OASBuilder: Generating OpenAPI Specifications from Online API Documentation with Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lazar, Koren, Vetzler, Matan, Kate, Kiran, Tsay, Jason, Gupta, David Boaz Himanshu, Shinnar, Avraham, Vallam, Rohith D, Goldbraich, David Amid Esther, Uziel, Guy, Laredo, Jim, Tavor, Ateret Anaby
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912471632052224
author Lazar, Koren
Vetzler, Matan
Kate, Kiran
Tsay, Jason
Gupta, David Boaz Himanshu
Shinnar, Avraham
Vallam, Rohith D
Goldbraich, David Amid Esther
Uziel, Guy
Laredo, Jim
Tavor, Ateret Anaby
author_facet Lazar, Koren
Vetzler, Matan
Kate, Kiran
Tsay, Jason
Gupta, David Boaz Himanshu
Shinnar, Avraham
Vallam, Rohith D
Goldbraich, David Amid Esther
Uziel, Guy
Laredo, Jim
Tavor, Ateret Anaby
contents AI agents and business automation tools interacting with external web services require standardized, machine-readable information about their APIs in the form of API specifications. However, the information about APIs available online is often presented as unstructured, free-form HTML documentation, requiring external users to spend significant time manually converting it into a structured format. To address this, we introduce OASBuilder, a novel framework that transforms long and diverse API documentation pages into consistent, machine-readable API specifications. This is achieved through a carefully crafted pipeline that integrates large language models and rule-based algorithms which are guided by domain knowledge of the structure of documentation webpages. Our experiments demonstrate that OASBuilder generalizes well across hundreds of APIs, and produces valid OpenAPI specifications that encapsulate most of the information from the original documentation. OASBuilder has been successfully implemented in an enterprise environment, saving thousands of hours of manual effort and making hundreds of complex enterprise APIs accessible as tools for LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2507_05316
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OASBuilder: Generating OpenAPI Specifications from Online API Documentation with Large Language Models
Lazar, Koren
Vetzler, Matan
Kate, Kiran
Tsay, Jason
Gupta, David Boaz Himanshu
Shinnar, Avraham
Vallam, Rohith D
Goldbraich, David Amid Esther
Uziel, Guy
Laredo, Jim
Tavor, Ateret Anaby
Software Engineering
Artificial Intelligence
AI agents and business automation tools interacting with external web services require standardized, machine-readable information about their APIs in the form of API specifications. However, the information about APIs available online is often presented as unstructured, free-form HTML documentation, requiring external users to spend significant time manually converting it into a structured format. To address this, we introduce OASBuilder, a novel framework that transforms long and diverse API documentation pages into consistent, machine-readable API specifications. This is achieved through a carefully crafted pipeline that integrates large language models and rule-based algorithms which are guided by domain knowledge of the structure of documentation webpages. Our experiments demonstrate that OASBuilder generalizes well across hundreds of APIs, and produces valid OpenAPI specifications that encapsulate most of the information from the original documentation. OASBuilder has been successfully implemented in an enterprise environment, saving thousands of hours of manual effort and making hundreds of complex enterprise APIs accessible as tools for LLMs.
title OASBuilder: Generating OpenAPI Specifications from Online API Documentation with Large Language Models
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2507.05316