Extending ChatGPT with a Browserless System for Web Product Price Extraction
Jorge Lloret-Gazo
TL;DR
This paper tackles enabling ChatGPT to answer real-time web price queries by integrating a browserless price extractor (Wextractor). It extends Wextractor with social extraction and pointing pattern extraction to speed and diversify retrieval, and demonstrates a SQL-based implementation with a three-tier workflow (social, pointing-pattern, from-scratch). Through simulation on a 735-page dataset, it achieves an 86.26% success rate and shows potential gains by manual pointing-pattern curation. The work contributes a loosely coupled approach to extending LM capabilities for e-commerce price extraction and outlines directions for deeper integration into real-time browsing.
Abstract
With the advenement of ChatGPT, we can find very clean, precise answers to a varied amount of questions. However, for questions such as 'find the price of the lemon cake at zingerman's', the answer looks like 'I can't browse the web right now'. In this paper, we propose a system, called Wextractor, which extends ChatGPT to answer questions as the one mentioned before. Obviously, our system cannot be labeled as `artificial intelligence'. Simply, it offers to cover a kind of transactional search that is not included in the current version of ChatGPT. Moreover, Wextractor includes two improvements with respect to the initial version: social extraction and pointing pattern extraction to improve the answer speed.