OpenAI for OpenAPI: Automated generation of REST API specification via LLMs

TL;DR

This paper introduces OOPS, a technology-agnostic LLM-based static analysis tool that automatically generates high-quality OpenAPI specifications for REST APIs across diverse programming languages and frameworks.

Contribution

It presents the first LLM-based static analysis method for OAS generation that reduces reliance on language-specific rules and human intervention, improving accuracy and applicability.

Findings

Achieves over 98% F1-score in endpoint method inference

Attains 97% accuracy in request parameter and response inference

Generates OAS with high token efficiency and low hallucination rates

Abstract

REST APIs, based on the REpresentational State Transfer (REST) architecture, are the primary type of Web API. The OpenAPI Specification (OAS) serves as the de facto standard for describing REST APIs and is crucial for multiple software engineering tasks. However, developers face challenges in writing and maintaining OAS. Although static analysis shows potential for OAS generation, it is limited to specific programming languages and development frameworks. The powerful code understanding capabilities of LLMs offer new opportunities for OAS generation, yet they are constrained by context limitations and hallucinations. To address these challenges, we propose the OpenAI OpenAPI Project Scanner (OOPS), the first technology-agnostic LLM-based static analysis method for OAS generation, requiring fewer technology-specific rules and less human expert intervention. OOPS is implemented as an LLM agent workflow comprising two key steps: endpoint method extraction and OAS generation. By constructing an API dependency graph, it establishes necessary file associations to address LLMs' context limitations. Through multi-stage generation and self-refine, it mitigates both syntactic and semantic hallucinations during OAS generation. We evaluated OOPS on 12 real-world REST APIs spanning 5 programming languages and 8 development frameworks. Experimental results demonstrate that OOPS accurately generates high-quality OAS for REST APIs implemented with diverse technologies, achieving an average F1-score exceeding 98% for endpoint method inference, 97% for both request parameter and response inference, and 92% for parameter constraint inference. The input tokens average below 5.6K with a maximum of 16.2K, while the output tokens average below 0.9K with a maximum of 7.7K.