The Stretto Execution Engine for LLM-Augmented Data Systems

TL;DR

Stretto is an execution engine for LLM-augmented data systems that optimally balances runtime efficiency and accuracy through a novel query planning approach and flexible operator implementations.

Contribution

It introduces a holistic query planning method using constrained optimization and a new KV-caching technique for fine-grained execution choices.

Findings

Outperforms existing systems in efficiency and accuracy guarantees.

Effectively manages runtime-accuracy trade-offs in LLM-augmented data queries.

Provides end-to-end query guarantees with optimized operator selection.

Abstract

LLM-augmented data systems enable semantic querying over structured and unstructured data, but executing queries with LLM-powered operators introduces a fundamental runtime-accuracy trade-off. In this paper, we present Stretto, a new execution engine that provides end-to-end query guarantees while efficiently navigating this trade-off in a holistic manner. For this, Stretto formulates query planning as a constrained optimization problem and uses a gradient-based optimizer to jointly select operator implementations and allocate error budgets across pipelines. Moreover, to enable fine-grained execution choices, Stretto introduces a novel idea on how KV-caching can be used to realize a spectrum of different physical operators that transform a sparse design space into a dense continuum of runtime-accuracy trade-offs. Experiments show that Stretto outperforms state-of-the-art systems while consistently meeting quality guarantees.