iPDB -- Optimizing Semantic SQL Queries

TL;DR

iPDB introduces an extended SQL system enabling efficient in-database ML and LLM inference, significantly improving semantic query performance over existing systems.

Contribution

The paper presents iPDB, a novel relational system with semantic query optimizations supporting in-database ML and LLM inferencing using extended SQL syntax.

Findings

iPDB outperforms state-of-the-art systems by 2.5x on average.

Speedups of up to 30x were achieved with iPDB.

Supports semantic projects, predicates, and aggregations within SQL queries.

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 aggregations in group-by clauses. iPDB has a new relational predict operator along with semantic query optimizations that enable users to write and efficiently execute semantic SQL queries, outperforming other state-of-the-art systems by 2.5x mean speedup, with speedups of up to 30x.