouping operations. The key innovations include the introduction of relational prediction operators and a semantic query optimization mechanism, enabling the first unified SQL framework that seamlessly and efficiently combines classical relational algebra with model-based inference. Experimental results demonstrate that iPDB allows concise expression of semantic queries in SQL while achieving superior execution efficiency compared to state-of-the-art approaches.

Technology Category

Machine Learning: Statistical Relational/Logic LearningData Mining & Knowledge Management: Intelligent Query ProcessingNatural Language Processing: Sentence-level Semantics, Textual Inference, etc.

Application Category

Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactionsSearch and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved informationUser Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Structured Query Language (SQL) has remained the standard query language for databases. SQL is highly optimized for processing structured data laid out in relations. Meanwhile, in the present application development landscape, it is highly desirable to utilize the power of learned models to perform complex tasks. Large language models (LLMs) have been shown to understand and extract information from unstructured textual data. However, SQL as a query language and accompanying relational database systems are either incompatible or inefficient for workloads that require leveraging learned models. This results in complex engineering and multiple data migration operations that move data between the data sources and the model inference platform. In this paper, we present iPDB, a relational system that supports in-database machine learning (ML) and large language model (LLM) inferencing using extended SQL syntax. In iPDB, LLMs and ML calls can function as semantic projects, as predicates to perform semantic selects and semantic joins, or for semantic grouping in group-by clauses. iPDB has a novel relational predict operator and semantic query optimizations that enable users to write and efficiently execute semantic SQL queries, outperforming the state-of-the-art.

Problem

• SQL
• Large Language Models
• In-database Machine Learning
• Semantic Queries
• Relational Databases

Innovation

• in-database ML
• LLM integration
• semantic SQL
• relational predict operator
• query optimization